技术领域Technical Field
本申请涉及照明领域，特别是涉及照明告警方法、装置和系统。The present application relates to the field of lighting, and in particular to a lighting alarm method, device and system.
背景技术Background Art
传统技术中，当智能照明灯检测到照明范围内发生包括人体运动、物体运动等变化时，自动启动照明。但智能照明灯无法区分经过的人的具体身份，因此，智能照明灯无法根据经过的人的具体身份判断是否需要报警，无法根据进行报警需求实现照明方式的调整。In traditional technology, when smart lighting detects changes in the lighting range, such as human movement or object movement, it automatically starts lighting. However, smart lighting cannot distinguish the specific identity of the person passing by. Therefore, smart lighting cannot determine whether an alarm is needed based on the specific identity of the person passing by, and cannot adjust the lighting mode according to the alarm needs.
针对相关技术中存在无法准确根据监控区域内用户信息调整照明方式的问题，目前还没有提出有效的解决方案。There is currently no effective solution to the problem in related technologies that the lighting method cannot be accurately adjusted according to user information in the monitored area.
发明内容Summary of the invention
基于此，有必要针对上述技术问题，提供一种能够解决无法准确根据监控区域内用户信息调整照明方式的照明告警方法、装置和系统。Based on this, it is necessary to provide a lighting alarm method, device and system that can solve the problem of being unable to accurately adjust the lighting mode according to user information in the monitored area in response to the above technical problems.
第一个方面，在本实施例中提供了一种照明告警方法，所述方法包括：In a first aspect, a lighting alarm method is provided in this embodiment, and the method includes:
在检测到监控区域内存在人体的情况下，根据所述监控区域的监控图像得到所述人体的面部特征；When a human body is detected in the monitoring area, facial features of the human body are obtained according to the monitoring image of the monitoring area;
判断所述面部特征是否与预设特征匹配；Determining whether the facial features match preset features;
若所述面部特征与所述预设特征不匹配，则执行第一照明策略；If the facial features do not match the preset features, executing a first lighting strategy;
若所述面部特征与所述预设特征匹配，则执行第二照明策略。If the facial features match the preset features, a second lighting strategy is executed.
在其中的一些实施例中，在执行第一照明策略之后，所述方法还包括：In some of the embodiments, after executing the first lighting strategy, the method further includes:
判断所述面部特征与所述预设特征不匹配的次数是否达到预设次数；Determining whether the number of times that the facial feature does not match the preset feature reaches a preset number;
若否，则返回执行根据所述监控图像得到所述人体的面部特征，判断所述面部特征是否与预设特征匹配的步骤，直至判断到面部特征与预设特征不匹配的次数达到所述预设次数，生成并存储告警信息。If not, return to the step of obtaining the facial features of the human body according to the monitoring image and determining whether the facial features match the preset features, until the number of times the facial features do not match the preset features reaches the preset number, and generate and store alarm information.
在其中的一些实施例中，所述生成告警信息，包括：In some embodiments, generating warning information includes:
获取所述监控区域的监控视频，所述监控视频的各视频帧皆包含与所述预设特征匹配的面部特征；Acquire a surveillance video of the surveillance area, wherein each video frame of the surveillance video contains a facial feature matching the preset feature;
根据所述监控图像和所述监控视频生成所述告警信息，其中，所述告警信息包括：所述监控图像的获取时间、所述监控图像中人体的面部图像、所述监控视频。The alarm information is generated according to the surveillance image and the surveillance video, wherein the alarm information includes: the acquisition time of the surveillance image, the facial image of the human body in the surveillance image, and the surveillance video.
在其中的一些实施例中，所述执行第一照明策略，包括：In some embodiments, executing the first lighting strategy includes:
基于预设的照明参数运行照明装置；operating the lighting device based on preset lighting parameters;
基于声音装置播放预设音频；Playing preset audio based on the sound device;
生成告警信号，并将所述告警信号传输至监控平台。An alarm signal is generated and transmitted to a monitoring platform.
在其中的一些实施例中，在检测到监控区域内存在人体的情况下，根据所述监控区域的监控图像得到所述人体的面部特征之前，所述方法还包括：In some of the embodiments, when a human body is detected in a monitoring area, before obtaining facial features of the human body according to a monitoring image of the monitoring area, the method further includes:
获取所述监控区域内的温度变化数据；Acquire temperature change data in the monitoring area;
根据所述温度变化数据，判断所述监控区域内的温度变化是否处于阈值范围内；According to the temperature change data, determining whether the temperature change in the monitoring area is within a threshold range;
若是，则判断所述监控区域存在人体并采集对应于所述人体的所述监控图像。If so, it is determined that there is a human body in the monitoring area and the monitoring image corresponding to the human body is collected.
在其中的一些实施例中，所述根据所述监控区域的监控图像得到所述人体的面部特征，包括：In some embodiments, obtaining the facial features of the human body according to the monitoring image of the monitoring area includes:
将多张包含所述人体的面部的监控图像转化为多个向量；Converting a plurality of surveillance images containing the face of the human body into a plurality of vectors;
计算各所述向量的平均值，以及各所述向量与所述平均值之间的第一差值；Calculating an average value of each of the vectors and a first difference between each of the vectors and the average value;
根据各所述第一差值构建矩阵，得到所述矩阵的多个特征向量；constructing a matrix according to each of the first differences, and obtaining a plurality of eigenvectors of the matrix;
根据所述矩阵的特征向量、与所述特征向量对应的第一差值的乘积，计算得到各监控图像中人体的面部的特征向量；Calculate the feature vector of the face of the human body in each monitoring image according to the product of the feature vector of the matrix and the first difference value corresponding to the feature vector;
根据所述监控图像、与所述监控图像对应的第一差值和特征向量，得到各张包含所述人体的面部的监控图像的权重向量；Obtaining a weight vector of each monitoring image including the face of the human body according to the monitoring image, the first difference corresponding to the monitoring image, and the feature vector;
根据所述权重向量得到所述人体的面部特征。The facial features of the human body are obtained according to the weight vector.
在其中的一些实施例中，所述判断所述面部特征是否与预设特征匹配，包括：In some embodiments, determining whether the facial feature matches a preset feature includes:
获取所述面部特征的向量长度和所述预设特征的向量长度；Obtaining the vector length of the facial feature and the vector length of the preset feature;
判断所述面部特征的向量长度和所述预设特征的向量长度之间的差值是否小于设定的阈值；Determining whether a difference between the vector length of the facial feature and the vector length of the preset feature is less than a set threshold;
若是，则判断所述面部特征和所述预设特征匹配；If so, determining that the facial feature matches the preset feature;
若否，则判断所述面部特征和所述预设特征不匹配。If not, it is determined that the facial feature does not match the preset feature.
第二个方面，在本实施例中提供了一种照明告警装置，所述装置包括：In a second aspect, in this embodiment, a lighting warning device is provided, the device comprising:
提取模块，用于根据监控区域内的监控图像，得到所述监控图像中人体的面部特征；An extraction module, used to obtain facial features of a human body in a surveillance image according to the surveillance image in the surveillance area;
判断模块，用于判断所述面部特征是否与预设特征匹配；A judging module, used to judge whether the facial features match the preset features;
第一执行模块，用于在所述面部特征与所述预设特征不匹配的情况下，执行第一照明策略；A first execution module, configured to execute a first lighting strategy when the facial feature does not match the preset feature;
第二执行模块，用于在所述面部特征与所述预设特征匹配的情况下，执行第二照明策略。The second execution module is used to execute a second lighting strategy when the facial feature matches the preset feature.
第三个方面，在本实施例中提供了一种照明告警系统，所述系统包括：检测器、处理器和照明系统，所述检测器与所述处理器连接，所述处理器与所述照明系统连接；其中，In a third aspect, a lighting alarm system is provided in this embodiment, the system comprising: a detector, a processor and a lighting system, the detector is connected to the processor, and the processor is connected to the lighting system; wherein,
所述检测器用于获取监控区域的监控图像；The detector is used to obtain a monitoring image of the monitoring area;
所述处理器用于在检测到所述监控区域内存在人体的情况下，根据所述监控区域的监控图像得到所述人体的面部特征；判断所述面部特征是否与预设特征匹配；若所述面部特征与所述预设特征不匹配，则生成第一信号，若所述面部特征与所述预设特征匹配，则生成第二信号；The processor is used to, when detecting the presence of a human body in the monitoring area, obtain the facial features of the human body according to the monitoring image of the monitoring area; determine whether the facial features match the preset features; if the facial features do not match the preset features, generate a first signal; if the facial features match the preset features, generate a second signal;
所述照明系统，用于响应于所述第一信号执行第一照明策略，和/或响应于所述第二信号执行第二照明策略。The lighting system is configured to execute a first lighting strategy in response to the first signal, and/or execute a second lighting strategy in response to the second signal.
在其中的一些实施例中，照明告警系统还包括通信器，所述通信器的一端与所述处理器连接，所述通信器的另一端与所述照明系统连接。In some of the embodiments, the lighting alarm system further includes a communicator, one end of the communicator is connected to the processor, and the other end of the communicator is connected to the lighting system.
上述照明告警方法、装置和系统，通过对比监控区域内人体的面部特征和预设特征，得到监控区域内被检测人体的信息，并基于不同的比较结果执行不同的照明策略，使得照明方式与进入监控区域内的人体信息相适应，实现了监控方法和照明策略的联动，解决了无法准确根据监控区域内用户信息调整照明方式的问题。The above-mentioned lighting alarm method, device and system obtain the information of the human body detected in the monitoring area by comparing the facial features and preset features of the human body in the monitoring area, and execute different lighting strategies based on different comparison results, so that the lighting mode is adapted to the information of the human body entering the monitoring area, realizing the linkage between the monitoring method and the lighting strategy, and solving the problem that the lighting mode cannot be accurately adjusted according to the user information in the monitoring area.
附图说明BRIEF DESCRIPTION OF THE DRAWINGS
图1为一个实施例中照明告警方法的应用环境图；FIG1 is a diagram showing an application environment of a lighting alarm method according to an embodiment;
图2为一个实施例中照明告警方法的流程示意图；FIG2 is a schematic diagram of a flow chart of a lighting alarm method in one embodiment;
图3为一个实施例中照明告警系统的结构框图；FIG3 is a block diagram of a lighting alarm system in one embodiment;
图4为一个实施例中照明告警方法的优选结构框图；FIG4 is a block diagram of a preferred structure of a lighting alarm method in one embodiment;
图5为一个实施例中基于人体传感器的监控照明方法的流程示意图；FIG5 is a schematic diagram of a process of a monitoring lighting method based on a human body sensor in one embodiment;
图6为一个实施例中照明告警装置的结构框图；FIG6 is a structural block diagram of a lighting alarm device in one embodiment;
图7为一个实施例中计算机设备的内部结构图。FIG. 7 is a diagram showing the internal structure of a computer device in one embodiment.
具体实施方式DETAILED DESCRIPTION
为了使本申请的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本申请进行进一步详细说明。应当理解，此处描述的具体实施例仅仅用以解释本申请，并不用于限定本申请。In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.
本申请实施例提供的照明告警方法，可以应用于如图1所示的应用环境中。其中，终端102通过网络与服务器104进行通信。数据存储系统可以存储服务器104需要处理的数据。数据存储系统可以集成在服务器104上，也可以放在云上或其他网络服务器上。通过终端102，或者服务器104，或者包括终端102和服务器104的系统，执行照明告警方法，确定执行第一照明策略或者第二照明策略。其中，终端102可以但不限于是各种个人计算机、笔记本电脑、智能手机、平板电脑等设备。服务器104可以用独立的服务器或者是多个服务器组成的服务器集群来实现。The lighting alarm method provided in the embodiment of the present application can be applied in the application environment as shown in FIG. 1 . The terminal 102 communicates with the server 104 through a network. The data storage system can store data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. The lighting alarm method is executed through the terminal 102, or the server 104, or a system including the terminal 102 and the server 104 to determine whether to execute the first lighting strategy or the second lighting strategy. The terminal 102 can be, but is not limited to, various personal computers, laptops, smart phones, tablet computers and other devices. The server 104 can be implemented with an independent server or a server cluster consisting of multiple servers.
在一个实施例中，如图2所示，提供了一种照明告警方法，以该方法应用于图1中的终端102为例进行说明，包括以下步骤：In one embodiment, as shown in FIG. 2 , a lighting alarm method is provided, and the method is applied to the terminal 102 in FIG. 1 as an example for description, including the following steps:
步骤202，在检测到监控区域内存在人体的情况下，根据监控区域的监控图像得到人体的面部特征。Step 202, when a human body is detected in the monitoring area, facial features of the human body are obtained according to the monitoring image of the monitoring area.
其中，人体的面部特征可以是监控图像中人体面部边缘信息，例如，脸部轮廓、眼睛轮廓等信息，也可以是人体面部关键特征点之间的位置信息，例如眼睛、鼻子和嘴巴的位置信息。可选地，通过监控设备对监控区域进行检测，基于监控设备检测到监控区域内存在人体后，获取监控图像。对监控图像进行图像识别和检测，确定人体面部并得到人体面部特征。The facial features of a human body may be the edge information of the human face in the monitoring image, such as the facial contour, eye contour and other information, or the position information between key feature points of the human face, such as the position information of the eyes, nose and mouth. Optionally, the monitoring area is detected by a monitoring device, and a monitoring image is acquired after the monitoring device detects that there is a human body in the monitoring area. Image recognition and detection are performed on the monitoring image to determine the human face and obtain the facial features of the human body.
步骤204，判断面部特征是否与预设特征匹配。Step 204, determining whether the facial features match the preset features.
其中，预设特征为预先存储于数据存储系统中的人体面部特征。可选地，通过采集用户的面部图像，得到用户的人体面部特征，将用户的人体面部特征作为预设特征存储于数据存储系统中。The preset features are human facial features pre-stored in the data storage system. Optionally, the user's facial features are obtained by collecting the user's facial image, and the user's facial features are stored in the data storage system as preset features.
可选地，在判断到面部特征与预设特征一致的情况下，判断面部特征与预设特征匹配；否则，面部特征与预设特征不匹配。或者，对比面部特征与预设特征之间的相似度，在判断到面部特征与预设特征之间的相似度达到指定程度的情况下，判断面部特征与预设特征匹配；否则，面部特征与预设特征不匹配。Optionally, if it is determined that the facial features are consistent with the preset features, the facial features are determined to match the preset features; otherwise, the facial features do not match the preset features. Alternatively, the facial features are compared with the preset features for similarity, and if it is determined that the facial features have a predetermined degree of similarity, the facial features are determined to match the preset features; otherwise, the facial features do not match the preset features.
步骤206，若面部特征与预设特征不匹配，则执行第一照明策略。Step 206: If the facial features do not match the preset features, the first lighting strategy is executed.
其中，第一照明策略用于打开或关闭指定的照明设备，或者调整照明设备发出的光的颜色、频率、光强等等工作参数。可选地，以预设特征为用户的人体面部特征为例，若根据监控图像得到的面部特征与预设特征不匹配，则判断监控区域内的人体为身份信息未存储于数据存储系统中陌生人，通过执行第一照明策略可以达到基于照明设备发射的光信号进行告警的效果。The first lighting strategy is used to turn on or off a specified lighting device, or to adjust the color, frequency, light intensity, and other working parameters of the light emitted by the lighting device. Optionally, taking the preset features as the facial features of a user as an example, if the facial features obtained from the monitoring image do not match the preset features, the human body in the monitoring area is judged to be a stranger whose identity information is not stored in the data storage system, and the effect of issuing an alarm based on the light signal emitted by the lighting device can be achieved by executing the first lighting strategy.
步骤208，若面部特征与预设特征匹配，则执行第二照明策略。Step 208: If the facial features match the preset features, a second lighting strategy is executed.
其中，第二照明策略也用于打开或关闭指定的照明设备，或者调整照明设备发出的光的颜色、频率、光强等等参数。第一照明策略和第二照明策略控制的照明设备和/或照明设备工作参数不同。可选地，以预设特征为用户的人体面部特征为例，根据监控图像得到的面部特征与预设特征匹配，则判断监控区域内的人体为用户的情况下，通过执行第二照明策略为用户提供预先设置的灯光。The second lighting strategy is also used to turn on or off a specified lighting device, or to adjust the color, frequency, light intensity, and other parameters of the light emitted by the lighting device. The lighting devices and/or lighting device operating parameters controlled by the first lighting strategy and the second lighting strategy are different. Optionally, taking the preset features as the facial features of the user as an example, if the facial features obtained from the monitoring image match the preset features, then if it is determined that the person in the monitoring area is the user, the second lighting strategy is executed to provide the user with the preset light.
上述照明告警方法中，通过获取监控区域内人体的面部特征，以及面部特征与预设特征之间的比较结果，确定监控区域内被检测人体的信息，并基于不同的比较结果执行不同的照明策略，使得照明方式与进入监控区域内的人体信息相适应，实现了监控方法和照明策略的联动，解决了无法准确根据监控区域内用户信息调整照明方式的问题。In the above-mentioned lighting alarm method, the information of the detected human body in the monitoring area is determined by obtaining the facial features of the human body in the monitoring area and the comparison results between the facial features and the preset features, and different lighting strategies are executed based on different comparison results, so that the lighting mode is adapted to the information of the human body entering the monitoring area, thereby realizing the linkage between the monitoring method and the lighting strategy, and solving the problem of being unable to accurately adjust the lighting mode according to the user information in the monitoring area.
在一个实施例中，在执行第一照明策略之后，方法还包括：判断面部特征与预设特征不匹配的次数是否达到预设次数；若否，则返回执行根据监控图像得到人体的面部特征，判断面部特征是否与预设特征匹配的步骤，直至判断到面部特征与预设特征不匹配的次数达到预设次数，生成并存储告警信息。In one embodiment, after executing the first lighting strategy, the method further includes: determining whether the number of times the facial features do not match the preset features reaches a preset number; if not, returning to execute the step of obtaining the facial features of the human body based on the monitoring image and determining whether the facial features match the preset features, until it is determined that the number of times the facial features do not match the preset features reaches a preset number, and generating and storing an alarm message.
其中，告警信息可以是预设的信号、文本，也可以是包含人体的面部特征的监控图像、监控区域出现人体的时间等等信息。在返回执行根据监控图像得到人体的面部特征，判断面部特征是否与预设特征匹配的步骤后，若再次判断到面部特征与预设特征不匹配，则判断面部特征与预设特征不匹配的次数增加一次。The alarm information may be a preset signal, text, or a monitoring image containing facial features of a human body, the time when a human body appears in the monitoring area, etc. After returning to the step of obtaining facial features of a human body according to the monitoring image and determining whether the facial features match the preset features, if it is determined again that the facial features do not match the preset features, the number of times the facial features are determined to not match the preset features increases by one.
可选地，若重复执行判断面部特征是否与预设特征匹配的步骤后，得到的判断结果不同，则生成告警信息后对告警信息进行打标，由人工进行校验，避免判断错误的情况。在人工校验通过的情况下，存储这一告警信息。或者，还可以将告警信息传输至监控平台。Optionally, if the judgment results obtained after repeatedly executing the step of determining whether the facial features match the preset features are different, the alarm information is marked after it is generated and manually verified to avoid misjudgment. If the manual verification passes, the alarm information is stored. Alternatively, the alarm information can also be transmitted to the monitoring platform.
进一步地，生成告警信息，包括：获取监控区域的监控视频，监控视频的各视频帧皆包含与预设特征匹配的面部特征；根据监控图像和监控视频生成告警信息，其中，告警信息包括：监控图像的获取时间、监控图像中人体的面部图像、监控视频。其中，监控图像的获取时间包括人体出现在监控区域中的起始时间和结束时间。可选地，根据监控视频还可以得到被检测的人体出现在监控区域中总时长等视频信息。Furthermore, generating alarm information includes: obtaining a surveillance video of the surveillance area, wherein each video frame of the surveillance video contains facial features that match the preset features; generating alarm information based on the surveillance image and the surveillance video, wherein the alarm information includes: the acquisition time of the surveillance image, the facial image of the human body in the surveillance image, and the surveillance video. The acquisition time of the surveillance image includes the start time and the end time when the human body appears in the surveillance area. Optionally, video information such as the total duration of the detected human body appearing in the surveillance area can also be obtained based on the surveillance video.
本实施例中，通过重复执行面部特征提取和匹配的步骤，直至面部特征与预设特征不匹配的次数达到预设次数，可以确保面部特征匹配的准确性，从而增加告警信息的可性度。In this embodiment, by repeatedly executing the steps of facial feature extraction and matching until the number of times that the facial features do not match the preset features reaches a preset number, the accuracy of facial feature matching can be ensured, thereby increasing the reliability of the alarm information.
在一个实施例中，执行第一照明策略，包括：基于预设的照明参数运行照明装置；基于声音装置播放预设音频；生成告警信号，并将告警信号传输至监控平台。In one embodiment, executing a first lighting strategy includes: operating a lighting device based on preset lighting parameters; playing preset audio based on a sound device; generating an alarm signal, and transmitting the alarm signal to a monitoring platform.
其中，照明装置可以安装于监控区域内，也可以安装于监控区域外。可选地，根据第二照明策略得到预设的照明参数。照明参数包括但不限于装置发光频率、光强、发光颜色等等。当照明装置基于预设的照明参数能够起到警示用户监控区域出现了面部特征与预设特征的被检测对象的效果。其中，第一照明策略对应的照明参数与第二照明策略不同。声音装置包括播放器、喇叭等音频播放设备，预设音频用于警告用户监控区域中出现面部特征与预设特征不匹配的对象。监控平台包括但不限于用户终端、管理平台。可选地，若照明告警系统的应用场景为家庭照明系统，则监控平台为社区管理系统或者用户终端所在平台；若应用场景为公共场所例如工厂、办公园区、医院等，则监控平台为公共场所的管理系统。Wherein, the lighting device can be installed in the monitoring area or outside the monitoring area. Optionally, preset lighting parameters are obtained according to the second lighting strategy. The lighting parameters include but are not limited to the device's light frequency, light intensity, light color, etc. When the lighting device is based on the preset lighting parameters, it can play the effect of alerting the user that a detected object with facial features and preset features appears in the monitoring area. Wherein, the lighting parameters corresponding to the first lighting strategy are different from the second lighting strategy. The sound device includes audio playback devices such as players and speakers, and the preset audio is used to warn the user that an object with facial features that do not match the preset features appears in the monitoring area. The monitoring platform includes but is not limited to a user terminal and a management platform. Optionally, if the application scenario of the lighting alarm system is a home lighting system, the monitoring platform is a community management system or a platform where the user terminal is located; if the application scenario is a public place such as a factory, office park, hospital, etc., the monitoring platform is a management system for a public place.
本实施例中，通过预设的照明参数运行照明装置、播放预设音频、传输告警信号至监控平台的方式，从而结合声音信号、光信号和电信号实现监控区域的告警，增强用户感知，使得用户可以通过多种方式快速地得到监控区域的告警情况，避免了监控区域的告警情况传递不及时的问题。In this embodiment, the lighting device is operated according to preset lighting parameters, preset audio is played, and the alarm signal is transmitted to the monitoring platform, thereby combining sound signals, light signals and electrical signals to realize the alarm of the monitored area, enhancing user perception, so that the user can quickly obtain the alarm status of the monitored area in a variety of ways, avoiding the problem of untimely transmission of the alarm status of the monitored area.
在一个实施例中，在检测到监控区域内存在人体的情况下，根据监控区域的监控图像得到人体的面部特征之前，方法还包括：获取监控区域内的温度变化数据；根据温度变化数据，判断监控区域内的温度变化是否处于阈值范围内；若是，则判断监控区域存在人体并采集对应于人体的监控图像。In one embodiment, when the presence of a human body is detected in the monitoring area, before obtaining the facial features of the human body based on the monitoring image of the monitoring area, the method also includes: obtaining temperature change data in the monitoring area; judging whether the temperature change in the monitoring area is within a threshold range based on the temperature change data; if so, judging that a human body exists in the monitoring area and acquiring a monitoring image corresponding to the human body.
其中，阈值范围根据人体温度和监控区域在无生命体的情况下的环境温度之间的温度差得到。可选地，温度传感器、人体传感器等设备通过热释电效应获取监控区域内的温度变化，在温度变化处于阈值范围内的情况下，生成信号，并将信号传输至监控设备，以获取监控图像。若温度变化不处于阈值范围内，那么监控区域不存在人体，无需获取监控图像并从中获取人体的面部特征。本实施例通过温度变化值，检测监控区域内是否存在人体，方法简单且准确性高。同时，仅在检测到人体的情况下获取监控图像，可以降低监控所需的资源消耗。Among them, the threshold range is obtained according to the temperature difference between the human body temperature and the ambient temperature of the monitored area in the absence of a living body. Optionally, devices such as temperature sensors and human body sensors obtain temperature changes in the monitored area through the pyroelectric effect, and when the temperature change is within the threshold range, a signal is generated and transmitted to the monitoring device to obtain a monitoring image. If the temperature change is not within the threshold range, then there is no human body in the monitored area, and there is no need to obtain a monitoring image and obtain the facial features of the human body therefrom. This embodiment detects whether there is a human body in the monitored area through the temperature change value, and the method is simple and accurate. At the same time, only when a human body is detected, the monitoring image is obtained, which can reduce the resource consumption required for monitoring.
在一个实施例中，根据监控区域的监控图像得到人体的面部特征，包括：将多张包含人体的面部的监控图像转化为多个向量；计算各向量的平均值，以及各向量与平均值之间的第一差值；根据各第一差值构建矩阵，得到矩阵的多个特征向量；根据矩阵的特征向量、与特征向量对应的第一差值的乘积，计算得到各监控图像中人体的面部的特征向量；根据监控图像、与监控图像对应的第一差值和特征向量，得到各张包含人体面部的监控图像的权重向量；根据权重向量得到人体的面部特征。In one embodiment, facial features of a human body are obtained based on surveillance images of a surveillance area, including: converting multiple surveillance images containing human faces into multiple vectors; calculating an average value of each vector and a first difference between each vector and the average value; constructing a matrix based on each first difference to obtain multiple eigenvectors of the matrix; calculating a eigenvector of the human face in each surveillance image based on the product of the eigenvector of the matrix and the first difference corresponding to the eigenvector; obtaining a weight vector of each surveillance image containing the human face based on the surveillance image, the first difference corresponding to the surveillance image and the eigenvector; and obtaining the facial features of the human body based on the weight vector.
可选地，假设采集到N张包括人脸图像信息的监控图像，图片像素个数是N，则得到人脸图像向量Si，i＝1，2，……，N，把每张图像拉成一列，得到矩阵S＝[S1，S2，……，SN]。Optionally, assuming that N surveillance images including facial image information are collected, the number of image pixels is N, then the facial image vector Si is obtained, i=1, 2, ..., N, and each image is pulled into a column to obtain a matrix S=[S1 ,S2 , ...,SN ].
对S进行求和并取平均值计算各向量的平均值，即被检测的人体的平均脸β：将每张人脸图像Si减去平均值β，得到第一差值γi，根据第一差值构成新的矩阵B＝[γ1，γ2，……，γN]。得到矩阵的特征向量C记为X＝[x1，x2，x3，……，xm]。Sum S and take the average value to calculate the average value of each vector, that is, the average face β of the detected human body: Subtract the average value β from each face image Si to obtain the first difference γi , and construct a new matrix B = [γ1 , γ2 , ..., γN ] based on the first difference. The eigenvector C of the obtained matrix is recorded as X = [x1 , x2 , x3 , ..., xm ].
根据与矩阵的特征向量xi、与特征向量对应的第一差值γi的乘积，计算得到各监控图像中人体面部的特征向量：The eigenvector of the human face in each monitoring image is calculated by multiplying the eigenvector xi of the matrix and the first difference γi corresponding to the eigenvector:
根据监控图像，与监控图像对应的第一差值和特征向量，得到各张包含人体面部的监控图像的权重向量包括：对初始的监控图像中所有图片进行权重标识。其中，获取监控图像对应的向量和第一差值之间的第二差值，根据第二差值和特征向量之间的乘积，得到各监控图像的权重：zi＝θi(S–γ)；结合多张监控图像的权重，得到被检测人体面部的权重ZT＝[z1，z2，，……，zi]，其中，ZT表示待检测人脸图像的权重，zi表示初始的监控图像中某个人脸的权重。According to the monitoring image, the first difference value corresponding to the monitoring image and the feature vector, the weight vector of each monitoring image containing a human face is obtained, including: weighting all images in the initial monitoring image. Among them, the second difference value between the vector corresponding to the monitoring image and the first difference value is obtained, and the weight of each monitoring image is obtained according to the product between the second difference value and the feature vector: zi =θi(S–γ); the weight of the detected human face ZT =[z1 ,z2 ,,…,zi ] is obtained by combining the weights of multiple monitoring images, wherein ZT represents the weight of the face image to be detected, and zi represents the weight of a certain face in the initial monitoring image.
进一步地，在一个实施例中，判断面部特征是否与预设特征匹配，包括：获取面部特征的向量长度和预设特征的向量长度；判断面部特征的向量长度和预设特征的向量长度之间的差值是否小于设定的阈值；若是，则判断面部特征和预设特征匹配；若否，则判断面部特征和预设特征不匹配。Further, in one embodiment, determining whether the facial feature matches the preset feature includes: obtaining the vector length of the facial feature and the vector length of the preset feature; determining whether the difference between the vector length of the facial feature and the vector length of the preset feature is less than a set threshold; if so, determining that the facial feature matches the preset feature; if not, determining that the facial feature does not match the preset feature.
可选地，当ZT的向量长度与预设特征的向量长度之间的差值小于设定的阈值时，则认定正在检测的人脸与预设特征对应的人脸吻合，面部特征和预设特征匹配；反之面部特征和预设特征不匹配。其中，设定的阈值大小可以根据应用需求自行设置。Optionally, when the difference between the vector length of ZT and the vector length of the preset feature is less than a set threshold, it is determined that the face being detected is consistent with the face corresponding to the preset feature, and the facial feature matches the preset feature; otherwise, the facial feature does not match the preset feature. The set threshold value can be set according to application requirements.
本实施例中，通过综合多帧监控图像中同一人体面部图像，得到该被检测人体的面部特征向量，提高了面部特征提取结果的准确性。并且，获取、比较面部特征的向量长度和预设特征的向量长度，确定面部特征是否与预设特征匹配的方法简单、快速。In this embodiment, by synthesizing the facial images of the same human body in multiple frames of monitoring images, the facial feature vector of the detected human body is obtained, thereby improving the accuracy of the facial feature extraction result. In addition, the method of obtaining and comparing the vector length of the facial feature and the vector length of the preset feature to determine whether the facial feature matches the preset feature is simple and fast.
本实施例还提供了一种照明告警系统，该装置用于实现上述方法实施例，已经进行过说明的不再赘述。如以下所使用的，术语“模块”、“单元”、“子单元”等可以实现预定功能的软件和/或硬件的组合。尽管以下实施例所描述的装置较佳地以软件来实现，但是硬件，或者软件和硬件的组合的实现也是可能并被构想的。This embodiment also provides a lighting alarm system, which is used to implement the above method embodiment, and the descriptions that have been made will not be repeated. As used below, the terms "module", "unit", "subunit", etc. can implement a combination of software and/or hardware for a predetermined function. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.
在一个实施例中，如图3所示，一种照明告警系统，系统包括：检测器、处理器和照明系统，检测器与处理器连接，处理器与照明系统连接；其中，检测器用于获取监控区域的监控图像；处理器用于在检测到监控区域内存在人体的情况下，根据监控区域的监控图像得到人体的面部特征；判断面部特征是否与预设特征匹配；若面部特征与预设特征不匹配，则生成第一信号，若面部特征与预设特征匹配，则生成第二信号；照明系统，用于响应于第一信号执行第一照明策略，和/或响应于第二信号执行第二照明策略。In one embodiment, as shown in FIG3 , a lighting alarm system includes: a detector, a processor, and a lighting system, wherein the detector is connected to the processor, and the processor is connected to the lighting system; wherein the detector is used to obtain a monitoring image of a monitoring area; the processor is used to obtain facial features of a human body according to the monitoring image of the monitoring area when detecting the presence of a human body in the monitoring area; determine whether the facial features match preset features; if the facial features do not match the preset features, generate a first signal, and if the facial features match the preset features, generate a second signal; the lighting system is used to execute a first lighting strategy in response to the first signal, and/or execute a second lighting strategy in response to the second signal.
进一步地，照明告警系统还包括通信器，通信器的一端与处理器连接，通信器的另一端与照明系统连接。其中，通信器用于实现检测器、处理器、照明系统、存储器的通信。Furthermore, the lighting alarm system further includes a communicator, one end of which is connected to the processor, and the other end of which is connected to the lighting system, wherein the communicator is used to realize communication among the detector, the processor, the lighting system, and the memory.
进一步地，图4是本申请实施例的照明告警系统的优选结构框图，如图4所示，照明告警系统不仅包括检测器、处理器、通信器和照明系统还可以包括存储器，存储器与通信器连接。其中，照明告警系统中的检测器包括：红外检测模块、摄像头和AI算法模块，照明告警系统中的照明系统包括监控平台和智能照明灯。Further, FIG4 is a preferred structural block diagram of the lighting alarm system of the embodiment of the present application. As shown in FIG4, the lighting alarm system includes not only a detector, a processor, a communicator and a lighting system, but also a memory, and the memory is connected to the communicator. Among them, the detector in the lighting alarm system includes: an infrared detection module, a camera and an AI algorithm module, and the lighting system in the lighting alarm system includes a monitoring platform and an intelligent lighting lamp.
基于图4所示的照明告警系统，图5提供了一种基于人体传感器的监控照明方法，包括：Based on the lighting alarm system shown in FIG4 , FIG5 provides a method for monitoring lighting based on a human body sensor, including:
步骤501，人体传感器检测到监控范围内有人进入。Step 501: The human body sensor detects that a person enters the monitoring range.
可选地，通过检测器红外检测模块中的人体传感器对监控区域进行检测，人体传感器根据热释电效应检测到监控区域内温度变化ΔT，当ΔT＝0时，传感器无输出，当ΔT≠0时，即人体传感器检测到监控范围内有人进入，将信号传输至摄像头。Optionally, the monitoring area is detected by the human body sensor in the infrared detection module of the detector. The human body sensor detects the temperature change ΔT in the monitoring area based on the pyroelectric effect. When ΔT=0, the sensor has no output. When ΔT≠0, the human body sensor detects that someone has entered the monitoring range and transmits the signal to the camera.
步骤502，摄像头捕捉画面。Step 502: The camera captures the image.
可选地，摄像头响应于人体传感器输出的信号，对监控区域进行拍摄。Optionally, the camera photographs the monitored area in response to a signal output by a human body sensor.
步骤503，人脸信息传输至AI算法模块。Step 503: The facial information is transmitted to the AI algorithm module.
其中，人脸信息指的是包括人体面部的摄像头捕捉画面。可选地，AI算法模块接收摄像头捕捉的画面，并对人脸识别，得到用于表征检测对象的人脸权重的向量。其中，AI算法模块可以通过边缘检测、卷积神经网络或者深度学习的方法实现人脸权重的获取，也可以基于上述方法实施例中获取人体的面部特征的方法，得到被检测人体面部的权重ZT＝[z1，z2，，……，zi]。可选地，检测器中的摄像头捕捉画面后，还将画面传输至处理器，处理器位于云端平台。Wherein, the facial information refers to a camera-captured picture including a human face. Optionally, the AI algorithm module receives the picture captured by the camera, and recognizes the face to obtain a vector of the face weight used to characterize the detected object. Wherein, the AI algorithm module can obtain the face weight through edge detection, convolutional neural network or deep learning methods, or can obtain the weight ZT = [z1 , z2 ,, ..., zi ] of the detected human face based on the method of obtaining the facial features of the human body in the above method embodiment. Optionally, after the camera in the detector captures the picture, it also transmits the picture to the processor, and the processor is located on the cloud platform.
步骤504，判断被检测对象是否为陌生人，若被检测对象为陌生人则执行步骤505，若被检测对象不是陌生人，则执行步骤508。Step 504, determining whether the detected object is a stranger, if the detected object is a stranger, executing step 505, if the detected object is not a stranger, executing step 508.
可选地，获取样本库，样本库中预先存储有与用户人脸的预设特征。获取被用于表征检测对象的人脸权重的向量，若人脸权重小于设定的阈值，则认定被检测的人脸与样本库中的人脸为同一人，即确认被检测的人脸属于样本库中的已知用户；反之，认定被检测的人脸属于陌生人。或者，在人脸权重的向量长度与预设特征的向量长度之间的差值小于另一设定的阈值的情况下，则认定被检测的人脸属于样本库中的已知用户；反之，认定被检测的人脸属于陌生人。Optionally, a sample library is obtained, in which preset features of the user's face are pre-stored. A vector of face weights used to characterize the detection object is obtained. If the face weight is less than a set threshold, it is determined that the detected face and the face in the sample library are the same person, that is, it is confirmed that the detected face belongs to a known user in the sample library; otherwise, it is determined that the detected face belongs to a stranger. Alternatively, when the difference between the vector length of the face weight and the vector length of the preset feature is less than another set threshold, it is determined that the detected face belongs to a known user in the sample library; otherwise, it is determined that the detected face belongs to a stranger.
步骤505，启动照明监控报警系统。Step 505, start the lighting monitoring alarm system.
可选地，AI算法模块在认定被检测的人脸不属于样本库的已知用户的情况下，输出信号至照明系统中的智能照明灯和监控平台，并启动照明监控报警系统。此时，照明系统基于样本库中已知用户的设定，控制智能照明灯基于第一照明策略运行，通过灯光告警用户监控区域内存在陌生人；照明系统生成告警信号并传输至监控平台。此外，还可以根据AI算法模块输出的信号进行声音报警。Optionally, when the AI algorithm module determines that the detected face does not belong to a known user in the sample library, it outputs a signal to the smart lighting and monitoring platform in the lighting system, and starts the lighting monitoring alarm system. At this time, the lighting system controls the smart lighting to operate based on the first lighting strategy based on the settings of the known users in the sample library, and warns the user through the light that there is a stranger in the monitoring area; the lighting system generates an alarm signal and transmits it to the monitoring platform. In addition, a sound alarm can also be issued based on the signal output by the AI algorithm module.
步骤506，二次检测被检测对象是否为陌生人。Step 506: re-detect whether the detected object is a stranger.
可选地，可以通过AI算法模块进行对包含人脸的图像进行二次检测，二次检测方法可以与AI算法模块的方法一致，也可以不一致，在此不做限定。Optionally, the AI algorithm module may be used to perform secondary detection on the image containing the face. The secondary detection method may be consistent with the method of the AI algorithm module or may be inconsistent, which is not limited here.
步骤507，在二次检测被检测对象为陌生人，则存储告警信息。Step 507: If the detected object is a stranger in the secondary detection, the alarm information is stored.
可选地，存储器用于二次检测照明系统是否判断正确后，存储告警信息。可选地，照明系统在收到AI算法模块输出的信号后进行二次检测，触发告警后摄像头录制视频并上传至处理器。经AI算法模块二次检测后，若确认报警无误，则根据摄像头录制得到人脸、时间、时长记录生成告警信息，并通过通信器将处理区中存储的图像和告警信息发送至存储器。Optionally, the memory is used to store the alarm information after the secondary detection of whether the lighting system is correct. Optionally, the lighting system performs a secondary detection after receiving the signal output by the AI algorithm module, and after the alarm is triggered, the camera records the video and uploads it to the processor. After the secondary detection by the AI algorithm module, if the alarm is confirmed to be correct, the alarm information is generated based on the face, time, and duration recorded by the camera, and the image and alarm information stored in the processing area are sent to the memory through the communicator.
步骤508，启动照明系统。Step 508, start the lighting system.
可选地，AI算法模块在认定被检测的人脸与样本库中的人脸为同一人的情况下，输出信号至照明系统，并启动照明系统。此时，照明系统基于样本库中已知用户的设定，即第二照明策略，控制智能照明灯运行。Optionally, when the AI algorithm module determines that the detected face is the same person as the face in the sample library, it outputs a signal to the lighting system and starts the lighting system. At this time, the lighting system controls the operation of the intelligent lighting based on the settings of the known users in the sample library, that is, the second lighting strategy.
本实施例中的方法可以应用于看家业务中，例如集成于摄像头、门铃中，促使看家业务持续发展，增强用户对智能化照明监控系统的感知性。也可应用于办公园区、实验室、医院等对人员进出有严格限制的公共场所，有陌生人闯入可以及时通过照明监控报警系统进行告警。提升保密型公共场所的安全性，对城市公共安全起到了有效的保障。The method in this embodiment can be applied to home security services, for example, integrated into cameras and doorbells, to promote the continuous development of home security services and enhance users' perception of intelligent lighting monitoring systems. It can also be applied to public places such as office parks, laboratories, and hospitals where there are strict restrictions on the entry and exit of personnel. If a stranger breaks in, an alarm can be issued in time through the lighting monitoring alarm system. The security of confidential public places is improved, which effectively protects urban public security.
传统技术中，照明监控装置仅根据红外检测器和摄像头判断是否有人经过，无法根据经过的人的具体身份判断选择照明方法以及判断是否需要启动报警信号，监控平台的资源消耗大。相比传统技术，本实施例中，通过摄像头所带的人体传感器在限定的区域内捕捉人体，同时针对摄像头捕捉到的人体面部基于特征脸人脸识别算法计算特征脸的特征向量。预置样本库，通过样本库的人脸特征和摄像头拍摄画面中的人脸特征之间的比对结果，确定摄像头拍摄画面中的人脸信息若检测到摄像头拍摄画面中的人脸为样本库中已有人脸，则通过通信器启动照明系统；若检测到摄像头拍摄画面中的人脸为陌生人，则通过通信器启动照明监控报警系统，监控资源消耗小，并实现了声光电混合报警。相比传统方法，通过联动照明、监控系统，实现声光电混合报警的方式以提醒用户得知监控区域内处于告警状态中。并且，照明系统收到告警信号后，通过二次检测确认报警无误判后再生成告警信息，二次验证的方法，还可以达到提升报警准确率的效果。In the traditional technology, the lighting monitoring device only determines whether someone passes by based on the infrared detector and the camera, and cannot determine the lighting method and whether to start the alarm signal according to the specific identity of the person passing by, and the resource consumption of the monitoring platform is large. Compared with the traditional technology, in this embodiment, the human body sensor carried by the camera is used to capture the human body in a limited area, and the characteristic vector of the characteristic face is calculated based on the characteristic face face recognition algorithm for the human face captured by the camera. A sample library is preset, and the face information in the camera shooting picture is determined by comparing the face features of the sample library with the face features in the camera shooting picture. If the face in the camera shooting picture is detected as a face in the sample library, the lighting system is started through the communicator; if the face in the camera shooting picture is detected as a stranger, the lighting monitoring alarm system is started through the communicator, the monitoring resource consumption is small, and the sound, light and electricity mixed alarm is realized. Compared with the traditional method, by linking the lighting and monitoring systems, the sound, light and electricity mixed alarm method is realized to remind the user that the monitoring area is in an alarm state. In addition, after the lighting system receives the alarm signal, it generates the alarm information after confirming that the alarm is not misjudged through secondary detection. The secondary verification method can also achieve the effect of improving the alarm accuracy.
应该理解的是，虽然如上所述的各实施例所涉及的流程图中的各个步骤按照箭头的指示依次显示，但是这些步骤并不是必然按照箭头指示的顺序依次执行。除非本文中有明确的说明，这些步骤的执行并没有严格的顺序限制，这些步骤可以以其它的顺序执行。而且，如上所述的各实施例所涉及的流程图中的至少一部分步骤可以包括多个步骤或者多个阶段，这些步骤或者阶段并不必然是在同一时刻执行完成，而是可以在不同的时刻执行，这些步骤或者阶段的执行顺序也不必然是依次进行，而是可以与其它步骤或者其它步骤中的步骤或者阶段的至少一部分轮流或者交替地执行。例如，在执行步骤503至步骤507任一步骤的同时，还可以同步执行步骤502。It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps. For example, while executing any one of steps 503 to 507, step 502 can also be executed synchronously.
基于同样的发明构思，本申请实施例还提供了一种用于实现上述所涉及的照明告警方法的照明告警装置。该装置所提供的解决问题的实现方案与上述方法中所记载的实现方案相似，故下面所提供的一个或多个照明告警装置实施例中的具体限定可以参见上文中对于照明告警方法的限定，在此不再赘述。Based on the same inventive concept, the embodiment of the present application also provides a lighting warning device for implementing the lighting warning method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in the one or more lighting warning device embodiments provided below can refer to the limitations of the lighting warning method above, and will not be repeated here.
在一个实施例中，如图6所示，提供了一种照明告警装置，包括：提取模块、判断模块、第一执行模块和第二执行模块，其中：提取模块，用于根据监控区域内的监控图像，得到所述监控图像中人体的面部特征；判断模块，用于判断所述面部特征是否与预设特征匹配；第一执行模块，用于在所述面部特征与所述预设特征不匹配的情况下，执行第一照明策略；第二执行模块，用于在所述面部特征与所述预设特征匹配的情况下，执行第二照明策略。In one embodiment, as shown in FIG6 , a lighting alarm device is provided, including: an extraction module, a judgment module, a first execution module, and a second execution module, wherein: the extraction module is used to obtain facial features of a human body in a monitoring image according to a monitoring image in a monitoring area; the judgment module is used to judge whether the facial features match preset features; the first execution module is used to execute a first lighting strategy when the facial features do not match the preset features; and the second execution module is used to execute a second lighting strategy when the facial features match the preset features.
在一个实施例中，第一执行模块在执行第一照明策略之后，所述方法还包括：判断面部特征与预设特征不匹配的次数是否达到预设次数；若否，则返回执行根据监控图像得到人体的面部特征，判断面部特征是否与预设特征匹配的步骤，直至判断到面部特征与预设特征不匹配的次数达到预设次数，生成告警信息。可选地，第一执行模块生成告警信息，包括：获取监控区域的监控视频，监控视频的各视频帧皆包含与预设特征匹配的面部特征；根据监控图像和监控视频生成告警信息，其中，告警信息包括：监控图像的获取时间、监控图像中人体的面部图像、监控视频。In one embodiment, after the first execution module executes the first lighting strategy, the method further includes: determining whether the number of times that the facial features do not match the preset features reaches a preset number; if not, returning to the step of obtaining the facial features of the human body according to the surveillance image and determining whether the facial features match the preset features, until it is determined that the number of times that the facial features do not match the preset features reaches a preset number, and generating an alarm message. Optionally, the first execution module generates the alarm message, including: acquiring a surveillance video of the surveillance area, each video frame of the surveillance video contains facial features that match the preset features; generating the alarm message according to the surveillance image and the surveillance video, wherein the alarm message includes: the acquisition time of the surveillance image, the facial image of the human body in the surveillance image, and the surveillance video.
可选地，第一执行模块在执行第一照明策略之后，还包括：基于声音装置播放预设音频；生成告警信号，并将告警信号传输至监控平台。Optionally, after executing the first lighting strategy, the first execution module further includes: playing a preset audio based on a sound device; generating an alarm signal, and transmitting the alarm signal to a monitoring platform.
在一个实施例中，提取模块在检测到监控区域内存在人体的情况下，根据监控区域的监控图像得到人体的面部特征之前，方法还包括：获取监控区域内的温度变化数据；根据温度变化数据，判断监控区域内的温度变化是否处于阈值范围内；若是，则判断监控区域存在人体并采集对应于人体的所述监控图像。In one embodiment, when the extraction module detects the presence of a human body in the monitoring area, before obtaining the facial features of the human body based on the monitoring image of the monitoring area, the method also includes: acquiring temperature change data within the monitoring area; judging whether the temperature change within the monitoring area is within a threshold range based on the temperature change data; if so, judging that a human body exists in the monitoring area and acquiring the monitoring image corresponding to the human body.
在一个实施例中，提取模块根据监控区域的监控图像得到人体的面部特征，包括：将多张包含人体面部的监控图像转化为多个向量；计算各向量的平均值，以及各向量与平均值之间的第一差值；根据各第一差值构建矩阵，得到矩阵的多个特征向量；根据与矩阵的特征向量、与特征向量对应的第一差值的乘积，计算得到各监控图像中人体面部的特征向量；根据矩阵的特征向量、与特征向量对应的第一差值的乘积，计算得到各监控图像中人体面部的特征向量；根据监控图像、与监控图像对应的第一差值和特征向量，得到各张包含人体面部的监控图像的权重向量；根据权重向量得到人体的面部特征。In one embodiment, an extraction module obtains facial features of a human body based on surveillance images of a surveillance area, including: converting multiple surveillance images containing human faces into multiple vectors; calculating an average value of each vector and a first difference between each vector and the average value; constructing a matrix based on each first difference to obtain multiple eigenvectors of the matrix; calculating a eigenvector of the human face in each surveillance image based on the product of an eigenvector of the matrix and a first difference corresponding to the eigenvector; calculating a eigenvector of the human face in each surveillance image based on the product of an eigenvector of the matrix and a first difference corresponding to the eigenvector; obtaining a weight vector of each surveillance image containing human faces based on the surveillance image, the first difference corresponding to the surveillance image and the eigenvector; and obtaining facial features of the human body based on the weight vector.
在一个实施例中，判断模块判断面部特征是否与预设特征匹配，包括：获取面部特征的向量长度和预设特征的向量长度；判断面部特征的向量长度和预设特征的向量长度之间的差值是否小于设定的阈值；若是，则判断面部特征和预设特征匹配；若否，则判断面部特征和预设特征不匹配。In one embodiment, the judgment module judges whether the facial feature matches the preset feature, including: obtaining the vector length of the facial feature and the vector length of the preset feature; judging whether the difference between the vector length of the facial feature and the vector length of the preset feature is less than a set threshold; if so, judging that the facial feature matches the preset feature; if not, judging that the facial feature does not match the preset feature.
上述照明告警装置中的各个模块可全部或部分通过软件、硬件及其组合来实现。上述各模块可以硬件形式内嵌于或独立于计算机设备中的处理器中，也可以以软件形式存储于计算机设备中的存储器中，以便于处理器调用执行以上各个模块对应的操作。Each module in the above-mentioned lighting warning device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each module.
在一个实施例中，提供了一种计算机设备，该计算机设备可以是服务器，其内部结构图可以如图7所示。该计算机设备包括处理器、存储器、输入/输出接口(Input/Output，简称I/O)和通信接口。其中，处理器、存储器和输入/输出接口通过系统总线连接，通信接口通过输入/输出接口连接到系统总线。其中，该计算机设备的处理器用于提供计算和控制能力。该计算机设备的存储器包括非易失性存储介质和内存储器。该非易失性存储介质存储有操作系统、计算机程序和数据库。该内存储器为非易失性存储介质中的操作系统和计算机程序的运行提供环境。该计算机设备的数据库用于存储第一照明策略、第二照明策略、预设特征等与照明告警策略相关的数据。该计算机设备的输入/输出接口用于处理器与外部设备之间交换信息。该计算机设备的通信接口用于与外部的终端通过网络连接通信。该计算机程序被处理器执行时以实现一种照明告警方法。In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be shown in FIG7. The computer device includes a processor, a memory, an input/output interface (I/O for short) and a communication interface. The processor, the memory and the input/output interface are connected via a system bus, and the communication interface is connected to the system bus via the input/output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data related to the lighting alarm strategy, such as a first lighting strategy, a second lighting strategy, and preset features. The input/output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a lighting alarm method is implemented.
本领域技术人员可以理解，图7中示出的结构，仅仅是与本申请方案相关的部分结构的框图，并不构成对本申请方案所应用于其上的计算机设备的限定，具体的计算机设备可以包括比图中所示更多或更少的部件，或者组合某些部件，或者具有不同的部件布置。Those skilled in the art will understand that the structure shown in FIG. 7 is merely a block diagram of a partial structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.
在一个实施例中，还提供了一种计算机设备，包括存储器和处理器，存储器中存储有计算机程序，该处理器执行计算机程序时实现上述各方法实施例中的步骤。In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.
在一个实施例中，提供了一种计算机可读存储介质，其上存储有计算机程序，该计算机程序被处理器执行时实现上述各方法实施例中的步骤。In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.
在一个实施例中，提供了一种计算机程序产品，包括计算机程序，该计算机程序被处理器执行时实现上述各方法实施例中的步骤。In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.
本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程，是可以通过计算机程序来指令相关的硬件来完成，所述的计算机程序可存储于一非易失性计算机可读取存储介质中，该计算机程序在执行时，可包括如上述各方法的实施例的流程。其中，本申请所提供的各实施例中所使用的对存储器、数据库或其它介质的任何引用，均可包括非易失性和易失性存储器中的至少一种。非易失性存储器可包括只读存储器(Read-OnlyMemory，ROM)、磁带、软盘、闪存、光存储器、高密度嵌入式非易失性存储器、阻变存储器(ReRAM)、磁变存储器(Magnetoresistive Random Access Memory，MRAM)、铁电存储器(Ferroelectric Random Access Memory，FRAM)、相变存储器(Phase Change Memory，PCM)、石墨烯存储器等。易失性存储器可包括随机存取存储器(Random Access Memory，RAM)或外部高速缓冲存储器等。作为说明而非局限，RAM可以是多种形式，比如静态随机存取存储器(Static Random Access Memory，SRAM)或动态随机存取存储器(Dynamic RandomAccess Memory，DRAM)等。本申请所提供的各实施例中所涉及的数据库可包括关系型数据库和非关系型数据库中至少一种。非关系型数据库可包括基于区块链的分布式数据库等，不限于此。本申请所提供的各实施例中所涉及的处理器可为通用处理器、中央处理器、图形处理器、数字信号处理器、可编程逻辑器、基于量子计算的数据处理逻辑器等，不限于此。Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.
以上实施例的各技术特征可以进行任意的组合，为使描述简洁，未对上述实施例中的各个技术特征所有可能的组合都进行描述，然而，只要这些技术特征的组合不存在矛盾，都应当认为是本说明书记载的范围。The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
以上所述实施例仅表达了本申请的几种实施方式，其描述较为具体和详细，但并不能因此而理解为对本申请专利范围的限制。应当指出的是，对于本领域的普通技术人员来说，在不脱离本申请构思的前提下，还可以做出若干变形和改进，这些都属于本申请的保护范围。因此，本申请的保护范围应以所附权利要求为准。The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410903883.0ACN118762459A (en) | 2024-07-05 | 2024-07-05 | Lighting alarm method, device and system |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410903883.0ACN118762459A (en) | 2024-07-05 | 2024-07-05 | Lighting alarm method, device and system |
| Publication Number | Publication Date |
|---|---|
| CN118762459Atrue CN118762459A (en) | 2024-10-11 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410903883.0APendingCN118762459A (en) | 2024-07-05 | 2024-07-05 | Lighting alarm method, device and system |
| Country | Link |
|---|---|
| CN (1) | CN118762459A (en) |
| Publication | Publication Date | Title |
|---|---|---|
| US10769914B2 (en) | Informative image data generation using audio/video recording and communication devices | |
| CN110291489B (en) | Computationally Efficient Human Identity Assistant Computer | |
| US10511810B2 (en) | Accessing cameras of audio/video recording and communication devices based on location | |
| US11195408B1 (en) | Sending signals for help during an emergency event | |
| JP2019096179A (en) | Behavior monitoring system | |
| US11659144B1 (en) | Security video data processing systems and methods | |
| US20110096994A1 (en) | Similar image retrieval system and similar image retrieval method | |
| CN100464348C (en) | Intelligent device and method for video surveillance and recognition | |
| US10943442B1 (en) | Customized notifications based on device characteristics | |
| US11069210B2 (en) | Selecting a video frame for notification using audio/video recording and communication devices | |
| WO2016172923A1 (en) | Video detection method, video detection system, and computer program product | |
| CN114859749A (en) | Intelligent home management method and system based on Internet of things | |
| CN111985407A (en) | Safety early warning method, device, equipment and storage medium | |
| CN114495395A (en) | Human shape detection method, monitoring and early warning method, device and system | |
| CN114494153A (en) | Article storage detection method and device, computer equipment and storage medium | |
| US20170300685A1 (en) | Method and system for visual authentication | |
| JP2005056213A5 (en) | ||
| CN108171224A (en) | A kind of electron album and attendance recorder | |
| JP7529241B2 (en) | Facial recognition system and facial recognition method | |
| CN118762459A (en) | Lighting alarm method, device and system | |
| CN115428047A (en) | System and method for identifying user-customized related individuals in an environmental image at a doorbell device | |
| CN114187650A (en) | Motion recognition method, device, electronic device and storage medium | |
| CN114079748A (en) | Monitoring method and device based on intelligent doorbell, electronic equipment and storage medium | |
| US20240362984A1 (en) | Method, an apparatus and a system for managing an event to generate an alert indicating a subject is likely to be unauthorized | |
| TWI781434B (en) | Access control system and access control method |
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |