CN115180522A - Safety monitoring method and system for hoisting device construction site - Google Patents
Safety monitoring method and system for hoisting device construction siteDownload PDFInfo
- Publication number
- CN115180522A CN115180522ACN202210613319.6ACN202210613319ACN115180522ACN 115180522 ACN115180522 ACN 115180522ACN 202210613319 ACN202210613319 ACN 202210613319ACN 115180522 ACN115180522 ACN 115180522A
- Authority
- CN
- China
- Prior art keywords
- current image
- construction site
- specific human
- detection
- hook
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66C—CRANES; LOAD-ENGAGING ELEMENTS OR DEVICES FOR CRANES, CAPSTANS, WINCHES, OR TACKLES
- B66C15/00—Safety gear
- B66C15/06—Arrangements or use of warning devices
- B66C15/065—Arrangements or use of warning devices electrical
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66C—CRANES; LOAD-ENGAGING ELEMENTS OR DEVICES FOR CRANES, CAPSTANS, WINCHES, OR TACKLES
- B66C13/00—Other constructional features or details
- B66C13/16—Applications of indicating, registering, or weighing devices
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Alarm Systems (AREA)
Abstract
Description
Translated fromChinese技术领域technical field
本申请涉及安防领域，特别是涉及一种起吊装置施工现场的安全监测方法、系统、计算机设备和计算机可读存储介质。The present application relates to the field of security, and in particular, to a method, system, computer equipment and computer-readable storage medium for security monitoring at a construction site of a hoisting device.
背景技术Background technique
随着现代化建设不断开展，塔吊成为工地上必不可少的常用机械设备，由于塔吊距离地面较高、起吊物体质量较大，因此，对于起吊过程的安全预警和报警至关重要。With the continuous development of modernization construction, tower cranes have become an indispensable common mechanical equipment on construction sites. Because the tower cranes are far from the ground and the quality of the objects to be lifted is relatively large, the safety early warning and alarm for the lifting process are very important.
在相关技术中，中国专利CN109019335A提供了一种基于深度学习的吊装安全距离检测方法，描述了对吊钩以及吊钩下行人的检测，通过检测结果计算实际距离从而判断是否报警。中国专利CN111062373A提供了一种基于深度学习的吊装过程危险识别方法及系统，通过监测吊钩、正确佩戴安全帽的工人以及未正确佩戴安全帽的工人，以判断工人行为是否满足吊装施工现场的安全作业要求，进一步的还可以判断工人是否位于吊钩的预测路径范围中，从而提升吊装施工现场的安全性。In the related art, Chinese patent CN109019335A provides a deep learning-based hoisting safety distance detection method, which describes the detection of hooks and pedestrians on the hooks, and calculates the actual distance through the detection results to determine whether to alarm. Chinese patent CN111062373A provides a deep learning-based hoisting process hazard identification method and system. By monitoring hooks, workers wearing safety helmets correctly, and workers who don't wear safety helmets correctly, it is possible to determine whether workers' behaviors meet the safety requirements of the hoisting construction site. According to the operation requirements, it can further judge whether the worker is located in the predicted path range of the hook, thereby improving the safety of the hoisting construction site.
但是，吊装重物过程中，预防安全事故的发生，仅依靠机器进行检测是不够的，仍然需要信号员一直在场监督，即使出现突发事故，也能由信号员及时应对，若信号员脱离监督岗位，将导致极大的安全风险。However, in the process of hoisting heavy objects, to prevent the occurrence of safety accidents, it is not enough to rely on the machine for detection. It is still necessary for the signalman to be on site to supervise all the time. Even if there is an accident, the signalman can respond in time. position, will lead to great security risks.
发明内容SUMMARY OF THE INVENTION
本申请实施例提供了一种起吊装置施工现场的安全监测方法、系统、计算机设备和计算机可读存储介质，以至少解决相关技术中起吊装置监控方法安全保障性较差的问题。Embodiments of the present application provide a safety monitoring method, system, computer equipment and computer-readable storage medium for a hoisting device construction site, so as to at least solve the problem of poor safety assurance of the hoisting device monitoring method in the related art.
第一方面，本申请实施例提供了一种起吊装置施工现场的安全监测方法，所述方法包括：In a first aspect, an embodiment of the present application provides a safety monitoring method for a construction site of a hoisting device, the method comprising:
获取起吊装置施工现场的历史图像集，并标注其中的目标对象，其中，所述目标对象包括吊钩、特定人体对象和非特定人体对象；Acquiring a historical image set of the construction site of the hoisting device, and labeling the target objects therein, wherein the target objects include hooks, specific human objects and non-specific human objects;
构建检测网络和分类网络，基于标注之后的历史图像集，分别训练所述检测网络和所述分类网络，分别得到检测模型和分类模型；Construct a detection network and a classification network, and train the detection network and the classification network respectively based on the historical image set after the labeling, and obtain a detection model and a classification model respectively;
采集所述施工现场的当前图像，通过所述检测模型，检测所述当前图像中的人体对象和吊钩，通过所述分类模型，识别所述人体对象中的特定人体对象；Collecting a current image of the construction site, detecting human objects and hooks in the current image through the detection model, and identifying specific human objects in the human objects through the classification model;
根据所述当前图像中的吊钩，在所述当前图像中确定目标区域；determining a target area in the current image according to the hook in the current image;
实时跟踪所述特定人体对象，获取其对应在所述当前图像中的坐标，并判断所述坐标，在预设时间段内是否处于所述目标区域，若否，指示发送安全警报。Track the specific human object in real time, obtain its coordinates corresponding to the current image, and determine whether the coordinates are in the target area within a preset time period, and if not, instruct to send a security alert.
在其中一些实施例中，所述特定人体对象是佩戴红色安全帽的信号员，所述非特定人体是除所述信号员之外的其他人员。In some of these embodiments, the specific human subject is a signalman wearing a red hard hat, and the non-specific human body is a person other than the signalman.
在其中一些实施例中，通过检测模型，检测所述当前图像中的人体对象和吊钩，包括：In some of the embodiments, the detection model is used to detect the human object and the hook in the current image, including:
通过主干网络，提取当前图像中的特征，其中，所述主干网络为Ghostnet 结构，Through the backbone network, the features in the current image are extracted, wherein the backbone network is a Ghostnet structure,
通过neck层融合所述特征得到特征图，其中，所述neck层包括自顶向下采样层和自底向上采样层，自顶向下采样层获取语义信息，自底向上采样层采样层获取定位信息，基于所述语义信息和所述定位信息融合所述特征；The feature map is obtained by fusing the features through the neck layer, wherein the neck layer includes a top-down sampling layer and a bottom-up sampling layer, the top-down sampling layer obtains semantic information, and the bottom-up sampling layer sampling layer obtains positioning information, and fuse the features based on the semantic information and the positioning information;
通过检测头检测所述特征图，得到述当前图像中的人体对象和吊钩。The feature map is detected by the detection head to obtain the human object and the hook in the current image.
在其中一些实施例中，所述方法还包括：In some of these embodiments, the method further includes:
在所述检测模型的训练过程中，通过mixup数据增强，扩充所述历史数据集，During the training process of the detection model, through mixup data enhancement, the historical data set is expanded,
采用BCEWithLogitsLoss作为分类损失函数，采用IoU loss作为回归损失函数。BCEWithLogitsLoss is used as the classification loss function, and IoU loss is used as the regression loss function.
在其中一些实施例中，所述分类模型为mobilenetv3模型，在所述分类模型的训练过程中，通过focalloss损失函数均衡正负样本。In some of the embodiments, the classification model is a mobilenetv3 model, and during the training process of the classification model, the positive and negative samples are balanced by the focalloss loss function.
在其中一些实施例中，根据所述当前图像中的吊钩，在所述当前图像中确定目标区域，包括：In some of these embodiments, determining the target area in the current image according to the hook in the current image includes:
获取所述吊钩对应在所述当前图像中的像素长度，以及获取所述吊钩的实际长度；Obtain the pixel length of the hook corresponding to the current image, and obtain the actual length of the hook;
确定所述实际长度与所述像素长度的转换比，以及所述信号工的在现实空间中的预设活动半径值；determining a conversion ratio of the actual length to the pixel length, and a preset active radius value of the signal in real space;
根据所述转换比，将所述预设活动半径值，转换为所述当前图像中的像素半径值；converting the preset active radius value into a pixel radius value in the current image according to the conversion ratio;
以所述吊钩的中心为圆心，根据所述像素半径值，在所述当前图像中确定所述目标区域。Taking the center of the hook as the center of the circle, and according to the pixel radius value, the target area is determined in the current image.
在其中一些实施例中，获取起吊装置施工现场的历史图像集之前，所述方法还包括：In some of these embodiments, before acquiring the historical image set of the construction site of the hoisting device, the method further includes:
通过摄像装置采集起吊装置施工现场的视频，将所述视频分割为多组单帧图像，由多组单帧图像组成所述历史图像集，其中，所述摄像装置安装在起吊装置大臂上，且摄像角度为垂直俯角。The video of the construction site of the hoisting device is collected by a camera device, the video is divided into multiple sets of single-frame images, and the historical image set is composed of multiple sets of single-frame images, wherein the camera device is installed on the boom of the hoisting device, And the camera angle is the vertical depression angle.
第二方面，本申请实施例提供了一种起吊装置施工现场的安全监测系统，所述系统包括：预处理模块、训练模块和检测模块，其中；In a second aspect, an embodiment of the present application provides a safety monitoring system for a construction site of a hoisting device, the system includes: a preprocessing module, a training module and a detection module, wherein;
所述预处理模块用于，获取起吊装置施工现场的历史图像集，并标注其中的目标对象，其中，所述目标对象包括吊钩、特定人体对象和非特定人体对象；The preprocessing module is used to acquire the historical image set of the construction site of the hoisting device, and mark the target objects therein, wherein the target objects include hooks, specific human objects and non-specific human objects;
所述训练模块用于，构建检测网络和分类网络，基于标注之后的历史图像集，分别训练所述检测网络和所述分类网络，分别得到检测模型和分类模型；The training module is used to construct a detection network and a classification network, and to train the detection network and the classification network respectively based on the marked historical image set to obtain a detection model and a classification model respectively;
所述检测模块用于，采集所述施工现场的当前图像，通过所述检测模型，检测所述当前图像中的人体对象和吊钩，通过所述分类模型，识别所述人体对象中的特定人体对象，以及The detection module is used to collect the current image of the construction site, detect human objects and hooks in the current image through the detection model, and identify a specific human body in the human object through the classification model object, and
根据所述当前图像中的吊钩，在所述当前图像中确定目标区域，以及determining a target area in the current image based on the hook in the current image, and
实时跟踪所述特定人体对象，获取其对应在所述当前图像中的坐标，并判断所述坐标，在预设时间段内是否处于所述目标区域，若否，指示发送安全警报。Track the specific human object in real time, obtain its coordinates corresponding to the current image, and determine whether the coordinates are in the target area within a preset time period, and if not, instruct to send a security alert.
第三方面，本申请实施例提供了一种计算机设备，包括存储器、处理器以及存储在所述存储器上并可在所述处理器上运行的计算机程序，所述处理器执行所述计算机程序时实现如上述第一方面所述的方法。In a third aspect, an embodiment of the present application provides a computer device, including a memory, a processor, and a computer program stored on the memory and executable on the processor, when the processor executes the computer program The method as described in the first aspect above is implemented.
第四方面，本申请实施例提供了一种计算机可读存储介质，其上存储有计算机程序，该程序被处理器执行时实现如上述第一方面所述的方法。In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium on which a computer program is stored, and when the program is executed by a processor, implements the method described in the first aspect.
相比于相关技术，本申请实施例提供的一种施工现场的安全监控方法，通过获取施工现场的多组历史图像，并标注其中的目标对象；基于标注之后的多组历史图像，训练检测模型和分类模型。进一步的，在实际检测环节，通过训练完成的检测模型和分类模型，检测当前图像中的人体对象和吊钩，并识别人体对象中的特定人体对象。最后，实时跟踪特定人体对象，并判断该特定人体对象在预设时间段内是否处于目标区域，若否，即指示该特定人体离开工作岗位超时，指示其他设备发送安全警报。解决了相关技术中起吊装置监控方法安全保障性较差的问题，实现了对负责监督的信号员的检测和跟踪，在安全员离开吊钩之下的预设活动范围达到一定时间后，即输出告警信号，从而提升了塔吊施工现场的安全监控能力，更进一步的保障了施工人员的安全。Compared with the related art, a method for safety monitoring of a construction site provided by the embodiment of the present application acquires multiple groups of historical images of the construction site, and annotates the target objects therein; and trains a detection model based on the multiple groups of historical images after the annotation. and classification models. Further, in the actual detection link, through the trained detection model and classification model, the human object and the hook in the current image are detected, and the specific human object in the human object is identified. Finally, the specific human object is tracked in real time, and it is judged whether the specific human object is in the target area within a preset time period. If not, the specific human body is instructed to leave the work position for a timeout, and other devices are instructed to send a security alarm. It solves the problem of poor safety guarantee of the monitoring method of the lifting device in the related art, and realizes the detection and tracking of the signal officer responsible for supervision. After the safety officer leaves the preset range of activities under the hook for a certain time, the output Alarm signal, thus improving the safety monitoring ability of the tower crane construction site, and further ensuring the safety of construction personnel.
附图说明Description of drawings
此处所说明的附图用来提供对本申请的进一步理解，构成本申请的一部分，本申请的示意性实施例及其说明用于解释本申请，并不构成对本申请的不当限定。在附图中：The drawings described herein are used to provide further understanding of the present application and constitute a part of the present application. The schematic embodiments and descriptions of the present application are used to explain the present application and do not constitute an improper limitation of the present application. In the attached image:
图1是根据本申请实施例的一种起吊装置施工现场的安全监测方法的应用环境示意图；1 is a schematic diagram of an application environment of a safety monitoring method at a construction site of a hoisting device according to an embodiment of the present application;
图2是根据本申请实施例的一种起吊装置施工现场的安全监测方法的流程图；2 is a flowchart of a method for safety monitoring at a construction site of a hoisting device according to an embodiment of the present application;
图3是根据本申请实施例的一种在neck层进行特征融合的示意图；3 is a schematic diagram of feature fusion at the neck layer according to an embodiment of the present application;
图4是根据本申请实施例的起吊装置施工现场的安全监测系统的结构框图；4 is a structural block diagram of a safety monitoring system at a construction site of a hoisting device according to an embodiment of the present application;
图5是根据本申请实施例的电子设备的内部结构示意图；5 is a schematic diagram of an internal structure of an electronic device according to an embodiment of the present application;
图6是根据本申请实施例的电子设备的内部结构示意图。FIG. 6 is a schematic diagram of an internal structure of an electronic device according to an embodiment of the present application.
具体实施方式Detailed ways
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，对本申请进行描述和说明。应当理解，此处所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。基于本申请提供的实施例，本领域普通技术人员在没有作出创造性劳动的前提下所获得的所有其他实施例，都属于本申请保护的范围。In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be described and illustrated below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, but not to limit the present application. Based on the embodiments provided in the present application, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present application.
显而易见地，下面描述中的附图仅仅是本申请的一些示例或实施例，对于本领域的普通技术人员而言，在不付出创造性劳动的前提下，还可以根据这些附图将本申请应用于其他类似情景。此外，还可以理解的是，虽然这种开发过程中所作出的努力可能是复杂并且冗长的，然而对于与本申请公开的内容相关的本领域的普通技术人员而言，在本申请揭露的技术内容的基础上进行的一些设计，制造或者生产等变更只是常规的技术手段，不应当理解为本申请公开的内容不充分。Obviously, the accompanying drawings in the following description are only some examples or embodiments of the present application. For those of ordinary skill in the art, the present application can also be applied to the present application according to these drawings without any creative effort. other similar situations. In addition, it will also be appreciated that while such development efforts may be complex and lengthy, for those of ordinary skill in the art to which the present disclosure pertains, the techniques disclosed in this application Some changes in design, manufacture or production based on the content are only conventional technical means, and it should not be understood that the content disclosed in this application is not sufficient.
在本申请中提及“实施例”意味着，结合实施例描述的特定特征、结构或特性可以包含在本申请的至少一个实施例中。在说明书中的各个位置出现该短语并不一定均是指相同的实施例，也不是与其它实施例互斥的独立的或备选的实施例。本领域普通技术人员显式地和隐式地理解的是，本申请所描述的实施例在不冲突的情况下，可以与其它实施例相结合。Reference in this application to an "embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor a separate or alternative embodiment that is mutually exclusive of other embodiments. It is explicitly and implicitly understood by those of ordinary skill in the art that the embodiments described in this application may be combined with other embodiments without conflict.
除非另作定义，本申请所涉及的技术术语或者科学术语应当为本申请所属技术领域内具有一般技能的人士所理解的通常意义。本申请所涉及的“一”、“一个”、“一种”、“该”等类似词语并不表示数量限制，可表示单数或复数。本申请所涉及的术语“包括”、“包含”、“具有”以及它们任何变形，意图在于覆盖不排他的包含；例如包含了一系列步骤或模块(单元)的过程、方法、系统、产品或设备没有限定于已列出的步骤或单元，而是可以还包括没有列出的步骤或单元，或可以还包括对于这些过程、方法、产品或设备固有的其它步骤或单元。本申请所涉及的“连接”、“相连”、“耦接”等类似的词语并非限定于物理的或者机械的连接，而是可以包括电气的连接，不管是直接的还是间接的。本申请所涉及的“多个”是指两个或两个以上。“和/或”描述关联对象的关联关系，表示可以存在三种关系，例如，“A和/或B”可以表示：单独存在A，同时存在 A和B，单独存在B这三种情况。字符“/”一般表示前后关联对象是一种“或”的关系。本申请所涉及的术语“第一”、“第二”、“第三”等仅仅是区别类似的对象，不代表针对对象的特定排序。Unless otherwise defined, the technical or scientific terms involved in this application shall have the usual meanings understood by those with ordinary skill in the technical field to which this application belongs. Words such as "a", "an", "an", "the" and the like mentioned in this application do not denote a quantitative limitation, and may denote the singular or the plural. The terms "comprising", "comprising", "having" and any variations thereof referred to in this application are intended to cover non-exclusive inclusion; for example, a process, method, system, product or The apparatus is not limited to the steps or units listed, but may further include steps or units not listed, or may further include other steps or units inherent to the process, method, product or apparatus. Words like "connected," "connected," "coupled," and the like referred to in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The "plurality" referred to in this application refers to two or more. "And/or" describes the relationship between associated objects, indicating that there can be three kinds of relationships. For example, "A and/or B" can mean that A exists alone, A and B exist at the same time, and B exists alone. The character "/" generally indicates that the associated objects are an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only to distinguish similar objects, and do not represent a specific order for the objects.
本申请提供的一种起吊装置施工现场的安全监测方法，可以应用在如图1 所示的应用环境中，图1是根据本申请实施例的一种起吊装置施工现场的安全监测方法的应用环境示意图，如图1所示，利用安装在塔吊大臂上的摄像装置 10实时采集施工现场的图像，进一步的，设置在监控室或云端的服务器11接收该图像，并通过内置的检测模型识别该图像中的人体对象，以及通过分类模型从所有人体中识别特定人体对象(如佩戴红色安全帽的信号员)。最后，实时跟踪该特定人体对象，并通过判断该特定人体对象是否位于吊钩下的预设活动范围内，来识别负责安全监督的信号员是否位于在岗状态，从而优化了施工安防监控能力，保障了施工人员的安全。A safety monitoring method for a construction site of a hoisting device provided by the present application can be applied in the application environment as shown in FIG. 1 . FIG. 1 is an application environment for a safety monitoring method for a construction site of a hoisting device according to an embodiment of the present application. Schematic diagram, as shown in FIG. 1, the image of the construction site is collected in real time by the
图2是根据本申请实施例的一种起吊装置施工现场的安全监测方法的流程图，如图2所示，该流程包括如下步骤：Fig. 2 is a flow chart of a method for safety monitoring at a construction site of a hoisting device according to an embodiment of the present application. As shown in Fig. 2 , the flow chart includes the following steps:
S201，通过摄像装置采集起吊装置施工现场的视频，将视频分割为多组单帧图像，并由多组单帧图像组成历史图像集，其中，摄像装置安装在起吊装置大臂上，且摄像角度为垂直俯角；S201 , the video of the construction site of the hoisting device is collected by a camera device, the video is divided into multiple sets of single-frame images, and a historical image set is composed of multiple sets of single-frame images, wherein the camera device is installed on the boom of the hoisting device, and the camera angle is the vertical depression angle;
本实施例中，摄像装置可以是常规相机、IPC相机、深度相机、红外相机中的任意一种。In this embodiment, the imaging device may be any one of a conventional camera, an IPC camera, a depth camera, and an infrared camera.
可选的，该摄像装置可以固定式或滑动式安装在起吊装置的大臂上，具体的：在滑动安装时，通过在起吊装置大臂上设置能够前后滑动的小车，再将该摄像装置安装在小车上，从而根据现场实际情况调整拍摄位置。Optionally, the camera device can be fixedly or slidably installed on the boom of the hoisting device, specifically: during sliding installation, a trolley that can slide forward and backward is arranged on the boom of the hoisting device, and then the camera device is installed. On the trolley, the shooting position can be adjusted according to the actual situation of the scene.
进一步的，该摄像装置的摄像角度为垂直俯角，用于拍摄畸变较小的更接近真实场景的现场图像。Further, the camera angle of the camera device is a vertical depression angle, and is used for capturing a live image with less distortion that is closer to the real scene.
需要说明的是，本步骤中获取的历史图像集中，图像的数量应该满足一定强度，从而满足模型训练的最低需求。It should be noted that, in the historical image set obtained in this step, the number of images should meet a certain intensity, so as to meet the minimum requirements for model training.
S202，获取起吊装置施工现场的历史图像集，并标注其中的目标对象，其中，目标对象包括吊钩、特定人体对象和非特定人体对象；S202, acquiring a historical image set of the construction site of the hoisting device, and marking the target objects therein, wherein the target objects include hooks, specific human objects and non-specific human objects;
其中，该历史图像集由多张内容不同的单帧图像组成，各个单帧图像可以相似，也可以完全不同；例如，人体轮廓清晰或模糊、人体轮廓大或小、人体有遮挡或无遮挡、人体有重叠或无重叠。The historical image set consists of multiple single-frame images with different contents, and each single-frame image may be similar or completely different; for example, the outline of the human body is clear or blurred, the outline of the human body is large or small, the human body is covered or not Human bodies with or without overlap.
需要说明的是，上述历史图像集中，单帧图像的类型必须是丰富的，从而保障后续得到的检测模型，得到能够满足需求的识别效果。It should be noted that, in the above historical image set, the types of single-frame images must be rich, so as to ensure the subsequent detection model and obtain the recognition effect that can meet the needs.
进一步的，标注图像的数量也应该达到一定数量级，其中，对于深度网络模型来说，在同等条件下，若训练过程中应用的数据量越大、数据类型越丰富，得到的模型将具备更好的效果。但是，对应的，数据量的增加也将导致运算量的增加，普通设备很可能不具备算力要求。本实例中，按照实际情况，标注的特定人体对象图像和非特定人体对象图像各1w张。Further, the number of labeled images should also reach a certain order of magnitude. Among them, for deep network models, under the same conditions, if the amount of data applied in the training process is larger and the data types are richer, the resulting model will be better. Effect. However, correspondingly, the increase in the amount of data will also lead to an increase in the amount of computation, and ordinary devices may not have the computing power requirements. In this example, according to the actual situation, there are 1w images of the marked specific human object and non-specific human object images.
在本实施例中，标注过程包括人体框的标注过程和分类标注过程，其中，人体框标注过程，即在原图像中将人体覆盖的区域框出来，其中，框的范围应该包括人体的整个部位；进一步的，分类标注过程，即将上述标人体框图区域裁切出来得到人体框图，再按照是否为特定人体对象对人体框图进行分类。In this embodiment, the labeling process includes the labeling process and the classification labeling process of the human body frame, wherein the human body frame labeling process is to frame the area covered by the human body in the original image, wherein the range of the frame should include the entire body part; Further, in the classification and labeling process, the above-mentioned area marked with the human body frame is cut out to obtain a human body frame, and then the human body frame is classified according to whether it is a specific human object.
需要说明的，在本实施例中，该特定人体对象为负责安全监督的信号员。按照当前施工行业规范要求，信号员显著性的标识特征，通常表现为佩戴红色安全帽；当然，在某些特殊场景下，信号员也可以具备其他标识特征，例如，佩戴蓝色安全帽、穿红色外套等。It should be noted that, in this embodiment, the specific human object is a signalman responsible for safety supervision. According to the requirements of current construction industry standards, the distinctive identification features of signalmen are usually shown as wearing red safety helmets; of course, in some special scenarios, signalmen can also have other identification characteristics, such as wearing blue red jacket etc.
应当理解，在信号员具备统一标识，且该标识能够被算法模型识别处理的情况下，本申请技术方案都可以利用该统一标识，达到预期的技术效果，因此，在本申请实施例中，对于特定人体对象采用何种标识特征，并不做具体限定。It should be understood that in the case where the signal operator has a unified identification and the identification can be recognized and processed by the algorithm model, the technical solutions of the present application can use the unified identification to achieve the expected technical effect. Therefore, in the embodiments of the present application, for There is no specific limitation on which identification feature a specific human object adopts.
S203，构建检测网络和分类网络，基于标注之后的历史图像集，分别训练检测网络和分类网络，分别得到检测模型和分类模型；S203, constructing a detection network and a classification network, respectively training the detection network and the classification network based on the marked historical image set, to obtain a detection model and a classification model respectively;
其中，上述检测网络是在yolov5算法的基础上，结合起吊装置施工现场特点，经过进一步改进得到，具体的：Among them, the above detection network is based on the yolov5 algorithm, combined with the characteristics of the construction site of the lifting device, and obtained after further improvement, specifically:
将原有yolov5算法中backbone替换为Ghostnet结构，由于Ghostnet相比较于backbone，网络结构更为轻量化，因此可以利用较小的参数生成更多的特征，从而提升整体检测速度；Replace the backbone in the original yolov5 algorithm with the Ghostnet structure. Compared with the backbone, Ghostnet has a lighter network structure, so it can use smaller parameters to generate more features, thereby improving the overall detection speed;
而在模型的特征融合层，添加了一层PAN结构，在原有的自底向上特征融合的基础上，进一步的再进行自顶而下特征融合，从而得到更好的特征图；In the feature fusion layer of the model, a layer of PAN structure is added. On the basis of the original bottom-up feature fusion, the top-down feature fusion is further performed to obtain a better feature map;
可选的，训练时可以采用mixup增强数据，主分类损失函数可以采用BCEWithLogitsLoss，回归损失函数可以采用IoU loss，最后，输出头依然保持为yolov5的输出头yolo1,yolo2,yolo3，可选的，训练迭代200个epoch(纪元)。Optionally, you can use mixup to enhance the data during training, the main classification loss function can use BCEWithLogitsLoss, the regression loss function can use IoU loss, and finally, the output head is still the output head yolo1, yolo2, yolo3 of yolov5, optional, training Iterate for 200 epochs.
进一步的，上述分类网络可以利用常见的任意一种二分类识别算法，可选的，可以采用mobilenetv3算法模型，该模型小而精，其输入分辨率为224*224，本实施例中，对分类模型训练迭代100个epoch(纪元)。Further, the above classification network can use any common two-class recognition algorithm. Optionally, the mobilenetv3 algorithm model can be used. This model is small and precise, and its input resolution is 224*224. In this embodiment, the classification Model training iterates for 100 epochs.
S204，采集施工现场的当前图像，通过检测模型，检测当前图像中的人体对象和吊钩，通过分类模型，识别人体对象中的特定人体对象；S204, collect the current image of the construction site, detect the human object and the hook in the current image through the detection model, and identify the specific human object in the human object through the classification model;
经过上述步骤S201至S203，已得到训练好的检测模型和分类模型，在本步骤中，可以将该模型部署在施工现场用于监控。利用检测模型识别获取现场实时图像中的吊钩和人体对象，再通过分类模型，从这些人体对象中识别出特定人体对象。After the above steps S201 to S203, the trained detection model and classification model have been obtained. In this step, the model can be deployed on the construction site for monitoring. The detection model is used to identify the hooks and human objects in the real-time images of the scene, and then the classification model is used to identify specific human objects from these human objects.
需要说明的是，由于摄像装置采用垂直俯角拍摄，且拍摄距离较高，所以在图像中，特定人体对象的标识性特征(如红色安全帽)，只会占据整张图像中很小范围。因此，若采用相关技术中，直接应用检测模型在整张图片中检测特定人体对象的方法，将存在很大程度的误检风险，例如：将非特定人体识别为特定人体，将非人体对象识别为上述特定人体对象。It should be noted that since the camera adopts vertical depression angle shooting and the shooting distance is relatively high, in the image, the identifying features of a specific human object (such as a red helmet) will only occupy a small area in the entire image. Therefore, if the method of directly applying the detection model to detect a specific human object in the whole picture is adopted in the related technology, there will be a great risk of false detection, for example, identifying a non-specific human body as a specific human body, and identifying a non-human body object as a specific human body. For the above-mentioned specific human subjects.
而在本申请实施例中，相比较于相关技术，并不直接从图像中检测特定人体对象，而是首先通过检测模型，从实时图像中获取所有人体对象(包括特定人体和非特定人体)组成人体框图，进一步的，再将所有人体对象框图输入分类模型，通过该分类模型，在所有人体对象框图这个较小的范围内，进行二分类，得到特定人体对象。从而极大程度的避免误检风险，提升检测准确率。However, in the embodiment of the present application, compared with the related art, the specific human object is not directly detected from the image, but all human objects (including the specific human body and the non-specific human body) are firstly obtained from the real-time image through the detection model. Human body block diagram, further, input all human body object block diagrams into the classification model, and through the classification model, within the smaller range of all human body object block diagrams, two classifications are performed to obtain specific human body objects. In this way, the risk of false detection is greatly avoided and the detection accuracy is improved.
S205，根据当前图像中的吊钩，在当前图像中确定目标区域，实时跟踪特定人体对象，获取其对应在当前图像中的坐标，并判断坐标在预设时间段内是否处于目标区域，若否，指示发送安全警报。S205, according to the hook in the current image, determine the target area in the current image, track the specific human object in real time, obtain its corresponding coordinates in the current image, and determine whether the coordinates are in the target area within the preset time period, if not , instructs to send a security alert.
需要说明的是，跟踪特定人体对象的过程，可以采用卡尔曼滤波结合匈牙利算法实现。It should be noted that the process of tracking a specific human object can be realized by using Kalman filtering combined with the Hungarian algorithm.
可选的，上述预设时间段可以是10分钟，当识别到该特定人体对象在预设时间段内未处于图像中吊钩下的目标区域时，即相当于信号员脱离监督岗位已超出要求时间。Optionally, the above-mentioned preset time period may be 10 minutes. When it is recognized that the specific human object is not in the target area under the hook in the image within the preset time period, it is equivalent to that the signalman has exceeded the requirements for leaving the supervision position. time.
在该种情况下，服务器指示报警装置发送安全警报，提醒信号员迅速回归监督岗位，或者通报管理人员进行进一步决策，其中，该报警装置可以是语音报警装置，例如，工地广播、便携仪通讯装置等。In this case, the server instructs the alarm device to send a safety alarm to remind the signalman to quickly return to the supervisory post, or notify the management personnel for further decision-making, wherein the alarm device may be a voice alarm device, such as a construction site broadcast, a portable instrument communication device Wait.
通过上述步骤S201至S205，相比较于相关技术中起吊装置施工现场的安全检测方法，本申请通过检测模型获取所有人体对象，进一步的，再通过分类模型从所有人体对象中识别出负责施工监督的佩戴红色安全帽的信号员。从而在识别出信号员超出吊钩之下的活动范围达到一定时间后，发送报警信号以提醒其迅速回归监督岗位。本申请实施例实现了对于特定人群的识别，提升了塔吊施工现场的安全监测能力，进一步的保障了施工人员的安全。Through the above steps S201 to S205, compared with the safety detection method on the construction site of the hoisting device in the related art, the present application obtains all human objects through the detection model, and further, through the classification model, identifies from all the human objects the person responsible for construction supervision Signalman in red hard hat. Therefore, after it is identified that the signalman has exceeded the scope of activity under the hook for a certain period of time, an alarm signal is sent to remind him to quickly return to the supervisory post. The embodiment of the present application realizes the identification of specific groups of people, improves the safety monitoring capability of the tower crane construction site, and further ensures the safety of construction personnel.
在其中一些实施例中，检测模型检测目标对象的过程包括：通过主干网络，提取历史图像或当前图像中的特征，其中，主干网络为Ghostnet结构，通过neck 层融合特征得到特征图，其中，neck层为PAN结构，通过检测头检测特征图，得到目标对象。In some of the embodiments, the process of detecting the target object by the detection model includes: extracting features in historical images or current images through a backbone network, wherein the backbone network is a Ghostnet structure, and obtaining a feature map by fusing the features at the neck layer, wherein the neck The layer is a PAN structure, and the target object is obtained by detecting the feature map through the detection head.
其中，Ghost模块，可以作为即插即用的组件来升级现有的卷积神经网络，而基于Ghost模块的堆叠则建立了轻量级的Ghostnet网络结构，具体的：Among them, the Ghost module can be used as a plug-and-play component to upgrade the existing convolutional neural network, and the stacking based on the Ghost module establishes a lightweight Ghostnet network structure, specifically:
Ghostnet网络结构中，一个普通卷积层会被分成两部分，第一部分涉及普通卷积，但它们的总数将受到严格控制；进一步的，再给定第一部分的内在特征图，应用简单的线性操作来生成更多的特征图。从而，在不改变输出特征图的大小的情况下，与传统的Bckbone卷积神经网络相比，Ghostnet网络结构所需的总体参数数量和计算复杂度有所降低。In the Ghostnet network structure, an ordinary convolutional layer will be divided into two parts. The first part involves ordinary convolutions, but their total number will be strictly controlled; further, given the intrinsic feature map of the first part, a simple linear operation is applied. to generate more feature maps. Thus, without changing the size of the output feature map, the overall number of parameters and computational complexity required by the Ghostnet network structure are reduced compared to the traditional Bckbone convolutional neural network.
进一步的，图3是根据本申请实施例的一种在neck层进行特征融合的示意图，如图3所示，Further, FIG. 3 is a schematic diagram of feature fusion at the neck layer according to an embodiment of the present application, as shown in FIG. 3 ,
传统的FPN结构仅执行自顶向下的采样，将高层特征通过上采样和低层特征做融合得到特征图。The traditional FPN structure only performs top-down sampling, and fuses high-level features with low-level features to obtain feature maps.
而在本实施例中，在FPN层的基础上，还添加了一个自底向上的特征金字塔结构(PAN结构)。通过两种采样层的结合操作，由FPN层自顶向下传达强语义特征，金字塔结构则自底向上传达定位特征，将语义特征和定位特征相结合，从不同的主干层对不同的检测层得到的特征进行参数聚合，从而得到效果更好的特征图。In this embodiment, on the basis of the FPN layer, a bottom-up feature pyramid structure (PAN structure) is also added. Through the combination operation of the two sampling layers, the FPN layer conveys strong semantic features from top to bottom, and the pyramid structure conveys localization features from the bottom to the top, combining semantic features and localization features, from different backbone layers to different detection layers The obtained features are subjected to parameter aggregation to obtain a better feature map.
图4是根据本申请实施例的一种检测模型的结构图，如图4所示，将施工现场图像输入模型，经过Ghostnet提取特征和PAN融合特征得到特征图，再经过检测头处理，得到输出yolo1、yolo2和yolo3。FIG. 4 is a structural diagram of a detection model according to an embodiment of the present application. As shown in FIG. 4 , a construction site image is input into the model, features are extracted through Ghostnet and PAN fusion features are obtained to obtain a feature map, and then the detection head is processed to obtain an output. yolo1, yolo2, and yolo3.
在其中一些实施例中，在检测模型的训练过程中，通过mixup增强数据扩充历史数据集，进一步的，采用BCEWithLogitsLoss作为分类损失函数，采用 IoU loss作为回归损失函数。In some of the embodiments, during the training process of the detection model, the historical data set is augmented by mixup enhancement data, and further, BCEWithLogitsLoss is used as the classification loss function, and IoU loss is used as the regression loss function.
需要说明的是，由于实际施工过程对应的图像，存在各种不同类型的情况，具体的，包括有人体遮挡或人体重叠图像、人体距离远或人体距离近的图像、人体轮廓大或轮廓小的图像等。而又因为采集和标注图像的数量是有限的，因此，用于训练的历史数据集并不能覆盖所有施工现场的情况，因此需要通过数据增强机制，利用现有的图像进行融合叠加，生成与原有图像类似但不完全相同的图像数据，从而填补现有图像之间的空白，丰富了数据的多样性，也提升模型的泛化能力。It should be noted that due to the images corresponding to the actual construction process, there are various types of situations, specifically, including images with human body occlusion or overlapping human bodies, images with far or close human body distances, and large or small outlines of the human body. images etc. And because the number of collected and annotated images is limited, the historical data set used for training cannot cover all construction sites. Therefore, it is necessary to use the existing images for fusion and superposition through the data enhancement mechanism to generate the same image as the original image. There are image data with similar but not identical images, thereby filling the gaps between existing images, enriching the diversity of data, and improving the generalization ability of the model.
在本申请实施例中，利用mixup数据增强的特性，在丰富数据多样性的同时，在进行BN(Batch Normalization批量归一化)操作时的时候，也可以更好的统计均值和方差。In the embodiment of the present application, by using the feature of data enhancement of mixup, while enriching the data diversity, when performing the BN (Batch Normalization) operation, the mean and variance can also be better counted.
在其中一些实施例中，根据当前图像中的吊钩，在当前图像中确定目标区域，包括：获取吊钩对应在当前图像中的像素长度，以及获取吊钩的实际长度；确定实际长度与像素长度的转换比，以及信号工的在现实空间中的预设活动半径值；根据转换比，将预设活动半径值，转换为当前图像中的像素半径值；以吊钩的中心为圆心，根据像素半径值，在当前图像中确定目标区域。In some of the embodiments, determining the target area in the current image according to the hook in the current image includes: acquiring the pixel length of the hook corresponding to the current image, and acquiring the actual length of the hook; determining the actual length and the pixel length The conversion ratio of the length, and the preset active radius value of the signal worker in the real space; according to the conversion ratio, the preset active radius value is converted into the pixel radius value in the current image; the center of the hook is the center of the circle, according to the Pixel radius value to determine the target area in the current image.
需要说明的是，在上述流程中或者附图的流程图中示出的步骤可以在诸如一组计算机可执行指令的计算机系统中执行，并且，虽然在流程图中示出了逻辑顺序，但是在某些情况下，可以以不同于此处的顺序执行所示出或描述的步骤。It should be noted that the steps shown in the above flow or the flow chart of the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical sequence is shown in the flow chart, in the In some cases, steps shown or described may be performed in an order different from that herein.
本实施例还提供了一种起吊装置施工现场的安全监测系统，该系统用于实现上述实施例及优选实施方式，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 safety monitoring system for a construction site of a hoisting device, the system is used to implement the above-mentioned embodiments and preferred implementations, and the descriptions that have been described will not be repeated. As used below, the terms "module," "unit," "subunit," etc. may be a combination of software and/or hardware that implements a predetermined function. Although the apparatus described in the following embodiments is preferably implemented in software, implementations in hardware, or a combination of software and hardware, are also possible and contemplated.
图5是根据本申请实施例的起吊装置施工现场的安全监测系统的结构框图，如图5所示，该系统包括：预处理模块50、训练模块51和检测模块52，其中；Fig. 5 is a structural block diagram of a safety monitoring system at a construction site of a hoisting device according to an embodiment of the present application. As shown in Fig. 5, the system includes: a preprocessing
预处理模块50用于，获取起吊装置施工现场的历史图像集，并标注其中的目标对象，其中，目标对象包括吊钩、特定人体对象和非特定人体对象；The
训练模块51用于，构建检测网络和分类网络，基于标注之后的历史图像集，训练检测网络和分类网络，分别得到检测模型和分类模型；The
检测模块52用于，采集施工现场的当前图像，通过检测模型，检测当前图像中的人体对象和吊钩，通过分类模型，识别人体对象中的特定人体对象，以及根据当前图像中的吊钩和特定人体对象，在当前图像中确定目标区域，以及实时跟踪特定人体对象，获取其对应在当前图像中的坐标，并判断坐标，在预设时间段内是否处于目标区域，若否，指示发送安全警报。The
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终端。该计算机设备包括通过系统总线连接的处理器、存储器、网络接口、显示屏和输入装置。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、内存储器。该非易失性存储介质存储有操作系统和计算机程序。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。该计算机设备的网络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起吊装置施工现场的安全监测方法。该计算机设备的显示屏可以是液晶显示屏或者电子墨水显示屏，该计算机设备的输入装置可以是显示屏上覆盖的触摸层，也可以是计算机设备外壳上设置的按键、轨迹球或触控板，还可以是外接的键盘、触控板或鼠标等。In one embodiment, a computer device is provided, which may be a terminal. The computer equipment includes a processor, memory, a network interface, a display screen, and an input device connected by a system bus. Among them, 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, an internal memory. The nonvolatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the execution of the operating system and computer programs in the non-volatile storage medium. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a safety monitoring method for a construction site of a hoisting device is realized. The display screen of the computer equipment may be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer equipment may be a touch layer covered on the display screen, or a button, a trackball or a touchpad set on the shell of the computer equipment , or an external keyboard, trackpad, or mouse.
在一个实施例中，图6是根据本申请实施例的电子设备的内部结构示意图，如图6所示，提供了一种电子设备，该电子设备可以是服务器，其内部结构图可以如图6所示。该电子设备包括通过内部总线连接的处理器、网络接口、内存储器和非易失性存储器，其中，该非易失性存储器存储有操作系统、计算机程序和数据库。处理器用于提供计算和控制能力，网络接口用于与外部的终端通过网络连接通信，内存储器用于为操作系统和计算机程序的运行提供环境，计算机程序被处理器执行时以实现一种起吊装置施工现场的安全监测方法，数据库用于存储数据。In one embodiment, FIG. 6 is a schematic diagram of the internal structure of an electronic device according to an embodiment of the present application. As shown in FIG. 6 , an electronic device is provided. The electronic device may be a server, and its internal structure diagram may be as shown in FIG. 6 . shown. The electronic device includes a processor, a network interface, an internal memory, and a non-volatile memory connected by an internal bus, wherein the non-volatile memory stores an operating system, a computer program, and a database. The processor is used to provide computing and control capabilities, the network interface is used to communicate with external terminals through a network connection, and the internal memory is used to provide an environment for the operation of the operating system and the computer program. When the computer program is executed by the processor, a lifting device is realized. Safety monitoring method on construction site, database is used to store data.
本领域技术人员可以理解，图6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电子设备的限定，具体的电子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 can understand that the structure shown in FIG. 6 is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the electronic device to which the solution of the present application is applied. The specific electronic device may be Include more or fewer components than shown in the figures, or combine certain components, or have a different arrangement of components.
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，该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、存储、数据库或其它介质的任何引用，均可包括非易失性和/或易失性存储器。非易失性存储器可包括只读存储器(ROM)、可编程ROM(PROM)、电可编程 ROM(EPROM)、电可擦除可编程ROM(EEPROM)或闪存。易失性存储器可包括随机存取存储器(RAM)或者外部高速缓冲存储器。作为说明而非局限， RAM以多种形式可得，诸如静态RAM(SRAM)、动态RAM(DRAM)、同步 DRAM(SDRAM)、双数据率SDRAM(DDRSDRAM)、增强型SDRAM (ESDRAM)、同步链路(Synchlink)DRAM(SLDRAM)、存储器总线(Rambus) 直接RAM(RDRAM)、直接存储器总线动态RAM(DRDRAM)、以及存储器总线动态RAM(RDRAM)等。Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be implemented by instructing 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 may include the processes of the above-mentioned method embodiments. Wherein, any reference to memory, storage, database or other medium used in the various embodiments provided in this application may include non-volatile and/or volatile memory. Nonvolatile memory may include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous chain Synchlink DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.
以上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发明专利范围的限制。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，本申请专利的保护范围应以所附权利要求为准。The above examples only represent several embodiments of the present application, and the descriptions thereof are relatively specific and detailed, but should not be construed as a limitation on the scope of the invention patent. It should be pointed out that for those skilled in the art, without departing from the concept of the present application, several modifications and improvements can be made, which all belong to the protection scope of the present application. Therefore, the scope of protection of the patent of the present application shall be subject to the appended claims.
Claims (10)
Translated fromChinesePriority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210613319.6ACN115180522B (en) | 2022-05-31 | 2022-05-31 | Safety monitoring method and system for construction site of hoisting device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210613319.6ACN115180522B (en) | 2022-05-31 | 2022-05-31 | Safety monitoring method and system for construction site of hoisting device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115180522Atrue CN115180522A (en) | 2022-10-14 |
| CN115180522B CN115180522B (en) | 2025-08-01 |
Family
ID=83513674
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210613319.6AActiveCN115180522B (en) | 2022-05-31 | 2022-05-31 | Safety monitoring method and system for construction site of hoisting device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115180522B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115601712A (en)* | 2022-12-15 | 2023-01-13 | 南京电力自动化设备三厂有限公司（Cn） | Image data processing method and system suitable for field safety measures |
| CN115818449A (en)* | 2022-11-28 | 2023-03-21 | 武汉建筑材料工业设计研究院有限公司 | A method and system for safety protection of gas filling production line based on machine vision |
| CN118134970A (en)* | 2024-05-06 | 2024-06-04 | 山西太重数智科技股份有限公司 | Jack-up and lifting hook detection tracking method and system based on image recognition |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110745704A (en)* | 2019-12-20 | 2020-02-04 | 广东博智林机器人有限公司 | Tower crane early warning method and device |
| US20200062555A1 (en)* | 2018-08-22 | 2020-02-27 | Tnt Crane & Rigging, Inc. | Remotely Operated Crane System |
| CN111091098A (en)* | 2019-12-20 | 2020-05-01 | 浙江大华技术股份有限公司 | Training method and detection method of detection model and related device |
| CN113033518A (en)* | 2021-05-25 | 2021-06-25 | 北京中科闻歌科技股份有限公司 | Image detection method, image detection device, electronic equipment and storage medium |
- 2022
- 2022-05-31CNCN202210613319.6Apatent/CN115180522B/enactiveActive
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200062555A1 (en)* | 2018-08-22 | 2020-02-27 | Tnt Crane & Rigging, Inc. | Remotely Operated Crane System |
| CN110745704A (en)* | 2019-12-20 | 2020-02-04 | 广东博智林机器人有限公司 | Tower crane early warning method and device |
| CN111091098A (en)* | 2019-12-20 | 2020-05-01 | 浙江大华技术股份有限公司 | Training method and detection method of detection model and related device |
| CN113033518A (en)* | 2021-05-25 | 2021-06-25 | 北京中科闻歌科技股份有限公司 | Image detection method, image detection device, electronic equipment and storage medium |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115818449A (en)* | 2022-11-28 | 2023-03-21 | 武汉建筑材料工业设计研究院有限公司 | A method and system for safety protection of gas filling production line based on machine vision |
| CN115601712A (en)* | 2022-12-15 | 2023-01-13 | 南京电力自动化设备三厂有限公司（Cn） | Image data processing method and system suitable for field safety measures |
| CN115601712B (en)* | 2022-12-15 | 2023-08-22 | 南京电力自动化设备三厂有限公司 | Image data processing method and system suitable for site safety measures |
| CN118134970A (en)* | 2024-05-06 | 2024-06-04 | 山西太重数智科技股份有限公司 | Jack-up and lifting hook detection tracking method and system based on image recognition |
| CN118134970B (en)* | 2024-05-06 | 2024-07-09 | 山西太重数智科技股份有限公司 | Jack-up and lifting hook detection tracking method and system based on image recognition |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115180522B (en) | 2025-08-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113516076B (en) | An improved lightweight YOLO v4 security protection detection method based on attention mechanism | |
| CN115180522A (en) | Safety monitoring method and system for hoisting device construction site | |
| CN108052859B (en) | A method, system and device for abnormal behavior detection based on clustered optical flow features | |
| CN108009473B (en) | Video structured processing method, system and storage device based on target behavior attribute | |
| CN108062349B (en) | Video surveillance method and system based on video structured data and deep learning | |
| CN110222672B (en) | Method, device and equipment for detecting wearing of safety helmet in construction site and storage medium | |
| CN110969130B (en) | Driver dangerous action identification method and system based on YOLOV3 | |
| CN112216049A (en) | Construction warning area monitoring and early warning system and method based on image recognition | |
| CN111783744A (en) | Operation site safety protection detection method and device | |
| US20220366697A1 (en) | Image processing method and apparatus, electronic device and storage medium | |
| CN110619277A (en) | Multi-community intelligent deployment and control method and system | |
| CN112396658A (en) | Indoor personnel positioning method and positioning system based on video | |
| CN113743256B (en) | Intelligent early warning method and device for site safety | |
| CN110111016A (en) | Method and device for monitoring dangerous state of operating personnel and computer equipment | |
| CN111652128B (en) | A safety monitoring method, system and storage device for high-altitude electric power work | |
| CN112184773A (en) | A kind of safety helmet wearing detection method and system based on deep learning | |
| WO2022121498A1 (en) | Identity recognition method, model training method, apparatuses, and device and storage medium | |
| CN115661766A (en) | Intelligent ship safety monitoring method and system based on deep learning | |
| CN111523362A (en) | Data analysis method and device based on electronic purse net and electronic equipment | |
| Wu et al. | Automated visual helmet identification based on deep convolutional neural networks | |
| CN114140849A (en) | Electric power infrastructure field personnel state management method and system based on expression recognition | |
| CN115146830A (en) | Method and system for intelligently identifying taxi taking intention of passerby and vehicle thereof | |
| CN118552772A (en) | Construction dangerous area personnel intrusion detection method and model building method thereof | |
| CN116912037A (en) | Safety monitoring system and method for building construction based on image processing | |
| CN115995097A (en) | Deep learning-based safety helmet wearing standard judging method |
Legal Events
| 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |