【技术领域】【Technical field】
本发明涉及车型识别技术领域，特别是涉及一种基于局部区域特征的车型识别方法和装置。The invention relates to the technical field of vehicle identification, in particular to a vehicle identification method and device based on local area features.
【背景技术】【Background technique】
随着我国经济的快速发展，汽车数量正在持续快速增加，而道路设施与汽车数量高速增长的矛盾显现，交通拥挤严重影响人们的出行，多发的交通事故进一步加剧交通拥挤。如何在这样的背景下识别出车辆的类型、车辆的特征模型及特征获取是解决问题的关键。With the rapid development of my country's economy, the number of cars continues to increase rapidly, and the contradiction between road facilities and the rapid growth of the number of cars appears. Traffic congestion seriously affects people's travel, and frequent traffic accidents further aggravate traffic congestion. How to identify the vehicle type, vehicle feature model and feature acquisition under such a background is the key to solving the problem.
车型识别方法是对现有的车牌自动识别系统的一次较大扩展。针对不同的应用,研究人员也釆用了不同的研究方法。在现阶段,车型识别的研究主要应用在两个方面:车辆结构(大型车,小型车)和车辆型号上(不同品牌型号)。在目前的车辆类型判别中，通过小波分析、模糊理论、神经网络等技术，主要集中在车辆结构上进行车型识别，如客车、货车，轿车车型分类，没有对车型进行具体的分类识别。The vehicle type recognition method is a large expansion of the existing automatic license plate recognition system. For different applications, researchers have also adopted different research methods. At this stage, the research on vehicle type recognition is mainly applied in two aspects: vehicle structure (large car, small car) and vehicle model (different brand models). In the current vehicle type discrimination, through wavelet analysis, fuzzy theory, neural network and other technologies, it mainly focuses on the vehicle structure for vehicle type identification, such as the classification of passenger cars, trucks, and sedan models, without specific classification and identification of vehicle types.
【发明内容】【Content of invention】
本发明要解决的技术问题是目前的车辆类型判别中，通过小波分析、模糊理论、神经网络等技术，主要集中在车辆结构上进行车型识别，如客车、货车，轿车车型分类，没有一种对车型进行具体的分类识别的方法。The technical problem to be solved by the present invention is that in the current vehicle type discrimination, through technologies such as wavelet analysis, fuzzy theory, neural network, etc., mainly focus on the vehicle structure for vehicle type identification, such as passenger cars, trucks, and car type classifications. A method for specific classification and identification of vehicle types.
本发明一方面，提出了一种基于局部区域特征的车型识别方法，包括：In one aspect of the present invention, a vehicle type identification method based on local area features is proposed, including:
调取视频监控设备记录的一帧图片数据；截取所述图片中的目标区域，匹配出该目标区域所对应的特征库，所述目标区域包括车头区域、车尾区域和/或车身区域；调用匹配出的特征库，并基于所述目标区域的特征检测，识别所述目标区域所对应的车型。Call a frame of picture data recorded by the video surveillance equipment; intercept the target area in the picture, match the feature library corresponding to the target area, and the target area includes the front area, the rear area and/or the body area; call The matching feature library is used to identify the vehicle type corresponding to the target area based on the feature detection of the target area.
优选的，所述匹配出该目标区域所对应的特征库，具体包括：Preferably, said matching the feature library corresponding to the target area specifically includes:
根据车辆中驾驶员和/或车轮的轮廓特性，识别该目标区域式属于车头区域、车尾区域或车身区域。Depending on the profile properties of the driver and/or the wheels in the vehicle, it is recognized that the target area belongs to the front area, the rear area or the body area.
优选的，所述基于所述目标区域的特征检测，具体包括：Preferably, the feature detection based on the target area specifically includes:
对目标区域进行Sobe l边缘检测，获得目标区域的轮廓数据，对轮廓图像计算Hu不变矩；利用surf算法对目标区域进行特征点检测，计算surf特征描述子；将Hu不变矩和surf特征描述子的特征参数输入到BP神经网络中进行识别。Perform Sobe l edge detection on the target area, obtain the contour data of the target area, and calculate the Hu invariant moment for the contour image; use the surf algorithm to detect the feature points of the target area, and calculate the surf feature descriptor; combine the Hu invariant moment and the surf feature The characteristic parameters of the descriptor are input into the BP neural network for identification.
优选的，在进行所述车型识别之前，所述方法还包括：进行BP神经网络的学习，并在训练误差在预设阈值内时，结束所述BP神经网络的学习。Preferably, before performing the vehicle type identification, the method further includes: performing learning of the BP neural network, and ending the learning of the BP neural network when the training error is within a preset threshold.
本发明在另一方面，提供了一种基于局部区域特征的车型识别方法，其特征在于，包括：In another aspect, the present invention provides a vehicle identification method based on local area features, which is characterized in that it includes:
从监控视频中获取一帧图片数据；截取所述图片中的目标区域，对目标区域进行Sobel边缘检测，获得目标区域的轮廓数据，对所述轮廓数据计算Hu不变矩；利用surf算法对目标区域进行特征点检测，计算surf特征描述子；将Hu不变矩和surf特征描述子的特征参数输入到BP神经网络中进行识别，得出所述目标的车型结果数据。Obtain a frame of picture data from the surveillance video; intercept the target area in the picture, perform Sobel edge detection on the target area, obtain the outline data of the target area, and calculate the Hu invariant moments for the outline data; use the surf algorithm to calculate the target area The feature points are detected in the area, and the surf feature descriptor is calculated; the Hu invariant moments and the feature parameters of the surf feature descriptor are input into the BP neural network for identification, and the vehicle model result data of the target is obtained.
优选的，所述目标区域包括车头区域、车尾区域和/或车身区域。Preferably, the target area includes the front area, the rear area and/or the body area.
优选的，在进行所述车型识别之前，所述方法还包括：进行BP神经网络的学习，并在训练误差在预设阈值内时，结束所述BP神经网络的学习。Preferably, before performing the vehicle type identification, the method further includes: performing learning of the BP neural network, and ending the learning of the BP neural network when the training error is within a preset threshold.
本发明另一方面，还提供了一种基于局部区域特征的车型识别装置，包括I/O装置、存储装置、处理装置和显示装置，具体的：Another aspect of the present invention also provides a vehicle identification device based on local area features, including an I/O device, a storage device, a processing device and a display device, specifically:
所述I/O装置，用于接收操作人员调取视频监控装置记录的一帧图片数据的操作指令；所述存储装置，用于存储特征库；所述处理装置，用于截取所述图片中的目标区域，匹配出该目标区域所对应的特征库，所述目标区域包括车头区域、车尾区域和/或车身区域；调用匹配出的特征库，并基于所述目标区域的特征检测，识别所述目标区域所对应的车型；The I/O device is used to receive an operation instruction for the operator to call a frame of picture data recorded by the video monitoring device; the storage device is used to store a feature library; the processing device is used to intercept the image in the picture The target area, match the feature library corresponding to the target area, the target area includes the front area, the rear area and/or the body area; call the matched feature library, and based on the feature detection of the target area, identify The vehicle type corresponding to the target area;
所述显示装置，用于显示识别出的车型结果。的特征检测，识别所述目标特征检测，识别所述目标区域所对应的车型；所述显示装置，用于显示识别出的车型结果。The display device is used for displaying the result of the recognized vehicle type. The feature detection is used to identify the target feature detection and identify the vehicle type corresponding to the target area; the display device is used to display the result of the identified vehicle type.
与现有技术相比，本发明的有益效果在于：本发明利用图像理论及计算机视觉技术快速对车型进行识别，进而对电子警察监控，肇事(车辆在发生事故后，会呈现不同的车辆姿态)、嫌疑、被盗车辆进行智能识别，并为进一步对交通事故责任的认定提供技术支持。Compared with the prior art, the beneficial effect of the present invention is that: the present invention uses image theory and computer vision technology to quickly identify the vehicle type, and then monitor the electronic police, causing accidents (vehicles will present different vehicle postures after an accident) , suspected, and stolen vehicles for intelligent identification, and provide technical support for further identification of traffic accident responsibilities.
【附图说明】【Description of drawings】
图1是本发明实施例提供的一种基于局部区域特征的车型识别方法的流程图；Fig. 1 is a flow chart of a vehicle identification method based on local area features provided by an embodiment of the present invention;
图2是本发明实施例提供的一种基于局部区域特征的车型识别方法的流程图；Fig. 2 is a flow chart of a vehicle identification method based on local area features provided by an embodiment of the present invention;
图3是本发明实施例提供的一种基于局部区域特征的车型识别装置的结构示意图。Fig. 3 is a schematic structural diagram of a vehicle type identification device based on local area features provided by an embodiment of the present invention.
【具体实施方式】【detailed description】
为了使本发明的目的、技术方案及优点更加清楚明白，以下结合附图及实施例，对本发明进行进一步详细说明。应当理解，此处所描述的具体实施例仅仅用以解释本发明，并不用于限定本发明。In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.
此外，下面所描述的本发明各个实施方式中所涉及到的技术特征只要彼此之间未构成冲突就可以相互组合。In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not constitute a conflict with each other.
实施例1:Example 1:
本发明实施例1提供了一种基于局部区域特征的车型识别方法，如图1所示，包括：Embodiment 1 of the present invention provides a vehicle identification method based on local area features, as shown in FIG. 1 , including:
在步骤201中，调取视频监控设备记录的一帧图片数据。In step 201, a frame of picture data recorded by a video surveillance device is retrieved.
在步骤202中，截取所述图片中的目标区域，匹配出该目标区域所对应的特征库，所述目标区域包括车头区域、车尾区域和/或车身区域。In step 202, a target area in the picture is intercepted, and a feature library corresponding to the target area is matched, and the target area includes a front area, a rear area and/or a body area.
在步骤203中，调用匹配出的特征库，并基于所述目标区域的特征检测，识别所述目标区域所对应的车型。In step 203, the matched feature library is invoked, and based on the feature detection of the target area, the vehicle type corresponding to the target area is identified.
本发明根据视频监控设备记录车辆的特性，将其记录的图片数据做了特性归类，分为了车头区域、车尾区域和车身区域，并利用图像理论及计算机视觉技术快速对车型进行识别，进而对电子警察监控，肇事(车辆在发生事故后，会呈现不同的车辆姿态)、嫌疑、被盗车辆进行智能识别，并为进一步对交通事故责任的认定提供技术支持。According to the characteristics of the vehicle recorded by the video monitoring equipment, the invention classifies the recorded picture data into characteristics, and divides them into the front area, the rear area and the body area, and uses image theory and computer vision technology to quickly identify the vehicle type, and then Intelligent identification of electronic police monitoring, accidents (vehicles will show different vehicle postures after an accident), suspected and stolen vehicles, and provide technical support for further identification of traffic accident responsibilities.
在本实施例中，所述匹配出该目标区域所对应的特征库，存在一种可行的实现方式，具体包括：In this embodiment, there is a feasible implementation method for matching the feature library corresponding to the target area, which specifically includes:
根据车辆中驾驶员和/或车轮的轮廓特性，识别该目标区域式属于车头区域、车尾区域或车身区域。Depending on the profile properties of the driver and/or the wheels in the vehicle, it is recognized that the target area belongs to the front area, the rear area or the body area.
在本实施例中，所述基于所述目标区域的特征检测，存在一种可行的实现方式，具体包括：In this embodiment, there is a feasible implementation of the feature detection based on the target area, which specifically includes:
对目标区域进行Sobel边缘检测，获得目标区域的轮廓数据，对轮廓图像计算Hu不变矩。Sobel edge detection is performed on the target area to obtain the contour data of the target area, and the Hu invariant moment is calculated for the contour image.
在具体的实现过程中，在得到轮廓图像对应的Hu不变矩时，还不能严格的区别出不同的车型特征，优选的在此基础上还需要进行一下步骤：In the specific implementation process, when obtaining the Hu invariant moment corresponding to the contour image, it is still not possible to strictly distinguish the characteristics of different vehicle types. It is preferable to perform the following steps on this basis:
利用surf算法对目标区域进行特征点检测，计算surf特征描述子。Use the surf algorithm to detect the feature points of the target area, and calculate the surf feature descriptor.
结合Hu不变矩和所述surf特征描述子后，已经可以较好的区别不同的车型，并能基于此识别出车型特征，但是，为了达到更小的误差率，本发明实施例还提供了一种优选方案，具体包括：将Hu不变矩和surf特征描述子的特征参数输入到BP神经网络中进行识别。After combining the Hu invariant moment and the surf feature descriptor, it is possible to distinguish different car models better, and to identify the car model features based on this. However, in order to achieve a smaller error rate, the embodiment of the present invention also provides A preferred solution specifically includes: inputting Hu invariant moments and characteristic parameters of the surf feature descriptor into a BP neural network for identification.
在本发明实施例采用BP神经网络匹配模型是，则在进行所述车型识别之前，所述方法还包括：When the BP neural network matching model is adopted in the embodiment of the present invention, before performing the vehicle identification, the method also includes:
进行BP神经网络的学习，并在训练误差在预设阈值内时，结束所述BP神经网络的学习。Carrying out the learning of the BP neural network, and ending the learning of the BP neural network when the training error is within the preset threshold.
实施例2:Example 2:
本发明实施例2提供了一种基于局部区域特征的车型识别方法，包括：Embodiment 2 of the present invention provides a vehicle identification method based on local area features, including:
在步骤301中，从监控视频中获取一帧图片数据。In step 301, a frame of picture data is acquired from a surveillance video.
在步骤302中，截取所述图片中的目标区域，对目标区域进行Sobel边缘检测，获得目标区域的轮廓数据，对所述轮廓数据计算Hu不变矩。In step 302, the target area in the picture is intercepted, Sobel edge detection is performed on the target area to obtain contour data of the target area, and Hu invariant moments are calculated for the contour data.
在具体实现中，可以利用轮廓的二值图像来代替灰度图像，简化了Hu不变矩的计算过程，其原点矩和中心矩的定义为：In the specific implementation, the binary image of the contour can be used to replace the grayscale image, which simplifies the calculation process of the Hu invariant moment. The origin moment and central moment are defined as:
其中,p,q＝0,1,2…,n,归一化的中心矩为Among them, p, q=0,1,2...,n, the normalized central moment is
利用代数不变量理论构造下面7个不变矩：Using the theory of algebraic invariants to construct the following seven invariant moments:
M1＝η20+η02M1 =η20 +η02
M2＝(η20-η02)2+4η121M2 =(η20 -η02 )2 +4η121
M3＝(η30-3η12)2+(η03-3η21)2M3 =(η30 -3η12 )2 +(η03 -3η21 )2
M4＝(η30+η12)2+(η03+η21)2M4 =(η30 +η12 )2 +(η03 +η21 )2
M5＝(η30-3η12)(η30+η12)[(η30+η12)2-3(η03+η21)2]M5 =(η30 -3η12 )(η30 +η12 )[(η30 +η12 )2 -3(η03 +η21 )2 ]
+(3η21-η03)(η21+η03)[3(η30+η12)2-(η03+η21)2]+(3η21 -η03 )(η21 +η03 )[3(η30 +η12 )2 -(η03 +η21 )2 ]
M6＝(η20-η02)[(η30+η12)2-(η03-η21)2]+4η11(η30+η12)(η03+η21)M6 =(η20 -η02 )[(η30 +η12 )2 -(η03 -η21 )2 ]+4η11 (η30 +η12 )(η03 +η21 )
M7＝(3η21-η03)(η30+η12)[(η30+η12)2-3(η03+η21)2]M7 =(3η21 -η03 )(η30 +η12 )[(η30 +η12 )2 -3(η03 +η21 )2 ]
+(3η21-η03)(η21+η03)[3(η30+η12)2-(η03+η21)2]+(3η21 -η03 )(η21 +η03 )[3(η30 +η12 )2 -(η03 +η21 )2 ]
在步骤303中，利用surf算法对目标区域进行特征点检测，计算surf特征描述子。In step 303, the surf algorithm is used to detect the feature points of the target area, and the surf feature descriptor is calculated.
在步骤304中，将Hu不变矩和surf特征描述子的特征参数输入到BP神经网络中进行识别，得出所述目标的车型结果数据。In step 304, the characteristic parameters of the Hu invariant moments and the surf characteristic descriptor are input into the BP neural network for identification, and the vehicle model result data of the target is obtained.
本发明根据并利用图像理论及计算机视觉技术，集合Hu不变矩和surf特征描述子，并通过BP神经网络匹配方法，快速对车型进行识别，进而对电子警察监控，肇事、嫌疑、被盗车辆进行智能识别，并为进一步对交通事故责任的认定提供技术支持。According to and using image theory and computer vision technology, the present invention integrates Hu invariant moments and surf feature descriptors, and uses BP neural network matching method to quickly identify vehicle types, and then monitor electronic police, accidents, suspects, and stolen vehicles Carry out intelligent identification and provide technical support for further identification of traffic accident responsibilities.
本实施例中，所述目标区域，可选的，包括车头区域、车尾区域和/或车身区域。In this embodiment, the target area may optionally include a front area, a rear area and/or a body area.
在不实施例中，由于采用了BP神经网络的学习，因此，在进行所述车型识别之前，所述方法还需要包括：In an embodiment, since the learning of the BP neural network is adopted, before performing the vehicle identification, the method also needs to include:
进行BP神经网络的学习，并在训练误差在预设阈值内时，结束所述BP神经网络的学习。Carrying out the learning of the BP neural network, and ending the learning of the BP neural network when the training error is within the preset threshold.
实施例3:Embodiment 3:
本发明实施例3提供了一种基于局部区域特征的车型识别装置1，包括I/O装置、存储装置、处理装置和显示装置，具体的：Embodiment 3 of the present invention provides a vehicle type identification device 1 based on local area features, including an I/O device, a storage device, a processing device and a display device, specifically:
所述I/O装置11，用于接收操作人员调取视频监控装置记录的一帧图片数据的操作指令；The I/O device 11 is used to receive an operation instruction for an operator to call a frame of picture data recorded by a video monitoring device;
所述存储装置12，用于存储特征库；The storage device 12 is used to store a feature library;
所述处理装置13，用于截取所述图片中的目标区域，匹配出该目标区域所对应的特征库，所述目标区域包括车头区域、车尾区域和/或车身区域；调用匹配出的特征库，并基于所述目标区域的特征检测，识别所述目标区域所对应的车型；The processing device 13 is configured to intercept the target area in the picture, and match the feature library corresponding to the target area, the target area includes the front area, the rear area and/or the body area; call the matched feature Library, and based on the feature detection of the target area, identify the vehicle type corresponding to the target area;
所述显示装置14，用于显示识别出的车型结果。The display device 14 is used for displaying the result of the recognized vehicle type.
值得说明的是，上述装置和系统内的模块、单元之间的信息交互、执行过程等内容，由于与本发明的处理方法实施例基于同一构思，具体内容可参见本发明方法实施例中的叙述，此处不再赘述。It is worth noting that the information interaction and execution process between the above-mentioned devices and modules and units in the system are based on the same idea as the embodiment of the processing method of the present invention, and the specific content can refer to the description in the embodiment of the method of the present invention , which will not be repeated here.
本领域普通技术人员可以理解实施例的各种方法中的全部或部分步骤是可以通过程序来指令相关的硬件来完成，该程序可以存储于一计算机可读存储介质中，存储介质可以包括：只读存储器(ROM，Read Only Memory)、随机存取存储器(RAM，Random AccessMemory)、磁盘或光盘等。Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the embodiments can be completed by instructing related hardware through a program. The program can be stored in a computer-readable storage medium, and the storage medium can include: only Read memory (ROM, Read Only Memory), random access memory (RAM, Random AccessMemory), magnetic disk or optical disk, etc.
以上所述仅为本发明的较佳实施例而已，并不用以限制本发明，凡在本发明的精神和原则之内所作的任何修改、等同替换和改进等，均应包含在本发明的保护范围之内。The above descriptions are only preferred embodiments of the present invention, and are not intended to limit the present invention. Any modifications, equivalent replacements and improvements made within the spirit and principles of the present invention should be included in the protection of the present invention. within range.
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510090518.3ACN104680795B (en) | 2015-02-28 | 2015-02-28 | A kind of model recognizing method and device based on local features |
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510090518.3ACN104680795B (en) | 2015-02-28 | 2015-02-28 | A kind of model recognizing method and device based on local features |
| Publication Number | Publication Date |
|---|---|
| CN104680795A CN104680795A (en) | 2015-06-03 |
| CN104680795Btrue CN104680795B (en) | 2018-02-27 |
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510090518.3AExpired - Fee RelatedCN104680795B (en) | 2015-02-28 | 2015-02-28 | A kind of model recognizing method and device based on local features |
| Country | Link |
|---|---|
| CN (1) | CN104680795B (en) |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105447456A (en)* | 2015-11-17 | 2016-03-30 | 上海良相智能化工程有限公司 | Intelligent visual vehicle identification method |
| CN106530317B (en)* | 2016-09-23 | 2019-05-24 | 南京凡豆信息科技有限公司 | A kind of scoring of simple picture computer and auxiliary painting methods |
| CN107273792A (en)* | 2017-04-27 | 2017-10-20 | 北京果毅科技有限公司 | Model recognizing method and device |
| CN108681707A (en)* | 2018-05-15 | 2018-10-19 | 桂林电子科技大学 | Wide-angle model recognizing method and system based on global and local Fusion Features |
| CN108986474A (en)* | 2018-08-01 | 2018-12-11 | 平安科技（深圳）有限公司 | Fix duty method, apparatus, computer equipment and the computer storage medium of traffic accident |
| CN109063768B (en)* | 2018-08-01 | 2021-10-01 | 北京旷视科技有限公司 | Vehicle weight identification method, device and system |
| CN109034086B (en)* | 2018-08-03 | 2021-03-23 | 北京旷视科技有限公司 | Vehicle weight identification method, device and system |
| CN109978132A (en)* | 2018-12-24 | 2019-07-05 | 中国科学院深圳先进技术研究院 | A kind of neural network method and system refining vehicle identification |
| CN110400464B (en)* | 2019-07-15 | 2021-06-01 | 杭州亿圣信息技术有限公司 | Method for monitoring illegal parking vehicles in community |
| CN110738181B (en)* | 2019-10-21 | 2022-08-05 | 东软睿驰汽车技术（沈阳）有限公司 | Method and device for determining vehicle orientation information |
| CN114241475B (en)* | 2021-11-22 | 2024-06-25 | 中冶赛迪信息技术(重庆)有限公司 | Self-adaptive automobile model recognition method and system based on three-dimensional laser scanning |
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP4703605B2 (en)* | 2007-05-31 | 2011-06-15 | アイシン・エィ・ダブリュ株式会社 | Feature extraction method, image recognition method and feature database creation method using the same |
| CN102810250B (en)* | 2012-07-31 | 2014-07-02 | 长安大学 | Video based multi-vehicle traffic information detection method |
| CN103593981B (en)* | 2013-01-18 | 2016-08-24 | 西安通瑞新材料开发有限公司 | A kind of model recognizing method based on video |
| CN103295017A (en)* | 2013-04-25 | 2013-09-11 | 哈尔滨工程大学 | Vehicle type identification method based on road videos |
| CN103246876B (en)* | 2013-05-10 | 2017-05-10 | 苏州祥益网络科技有限公司 | Image feature comparison based counterfeit vehicle registration plate identification method |
| Publication number | Publication date |
|---|---|
| CN104680795A (en) | 2015-06-03 |
| Publication | Publication Date | Title |
|---|---|---|
| CN104680795B (en) | A kind of model recognizing method and device based on local features | |
| CN111242015B (en) | A Method of Predicting Dangerous Driving Scenes Based on Motion Contour Semantic Map | |
| Kherraki et al. | Deep convolutional neural networks architecture for an efficient emergency vehicle classification in real-time traffic monitoring | |
| CN109800633B (en) | Non-motor vehicle traffic violation judgment method and device and electronic equipment | |
| CN109409337B (en) | Feature recognition method of muck truck based on convolutional neural network | |
| CN108171112A (en) | Vehicle identification and tracking based on convolutional neural networks | |
| CN109740463A (en) | A target detection method in vehicle environment | |
| CN108764169A (en) | A kind of driver's Emotion identification based on machine learning and display device and method | |
| CN110619277A (en) | Multi-community intelligent deployment and control method and system | |
| CN110895662A (en) | Vehicle overload alarm method and device, electronic equipment and storage medium | |
| CN106384100A (en) | Component-based fine vehicle model recognition method | |
| CN103903005A (en) | License plate image identification system and method | |
| CN106022285A (en) | Vehicle type identification method and vehicle type identification device based on convolutional neural network | |
| CN105335710A (en) | Fine vehicle model identification method based on multi-stage classifier | |
| CN106469309A (en) | The method and apparatus of vehicle monitoring, processor, image capture device | |
| CN106600977A (en) | Parking violation detection method and system based on multi-feature identification | |
| CN104778444A (en) | Method for analyzing apparent characteristic of vehicle image in road scene | |
| CN106570439B (en) | Vehicle detection method and device | |
| CN105160330A (en) | Vehicle logo recognition method and vehicle logo recognition system | |
| Kumtepe et al. | Driver aggressiveness detection via multisensory data fusion | |
| CN114550490B (en) | Parking space statistics method, system, computer equipment and storage medium of parking lot | |
| Awang et al. | Vehicle type classification using an enhanced sparse-filtered convolutional neural network with layer-skipping strategy | |
| JP2019106193A (en) | Information processing device, information processing program and information processing method | |
| JP5759124B2 (en) | Computerized method and system for analyzing objects in images obtained from a camera system | |
| CN104751197A (en) | Device and method for recognizing faces of drivers during vehicle running on basis of video analysis |
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | Effective date of registration:20181008 Address after:510663 the 3 floor of block A, No. 101 Ting Yue Road, Guangzhou hi tech Industrial Development Zone, Guangdong. Patentee after:GUANGZHOU FENGHUO ZHONGZHI DIGITAL TECHNOLOGY CO.,LTD. Address before:430074, No. 88, postal academy road, Hongshan District, Hubei, Wuhan Patentee before:WUHAN FIBERHOME DIGITAL TECHNOLOGY Co.,Ltd. | |
| TR01 | Transfer of patent right | ||
| CF01 | Termination of patent right due to non-payment of annual fee | Granted publication date:20180227 | |
| CF01 | Termination of patent right due to non-payment of annual fee |