WO2020134408A1 - Multi-path load-balanced asynchronous target detection method, storage medium, and processor - Google Patents
Multi-path load-balanced asynchronous target detection method, storage medium, and processor Download PDFInfo
- Publication number
- WO2020134408A1 WO2020134408A1 PCT/CN2019/112485 CN2019112485W WO2020134408A1 WO 2020134408 A1 WO2020134408 A1 WO 2020134408A1 CN 2019112485 W CN2019112485 W CN 2019112485W WO 2020134408 A1 WO2020134408 A1 WO 2020134408A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- yolo
- load balancing
- detection method
- target detection
- module
- Prior art date
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
- G06F9/505—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals considering the load
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/24—Aligning, centring, orientation detection or correction of the image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
Definitions
- the present invention relates to the field of target recognition technology, and more specifically, to a multi-path load balancing asynchronous target detection method, storage medium, and processor.
- Target detection can be used in many fields such as security, industry, and automobile assisted driving. For example, in the security field, the number of people in key areas can be counted to prevent crowded trampling incidents, and abnormal targets can be detected in sensitive areas to prevent regional intrusion. At the same time, target detection It is also the upstream input of visual technologies such as target recognition, instance segmentation, and morphological analysis. The quality of target detection directly determines the processing results of these more complex tasks.
- the target detection technology based on computer vision is to give an image and give an understanding of the foreground and background of the image. We need to separate the target of interest from the background and determine the classification and position of the target; therefore, the target detection output Is a list, and each data group element of the list gives a classification and position of the detection target; it is easy for humans to locate and classify the target from a given image, but for computers, the "person” is obtained from the multi-channel pixel matrix ", "car” and other abstract concepts of target objects and determine their location, coupled with multiple targets overlapping, covering and other situations, target detection is more difficult.
- the mainstream of target detection is based on deep learning, and a multi-process YOLO target detection scheme in PUSH/PULL mode that achieves a good balance between speed and accuracy.
- YOLO is the pioneering work of the end-to-end model. At speed, it is named after only one process to get the target position and classification. Compared with the two-stage method, the real-time speed is impressive.
- the training process of YOLO_V3 is as follows:
- Convolutional network use Darknet-53 to extract features, each grid in the three-scale feature map predicts a conditional probability value for each category, and generates B boxes on each grid, each box prediction [num_anchors*(5+num_classes+num_properti es)] regression values, which are the output of x, y, width, height, configure score, classes scores of bounding boxes under different anchors. During the test, the score is calculated as follows:
- the first term on the left side of the equation is predicted by the grid, and the last two terms are predicted by each box.
- the conditional probability is used to obtain the score of each box containing objects of different categories. Therefore, the number of prediction values output by the convolutional network is S ⁇ S ⁇ (B ⁇ 5+C), where S is the number of grids, B is the number of boxes generated for each grid, and C is the number of categories;
- NMS Non-Maximum Suppression, non-maximum suppression
- one server When using ZMQ's PUSH/PULL mode, one server is responsible for PUSH data, and multiple clients queue up for PULL data. A piece of data on the server PUSH will only be pulled by one of the clients, and either the server or the client will be disconnected. , Will not affect the other party;
- the video providing module serves as the server
- the YOLO detection module serves as the client.
- Multiple YOLO detection processes can be started at the same time, which can detect the target faster.
- the technical problem to be solved by the present invention is to provide a multi-channel load balancing asynchronous target detection method, storage medium and processor, which can start multi-channel YOLO processes, and can process multi-channel video inputs in real time through queue, dictionary and other shared process information It can make full use of hardware resources through load balancing, and can be widely used in target recognition such as YOLO monitoring system, facenet, tinyface and so on.
- an embodiment of the present invention provides a multi-path load balancing asynchronous target detection method, including:
- the dealer monitors the port occupied by the video sending module to send the image frame to obtain the input image
- the multi-process YOLO module processes the distributed image frames and detects the target attributes in the images
- the dealer monitors the port occupied by the video sending module to send the image frame, and obtaining the input image includes:
- the video sending module receives the video file from the camera, and processes the video file from the camera.
- the multi-channel balanced load and queue shared image frame using ZMQ includes:
- the input image is shared in the multi-path balanced load and queue of ZMQ, and the multi-path balanced load and queue of ZMQ is to be processed.
- the processing of the distributed image frames by the multi-process YOLO module includes: the multi-process YOLO module receives the image frames distributed by the multi-path balanced load of ZMQ.
- the target attributes in the image detected by the multi-process YOLO module include: facial attributes.
- the target attributes in the image detected by the multi-process YOLO module include: license plate attributes.
- the facial attributes include: gender attributes, ethnic attributes, age attributes, and facial decorations.
- the license plate attributes include: model, year, and body color.
- an embodiment of the present invention provides a storage medium, the storage medium includes a stored program, wherein, when the program runs, the above-described asynchronous target detection method for multiple load balancing is executed.
- an embodiment of the present invention provides a processor, which is used to run a program, wherein the above-mentioned multi-path load balancing asynchronous target detection method is executed when the program is run.
- the above technical solution has the following advantages: open multiple YOLO processes, share process information through queues, dictionaries, etc., can simultaneously process multiple video inputs in real time, and fully utilize hardware resources through load balancing, which is generally applicable In YOLO monitoring system, facenet, tinyface and other target recognition.
- FIG. 1 is a schematic diagram of a load target detection method in the prior art.
- FIG. 2 is a flowchart of the load balancing asynchronous target detection method of the present invention.
- FIG. 3 is an analysis diagram of multi-path load balancing through an intermediate agent in ZMQ in the load balancing asynchronous target detection method of the present invention.
- FIG. 4 is an embodiment of FIG. 3.
- Fig. 5 is another embodiment of Fig. 3.
- Target detection involves identifying targets first and then detecting them from many targets.
- Target recognition refers to the process of distinguishing a particular target (or one type of target) from other targets (or other types of targets). It includes both the recognition of two very similar targets and the recognition of one type of target and other types of targets.
- FIG. 1 is a schematic diagram of a multi-process target detection method in the prior art. The method shown in FIG. 1 is adopted in the background art.
- FIG. 2 is a flowchart of the load balancing asynchronous target detection method of the present invention.
- an asynchronous target detection method for multi-channel load balancing includes: S11, the dealer monitors the port occupied by the video sending module to send the image frame to obtain the input image; S12, the multi-channel balanced load and queue sharing using ZMQ Image frames, distribute the received images to the multi-process YOLO module that is started concurrently; S13, the multi-process YOLO module processes the distributed image frames and detects the target attributes in the image; S14, multi-channel balanced load through ZMQ, and The queue sharing detection result is returned to the downstream identification module.
- the dealer monitors the port occupied by the video sending module to send the image frame, and obtaining the input image includes: the video sending module receives the video file from the camera and processes the video file from the camera.
- ZMQ's multi-channel balanced load and queue-sharing image frames include: the input image is shared in ZMQ's multi-channel balanced load and queue, and ZMQ's multi-channel balanced load and queue are to be processed.
- the processing of the distributed image frames by the multi-process YOLO module includes: the multi-process YOLO module receives the image frames distributed by the multi-path balanced load of ZMQ.
- the multi-process YOLO module detects that the target attributes in the image include: facial attributes or license plate attributes.
- Facial attributes include but are not limited to: gender attributes, ethnic attributes, age attributes, facial decorations, etc.
- License plate attributes include but are not limited to: model, year, body color, etc. .
- the downstream facial recognition module performs feature extraction on the detected image, and then compares it with the face feature library to see how much the difference is. If the difference is less than a certain threshold, it is considered to be a person.
- the downstream license plate recognition module does OCR (Optical Character Recognition) recognition through deep learning, and then recognizes the license plate information.
- OCR Optical Character Recognition
- FIG. 3 is an analysis diagram of multi-path load balancing through an intermediate agent in ZMQ in the load balancing asynchronous target detection method of the present invention.
- the server and the client are not directly connected, but through ROUTER [router] and DEALER [dealer], all requests are queued fairly after arriving at the router, and then sent to the server by the dealer after load balancing, and the server answers the result The dealer and router then return to the client.
- FIG. 4 is an embodiment of FIG. 3.
- Fig. 5 is another embodiment of Fig. 3.
- receive the image frame information of the DEALER port and detect the faces, license plates and other objects in it receive the image frame information of the DEALER port and detect the faces, license plates and other objects in it;
- DEALER and ROUTER communication modules process the video transmission module, YOLO detection module and face recognition among other modules Asynchronous load balancing communication;
- send face information module extract the face information from the detection result of the YOLO detection module, encode it into a format suitable for network transmission, and send it to the face recognition module;
- send the license plate recognition module from the YOLO detection module In the detection result, the license plate information is extracted, encoded into a format suitable for network transmission, and sent to the license plate recognition module.
- the YOLO detection module, the send face information module, the DEALER and ROUTER communication modules, and the send vehicle information module interact with each other through queues and dictionaries.
- An embodiment of the present invention further provides a storage medium, the storage medium includes a stored program, wherein the above-mentioned multi-path load balancing asynchronous target detection method flow is executed when the above program runs.
- the above storage medium may be set to store program code for performing the following face attribute recognition method flow:
- the dealer monitors the port occupied by the video sending module to send the image frame to obtain the input image
- the multi-process YOLO module processes the distributed image frames and detects the target attributes in the images
- the above storage medium may include, but is not limited to: a U disk, a read-only memory (Read-Only Memory, referred to as ROM), random access memory (Random Access Memory (referred to as RAM), mobile hard disk, magnetic disk or optical disk and other media that can store program code.
- ROM read-only memory
- RAM random access memory
- mobile hard disk magnetic disk or optical disk and other media that can store program code.
- An embodiment of the present invention further provides a processor, which is used to run a program, where the program executes the steps in the above-mentioned multi-path load balancing asynchronous target detection method when the program is running.
- the above program is used to perform the following steps:
- the dealer monitors the port occupied by the video sending module to send the image frame to obtain the input image
- the multi-process YOLO module processes the distributed image frames and detects the target attributes in the images
- the multi-channel YOLO process is started, and the multi-channel video input can be simultaneously processed in real time through the shared process information such as queues and dictionaries.
- Load balancing can make full use of hardware resources, and can be universally applied to detection systems such as YOLO and facenet, and target recognition systems such as tinyface.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides a multi-path load-balanced asynchronous target detection method, a storage medium, and a processor. The method comprises: S11, a dealer monitors a port occupied by a video sending module sending an image frame, so as to obtain an input image; S12, share the image frame by using a multi-path balanced load of ZMQ and a queue, and distribute the received image to a multi-process YOLO module started concurrently; S13, each YOLO process processes the distributed image frame and detects a target attribute in the obtained image; and S14, share a detection result by means of the multi-path balanced load of ZMQ and the queue, and return same to a downstream identification module. The multiple YOLO processes are started, process information is shared by means of a queue, a dictionary, and the like, multiple video inputs can be simultaneously processed in real time, hardware resources can be fully utilized by means of load balancing, and the method can be widely suitable for target identification in a YOLO monitoring system, facenet, tinyface, and the like.
Description
本发明涉及目标识别技术领域,更为具体地说,涉及一种多路负载均衡异步目标检测方法、存储介质及处理器。The present invention relates to the field of target recognition technology, and more specifically, to a multi-path load balancing asynchronous target detection method, storage medium, and processor.
目标检测可运用于安防、工业、汽车辅助驾驶等众多领域,比如安防领域中,可以对重点区域进行人数统计以防止拥挤***件、对敏感区域做异常目标检测以防止区域入侵等;同时目标检测也是目标识别、实例分割、形态分析等视觉技术的上游输入,目标检测效果的好坏直接决定了这些更复杂任务处理结果。Target detection can be used in many fields such as security, industry, and automobile assisted driving. For example, in the security field, the number of people in key areas can be counted to prevent crowded trampling incidents, and abnormal targets can be detected in sensitive areas to prevent regional intrusion. At the same time, target detection It is also the upstream input of visual technologies such as target recognition, instance segmentation, and morphological analysis. The quality of target detection directly determines the processing results of these more complex tasks.
基于计算机视觉的目标检测技术,是给定一张图像,给出对图像前景和背景的理解,我们需要从背景中分离出感兴趣的目标,并且要确定目标的分类和位置;因而目标检测输出的是一个列表,列表的每一项数据组元素给出一个检测目标的分类和位置;对于人类从给定图像中定位、分类目标很容易,但是对于计算机,从多通道像素矩阵中得到“人”、“车”等目标物体的抽象概念并确定其位置,再加上多目标重叠、遮盖等情况,目标检测就更加困难了。The target detection technology based on computer vision is to give an image and give an understanding of the foreground and background of the image. We need to separate the target of interest from the background and determine the classification and position of the target; therefore, the target detection output Is a list, and each data group element of the list gives a classification and position of the detection target; it is easy for humans to locate and classify the target from a given image, but for computers, the "person" is obtained from the multi-channel pixel matrix ", "car" and other abstract concepts of target objects and determine their location, coupled with multiple targets overlapping, covering and other situations, target detection is more difficult.
目前目标检测主流是基于深度学***衡的PUSH/PULL模式的多进程YOLO目标检测方案。At present, the mainstream of target detection is based on deep learning, and a multi-process YOLO target detection scheme in PUSH/PULL mode that achieves a good balance between speed and accuracy.
YOLO是端到端模型的开山之作,在速度它以得到目标位置和分类只需要一次处理而得名,相比两阶段方法,实时速度令人映像深刻;YOLO_V3的训练过程如下:YOLO is the pioneering work of the end-to-end model. At speed, it is named after only one process to get the target position and classification. Compared with the two-stage method, the real-time speed is impressive. The training process of YOLO_V3 is as follows:
1、准备数据:将图片缩放到规定尺寸,输入到网络;提取特征的网络将会输出3个不同尺度【分别是13*13、26*26、52*52】的特征图,将样本按照IOU【只考虑面积,不考虑位置】匹配到不同的anchor【yolo_v3为每个特征图设定3个anchor,因此总共有9个anchor】;1. Prepare the data: scale the picture to the specified size and input it to the network; the network that extracts the features will output 3 different scales [13*13, 26*26, 52*52] feature maps respectively [Only considering the area, not considering the location] Match to different anchors [yolo_v3 sets 3 anchors for each feature map, so there are 9 anchors in total];
2、卷积网络:使用Darknet-53来实现提取特征,三个尺度的特征图中每个网格对每个类别预测一个条件概率值,并在每个网格上生成B个box,每个box预测[num_anchors*(5+num_classes+num_properti
es)]个回归值,既是输出不同anchor下的bounding box的x,y,width,height,configure score,classes scores。测试时,分数如下计算:2. Convolutional network: use Darknet-53 to extract features, each grid in the three-scale feature map predicts a conditional probability value for each category, and generates B boxes on each grid, each box prediction [num_anchors*(5+num_classes+num_properti
es)] regression values, which are the output of x, y, width, height, configure score, classes scores of bounding boxes under different anchors. During the test, the score is calculated as follows:
等式左边第一项由网格预测,后两项由每个box预测,以条件概率的方式得到每个box含有不同类别物体的分数。因而,卷积网络共输出的预测值个数为S×S×(B×5+C),其中S为网格数,B为每个网格生成box个数,C为类别数;The first term on the left side of the equation is predicted by the grid, and the last two terms are predicted by each box. The conditional probability is used to obtain the score of each box containing objects of different categories. Therefore, the number of prediction values output by the convolutional network is S×S×(B×5+C), where S is the number of grids, B is the number of boxes generated for each grid, and C is the number of categories;
YOLO_V3在做前向预测时,输入为任意尺寸的图像,在最终输出detection时,需要使用NMS(Non-Maximum Suppression,非极大抑制)过滤得到最后的预测框。When YOLO_V3 is doing forward prediction, the input is an image of any size. When the detection is finally output, NMS (Non-Maximum Suppression, non-maximum suppression) filtering is required to obtain the final prediction frame.
使用ZMQ的PUSH/PULL模式时,一个服务端负责PUSH数据,多个客户端排队PULL数据,服务端PUSH的一份数据只会被其中一个客户端拉取,服务端和客户端任一方断掉,都不会影响另一方;When using ZMQ's PUSH/PULL mode, one server is responsible for PUSH data, and multiple clients queue up for PULL data. A piece of data on the server PUSH will only be pulled by one of the clients, and either the server or the client will be disconnected. , Will not affect the other party;
应用到YOLO目标检测***时,为提高检测的实时性,视频提供模块做服务端,YOLO检测模块做客户端,可以同时开启多个YOLO检测进程,能较快的检测目标。When applied to the YOLO target detection system, in order to improve the real-time detection, the video providing module serves as the server, and the YOLO detection module serves as the client. Multiple YOLO detection processes can be started at the same time, which can detect the target faster.
由此可见,其不足之处有:This shows that its shortcomings are:
(1)YOLO模块工作时,只是较机械的排队等待,并没有做负载均衡;(1) When the YOLO module is working, it is only a more mechanical queue waiting, and there is no load balancing;
(2)开启多路视频检测时,实现较麻烦;(2) When enabling multi-channel video detection, it is more troublesome to implement;
服务端PUSH消息时,容易堆积,很可能会造成数据丢失,这是决不能允许的。When PUSH messages on the server side are easy to accumulate, it is likely to cause data loss, which can never be allowed.
本发明所要解决的技术问题是提供一种多路负载均衡异步目标检测方法、存储介质及处理器,能够开启多路YOLO进程,通过队列、字典等共享进程信息,可以同时实时处理多路视频输入,通过负载均衡可以充分利用硬件资源,可普遍适用于YOLO监测***、facenet、tinyface等目标识别中。The technical problem to be solved by the present invention is to provide a multi-channel load balancing asynchronous target detection method, storage medium and processor, which can start multi-channel YOLO processes, and can process multi-channel video inputs in real time through queue, dictionary and other shared process information It can make full use of hardware resources through load balancing, and can be widely used in target recognition such as YOLO monitoring system, facenet, tinyface and so on.
为解决上述技术问题,一方面,本发明一实施例提供了一种多路负载均衡异步目标检测方法,包括:In order to solve the above technical problems, on the one hand, an embodiment of the present invention provides a multi-path load balancing asynchronous target detection method, including:
S11、dealer监听视频发送模块发送图像帧所占用的端口,得到输入图像;S11. The dealer monitors the port occupied by the video sending module to send the image frame to obtain the input image;
S12、用ZMQ的多路均衡负载和队列共享图像帧,将接收到的图像分发到并发开启的多进程YOLO模块;S12. Use ZMQ's multi-channel balanced load and queue to share image frames, and distribute the received images to the multi-process YOLO module started concurrently;
S13、多进程YOLO模块处理分发得到的图像帧,检测得到图像中的目标属性;S13. The multi-process YOLO module processes the distributed image frames and detects the target attributes in the images;
S14、通过ZMQ的多路均衡负载,以及队列共享检测结果,返回给下游的识别模块。S14. The multi-channel balanced load through ZMQ and the result of queue sharing detection are returned to the downstream identification module.
优选地,所述dealer监听视频发送模块发送图像帧所占用的端口,得到输入图像包括:Preferably, the dealer monitors the port occupied by the video sending module to send the image frame, and obtaining the input image includes:
视频发送模块接收来自摄像头的视频文件,且对来自摄像头的视频文件进行处理。The video sending module receives the video file from the camera, and processes the video file from the camera.
优选地,所述用ZMQ的多路均衡负载和队列共享图像帧包括:Preferably, the multi-channel balanced load and queue shared image frame using ZMQ includes:
所述输入图像共享在ZMQ的多路均衡负载和队列中,由ZMQ的多路均衡负载和队列待处理。The input image is shared in the multi-path balanced load and queue of ZMQ, and the multi-path balanced load and queue of ZMQ is to be processed.
优选地,所述多进程YOLO模块处理分发得到的图像帧包括:多进程YOLO模块接收由ZMQ的多路均衡负载分发的图像帧。Preferably, the processing of the distributed image frames by the multi-process YOLO module includes: the multi-process YOLO module receives the image frames distributed by the multi-path balanced load of ZMQ.
优选地,所述多进程YOLO模块检测得到图像中的目标属性包括:面部属性。Preferably, the target attributes in the image detected by the multi-process YOLO module include: facial attributes.
优选地,所述多进程YOLO模块检测得到图像中的目标属性包括:车牌属性。Preferably, the target attributes in the image detected by the multi-process YOLO module include: license plate attributes.
优选地,所述面部属性包括:性别属性、人种属性、年龄属性、面部装饰。Preferably, the facial attributes include: gender attributes, ethnic attributes, age attributes, and facial decorations.
优选地,所述车牌属性包括:车型、年份、车身颜色。Preferably, the license plate attributes include: model, year, and body color.
另一方面,本发明一实施例提供了一种存储介质,所述存储介质包括存储的程序,其中,所述程序运行时执行上述的多路负载均衡异步目标检测方法。On the other hand, an embodiment of the present invention provides a storage medium, the storage medium includes a stored program, wherein, when the program runs, the above-described asynchronous target detection method for multiple load balancing is executed.
另一方面,本发明一实施例提供了一种处理器,所述处理器用于运行程序,其中,所述程序运行时执行上述的多路负载均衡异步目标检测方法。On the other hand, an embodiment of the present invention provides a processor, which is used to run a program, wherein the above-mentioned multi-path load balancing asynchronous target detection method is executed when the program is run.
与现有技术相比,上述技术方案具有以下优点:开启多路YOLO进程,通过队列、字典等共享进程信息,可以同时实时处理多路视频输入,通过负载均衡可以充分利用硬件资源,可普遍适用于YOLO监测***、facenet、tinyface等目标识别中。Compared with the prior art, the above technical solution has the following advantages: open multiple YOLO processes, share process information through queues, dictionaries, etc., can simultaneously process multiple video inputs in real time, and fully utilize hardware resources through load balancing, which is generally applicable In YOLO monitoring system, facenet, tinyface and other target recognition.
为了更清楚地说明本发明实施例中的技术方案,下面将对实施例描述中所需要使用的附图作简单地介绍,显而易见地,下面描述中的附图仅仅是本发明的一些实施例,对于本领域普通技术人员来讲,在不付出创造性劳动性的前提下,还可以根据这些附图获得其它的附图。In order to more clearly explain the technical solutions in the embodiments of the present invention, the drawings required in the description of the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without paying any creative labor, other drawings can also be obtained based on these drawings.
图1是现有技术中负载目标检测方法原理图。FIG. 1 is a schematic diagram of a load target detection method in the prior art.
图2是本发明负载均衡异步目标检测方法流程图。FIG. 2 is a flowchart of the load balancing asynchronous target detection method of the present invention.
图3是本发明负载均衡异步目标检测方法中ZMQ中通过中间代理实现多路负载均衡的解析图。FIG. 3 is an analysis diagram of multi-path load balancing through an intermediate agent in ZMQ in the load balancing asynchronous target detection method of the present invention.
图4是图3的一实施例。FIG. 4 is an embodiment of FIG. 3.
图5是图3的另一实施例。Fig. 5 is another embodiment of Fig. 3.
下面将结合本发明实施例中的附图,对本发明实施例中的技术方案进行清楚、完整地描述,显然,所描述的实施例仅仅是本发明一部分实施例,而不是全部的实施例。基于本发明中的实施例,本领域普通技术人员在没有作出创造性劳动前提下所获得的所有其它实施例,都属于本发明保护的范围。The technical solutions in the embodiments of the present invention will be described clearly and completely in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present invention.
A
实施例一、Example one
目标检测通过先对目标进行识别然后再从众多目标中检测出来。目标识别是指一个特殊目标(或一种类型的目标)从其它目标(或其它类型的目标)中被区分出来的过程。它既包括两个非常相似目标的识别,也包括一种类型的目标同其他类型目标的识别。图1是现有技术中多进程目标检测方法原理图。背景技术中采用的如图1的方式。Target detection involves identifying targets first and then detecting them from many targets. Target recognition refers to the process of distinguishing a particular target (or one type of target) from other targets (or other types of targets). It includes both the recognition of two very similar targets and the recognition of one type of target and other types of targets. FIG. 1 is a schematic diagram of a multi-process target detection method in the prior art. The method shown in FIG. 1 is adopted in the background art.
图2是本发明负载均衡异步目标检测方法流程图。如图2所示,一种多路负载均衡异步目标检测方法,包括:S11、dealer监听视频发送模块发送图像帧所占用的端口,得到输入图像;S12、用ZMQ的多路均衡负载和队列共享图像帧,将接收到的图像分发到并发开启的多进程YOLO模块;S13、多进程YOLO模块处理分发得到的图像帧,检测得到图像中的目标属性;S14、通过ZMQ的多路均衡负载,以及队列共享检测结果,返回给下游的识别模块。FIG. 2 is a flowchart of the load balancing asynchronous target detection method of the present invention. As shown in Figure 2, an asynchronous target detection method for multi-channel load balancing includes: S11, the dealer monitors the port occupied by the video sending module to send the image frame to obtain the input image; S12, the multi-channel balanced load and queue sharing using ZMQ Image frames, distribute the received images to the multi-process YOLO module that is started concurrently; S13, the multi-process YOLO module processes the distributed image frames and detects the target attributes in the image; S14, multi-channel balanced load through ZMQ, and The queue sharing detection result is returned to the downstream identification module.
dealer监听视频发送模块发送图像帧所占用的端口,得到输入图像包括:视频发送模块接收来自摄像头的视频文件,且对来自摄像头的视频文件进行处理。ZMQ的多路均衡负载和队列共享图像帧包括:输入图像共享在ZMQ的多路均衡负载和队列中,由ZMQ的多路均衡负载和队列待处理。多进程YOLO模块处理分发得到的图像帧包括:多进程YOLO模块接收由ZMQ的多路均衡负载分发的图像帧。所述多进程YOLO模块检测得到图像中的目标属性包括:面部属性或车牌属性。面部属性包括但不限于:性别属性、人种属性、年龄属性、面部装饰等。车牌属性包括但不限于:车型、年份、车身颜色等。。下游面部识别模块对检测出来的图像,做特征提取,然后和人脸的特征库比对,看他们的差异多少,如果差异少于一定阈值,就认为是某个人。下游车牌识别模块通过深度学习的方法,做OCR(光学字符识别)识别,进而识别出车牌信息。The dealer monitors the port occupied by the video sending module to send the image frame, and obtaining the input image includes: the video sending module receives the video file from the camera and processes the video file from the camera. ZMQ's multi-channel balanced load and queue-sharing image frames include: the input image is shared in ZMQ's multi-channel balanced load and queue, and ZMQ's multi-channel balanced load and queue are to be processed. The processing of the distributed image frames by the multi-process YOLO module includes: the multi-process YOLO module receives the image frames distributed by the multi-path balanced load of ZMQ. The multi-process YOLO module detects that the target attributes in the image include: facial attributes or license plate attributes. Facial attributes include but are not limited to: gender attributes, ethnic attributes, age attributes, facial decorations, etc. License plate attributes include but are not limited to: model, year, body color, etc. . The downstream facial recognition module performs feature extraction on the detected image, and then compares it with the face feature library to see how much the difference is. If the difference is less than a certain threshold, it is considered to be a person. The downstream license plate recognition module does OCR (Optical Character Recognition) recognition through deep learning, and then recognizes the license plate information.
图3是本发明负载均衡异步目标检测方法中ZMQ中通过中间代理实现多路负载均衡的解析图。有多路视频输入,同时也打开了多个YOLO检测进程;视频输入作为客户端,YOLO检测进程作为服务端;通过ZMQ的多路负载均衡,实现合理、充分利用硬件资源的多进程异步通信;服务端和客户端并不是直接连接,而是通过ROUTER【路由器】和DEALER【经销商】,所有的请求到达路由器以后公平的排队,然后由经销商负载均衡后发送给服务端,服务器应答的结果再由经销商和路由器返回给客户端。FIG. 3 is an analysis diagram of multi-path load balancing through an intermediate agent in ZMQ in the load balancing asynchronous target detection method of the present invention. There are multiple video inputs, and multiple YOLO detection processes are also opened; the video input is the client and the YOLO detection process is the server; through ZMQ's multi-channel load balancing, reasonable and full use of hardware resources is achieved for asynchronous multi-process communication; The server and the client are not directly connected, but through ROUTER [router] and DEALER [dealer], all requests are queued fairly after arriving at the router, and then sent to the server by the dealer after load balancing, and the server answers the result The dealer and router then return to the client.
图4是图3的一实施例。图5是图3的另一实施例。如图4、图5所示,接收DEALER端口的图像帧信息,检测其中的人脸、车牌等目标;DEALER和ROUTER通信模块:处理视频发送模块、YOLO检测模块以及人脸识别等模块之间的异步负载均衡通信;发送人脸信息模块:从YOLO检测模块的检测结果中,提取人脸信息,编码成适合网络传输的格式,发送到人脸识别模块;发送车牌识别模块:从YOLO检测模块的检测结果中,提取车牌信息,编码成适合网络传输的格式,发送到车牌识别模块。YOLO检测模块、发送人脸信息模块、DEALER和ROUTER通信模块、发送车辆信息模块两两之间均通过队列、字典等通信方式进行交互。FIG. 4 is an embodiment of FIG. 3. Fig. 5 is another embodiment of Fig. 3. As shown in Figures 4 and 5, receive the image frame information of the DEALER port and detect the faces, license plates and other objects in it; DEALER and ROUTER communication modules: process the video transmission module, YOLO detection module and face recognition among other modules Asynchronous load balancing communication; send face information module: extract the face information from the detection result of the YOLO detection module, encode it into a format suitable for network transmission, and send it to the face recognition module; send the license plate recognition module: from the YOLO detection module In the detection result, the license plate information is extracted, encoded into a format suitable for network transmission, and sent to the license plate recognition module. The YOLO detection module, the send face information module, the DEALER and ROUTER communication modules, and the send vehicle information module interact with each other through queues and dictionaries.
A
实施例二Example 2
本发明的实施例还提供了一种存储介质,该存储介质包括存储的程序,其中,上述程序运行时执行上述的多路负载均衡异步目标检测方法流程。An embodiment of the present invention further provides a storage medium, the storage medium includes a stored program, wherein the above-mentioned multi-path load balancing asynchronous target detection method flow is executed when the above program runs.
可选地,在本实施例中,上述存储介质可以被设置为存储用于执行以下人脸属性识别方法流程的程序代码:Optionally, in this embodiment, the above storage medium may be set to store program code for performing the following face attribute recognition method flow:
S11、dealer监听视频发送模块发送图像帧所占用的端口,得到输入图像;S11. The dealer monitors the port occupied by the video sending module to send the image frame to obtain the input image;
S12、用ZMQ的多路均衡负载和队列共享图像帧,将接收到的图像分发到并发开启的多进程YOLO模块;S12. Use ZMQ's multi-channel balanced load and queue to share image frames, and distribute the received images to the multi-process YOLO module started concurrently;
S13、多进程YOLO模块处理分发得到的图像帧,检测得到图像中的目标属性;S13. The multi-process YOLO module processes the distributed image frames and detects the target attributes in the images;
S14、通过ZMQ的多路均衡负载,以及队列共享检测结果,返回给下游的识别模块。S14. The multi-channel balanced load through ZMQ and the result of queue sharing detection are returned to the downstream identification module.
可选地,在本实施例中,上述存储介质可以包括但不限于:U盘、只读存储器(Read-Only
Memory,简称为ROM)、随机存取存储器(Random
Access Memory,简称为RAM)、移动硬盘、磁碟或者光盘等各种可以存储程序代码的介质。Optionally, in this embodiment, the above storage medium may include, but is not limited to: a U disk, a read-only memory (Read-Only
Memory, referred to as ROM), random access memory (Random
Access Memory (referred to as RAM), mobile hard disk, magnetic disk or optical disk and other media that can store program code.
由此可见,通过采用本发明存储介质,开启多路YOLO进程,通过队列、字典等共享进程信息,可以同时实时处理多路视频输入,通过负载均衡可以充分利用硬件资源,可普遍适用于YOLO、tinyface等检测***tinyface等目标识别***中。It can be seen that by using the storage medium of the present invention, multiple YOLO processes are started, multiple process video inputs can be processed in real time through queues, dictionaries and other shared process information, and hardware resources can be fully utilized through load balancing, which can be generally applied to YOLO, Tinyface and other detection systems such as tinyface and other target recognition systems.
A
实施例三Example Three
本发明的实施例还提供了一种处理器,该处理器用于运行程序,其中,该程序运行时执行上述的多路负载均衡异步目标检测方法中的步骤。An embodiment of the present invention further provides a processor, which is used to run a program, where the program executes the steps in the above-mentioned multi-path load balancing asynchronous target detection method when the program is running.
可选地,在本实施例中,上述程序用于执行以下步骤:Optionally, in this embodiment, the above program is used to perform the following steps:
S11、dealer监听视频发送模块发送图像帧所占用的端口,得到输入图像;S11. The dealer monitors the port occupied by the video sending module to send the image frame to obtain the input image;
S12、用ZMQ的多路均衡负载和队列共享图像帧,将接收到的图像分发到并发开启的多进程YOLO模块;S12. Use ZMQ's multi-channel balanced load and queue to share image frames, and distribute the received images to the multi-process YOLO module started concurrently;
S13、多进程YOLO模块处理分发得到的图像帧,检测得到图像中的目标属性;S13. The multi-process YOLO module processes the distributed image frames and detects the target attributes in the images;
S14、通过ZMQ的多路均衡负载,以及队列共享检测结果,返回给下游的识别模块。S14. The multi-channel balanced load through ZMQ and the result of queue sharing detection are returned to the downstream identification module.
可选地,本实施例中的具体示例可以参考上述实施例及具体实施时所描述的示例,本实施例在此不再赘述。Optionally, for specific examples in this embodiment, reference may be made to the foregoing embodiments and the examples described in the specific implementation, and this embodiment will not be repeated here.
由此可见,通过采用本发明处理器,开启多路YOLO进程,通过队列、字典等共享进程信息,可以同时实时处理多路视频输入,通过负载均衡可以充分利用硬件资源,可普遍适用于YOLO、tinyface等检测***、facenet等目标识别***中。It can be seen that by using the processor of the present invention to start multiple YOLO processes, through the sharing of process information such as queues and dictionaries, multiple video inputs can be processed in real time, and the hardware resources can be fully utilized through load balancing. It can be generally applied to YOLO, Detection systems such as tinyface, and target recognition systems such as facenet.
由上述说明可知,使用根据本发明的多路负载均衡异步目标检测方法、存储介质及处理器,开启多路YOLO进程,通过队列、字典等共享进程信息,可以同时实时处理多路视频输入,通过负载均衡可以充分利用硬件资源,可普遍适用于YOLO、facenet等检测***、tinyface等目标识别***中。As can be seen from the above description, using the multi-channel load balancing asynchronous target detection method, storage medium and processor according to the present invention, the multi-channel YOLO process is started, and the multi-channel video input can be simultaneously processed in real time through the shared process information such as queues and dictionaries. Load balancing can make full use of hardware resources, and can be universally applied to detection systems such as YOLO and facenet, and target recognition systems such as tinyface.
以上对本发明实施例进行了详细介绍,本文中应用了具体个例对本发明的原理及实施方式进行了阐述,以上实施例的说明只是用于帮助理解本发明的方法及其核心思想;同时,对于本领域的一般技术人员,依据本发明的思想,在具体实施方式及应用范围上均会有改变之处,综上所述,本说明书内容不应理解为对本发明的限制。The embodiments of the present invention have been described in detail above, and specific examples have been used in this article to explain the principles and implementations of the present invention. The descriptions of the above embodiments are only used to help understand the method and core idea of the present invention; Those of ordinary skill in the art, according to the ideas of the present invention, will have changes in specific implementations and application scopes. In summary, the content of this specification should not be construed as limiting the present invention.
Claims (10)
- 一种多路负载均衡异步目标检测方法,其特征在于,包括:A multi-channel load balancing asynchronous target detection method, characterized in that it includes:S11、dealer监听视频发送模块发送图像帧所占用的端口,得到输入图像;S11. The dealer monitors the port occupied by the video sending module to send the image frame to obtain the input image;S12、用ZMQ的多路均衡负载和队列共享图像帧,将接收到的图像分发到并发开启的多进程YOLO模块;S12. Use ZMQ's multi-channel balanced load and queue to share image frames, and distribute the received images to the multi-process YOLO module started concurrently;S13、多进程YOLO模块处理分发得到的图像帧,检测得到图像中的目标属性;S13. The multi-process YOLO module processes the distributed image frames and detects the target attributes in the images;S14、通过ZMQ的多路均衡负载,以及队列共享检测结果,返回给下游的识别模块。S14. The multi-channel balanced load through ZMQ and the result of queue sharing detection are returned to the downstream identification module.
- 根据权利要求1所述的多路负载均衡异步目标检测方法,其特征在于,所述dealer监听视频发送模块发送图像帧所占用的端口,得到输入图像包括:The multi-channel load balancing asynchronous target detection method according to claim 1, wherein the dealer monitors the port occupied by the video sending module to send the image frame, and obtaining the input image includes:视频发送模块接收来自摄像头的视频文件,且对来自摄像头的视频文件进行处理。The video sending module receives the video file from the camera, and processes the video file from the camera.
- 根据权利要求1所述的多路负载均衡异步目标检测方法,其特征在于,所述用ZMQ的多路均衡负载和队列共享图像帧包括:The asynchronous target detection method of multi-path load balancing according to claim 1, wherein the multi-path load balancing and queue shared image frame using ZMQ comprises:所述输入图像共享在ZMQ的多路均衡负载和队列中,由ZMQ的多路均衡负载和队列待处理。The input image is shared in the multi-path balanced load and queue of ZMQ, and the multi-path balanced load and queue of ZMQ is to be processed.
- 根据权利要求1所述的多路负载均衡异步目标检测方法,其特征在于,所述多进程YOLO模块处理分发得到的图像帧包括:多进程YOLO模块接收由ZMQ的多路均衡负载分发的图像帧。The asynchronous target detection method for multi-path load balancing according to claim 1, wherein the processing of the distributed image frames by the multi-process YOLO module comprises: the multi-process YOLO module receiving the image frames distributed by the multi-path load balancing of ZMQ .
- 根据权利要求1所述的多路负载均衡异步目标检测方法,其特征在于,所述多进程YOLO模块检测得到图像中的目标属性包括:面部属性。The asynchronous target detection method of multi-channel load balancing according to claim 1, wherein the target attributes in the image detected by the multi-process YOLO module include: facial attributes.
- 根据权利要求1所述的多路负载均衡异步目标检测方法,其特征在于,所述多进程YOLO模块检测得到图像中的目标属性包括:车牌属性。The multi-path load balancing asynchronous target detection method according to claim 1, wherein the target attributes in the image detected by the multi-process YOLO module include: license plate attributes.
- 根据权利要求5所述的多路负载均衡异步目标检测方法,其特征在于,所述面部属性包括:性别属性、人种属性、年龄属性、面部装饰。The asynchronous target detection method of multi-channel load balancing according to claim 5, wherein the facial attributes include: gender attributes, ethnic attributes, age attributes, and facial decorations.
- 根据权利要求6所述的多路负载均衡异步目标检测方法,其特征在于,所述车牌属性包括:车型、年份、车身颜色。The multi-channel load balancing asynchronous target detection method according to claim 6, wherein the license plate attributes include: vehicle model, year, and body color.
- 一种存储介质,其特征在于,所述存储介质包括存储的程序,其中,所述程序运行时执行权利要求1至8中任一项所述的多路负载均衡异步目标检测方法。A storage medium, characterized in that the storage medium includes a stored program, wherein, when the program runs, the asynchronous target detection method for multi-channel load balancing according to any one of claims 1 to 8 is executed.
- 一种处理器,其特征在于,所述处理器用于运行程序,其中,所述程序运行时执行权利要求1至8中任一项所述的多路负载均衡异步目标检测方法。A processor, characterized in that the processor is used to run a program, wherein, when the program runs, the asynchronous target detection method for multi-channel load balancing according to any one of claims 1 to 8 is executed.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811655208.1A CN111382737A (en) | 2018-12-29 | 2018-12-29 | Multi-path load balancing asynchronous target detection method, storage medium and processor |
CN201811655208.1 | 2018-12-29 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2020134408A1 true WO2020134408A1 (en) | 2020-07-02 |
Family
ID=71126881
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2019/112485 WO2020134408A1 (en) | 2018-12-29 | 2019-10-22 | Multi-path load-balanced asynchronous target detection method, storage medium, and processor |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN111382737A (en) |
WO (1) | WO2020134408A1 (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113807235A (en) * | 2021-09-14 | 2021-12-17 | 温州大学大数据与信息技术研究院 | Target detector and target detection method |
CN114916336A (en) * | 2022-05-06 | 2022-08-19 | 山东理工大学 | Chemical topping method based on classification and identification of maturity stages of cotton top leaves |
CN115174941A (en) * | 2022-07-06 | 2022-10-11 | 灵羲科技(北京)有限公司 | Real-time motion performance analysis and real-time data sharing method based on multi-channel video streams |
CN117347888A (en) * | 2023-12-05 | 2024-01-05 | 深圳市易检车服科技有限公司 | Battery equalizer load measuring method and device, computer equipment and storage medium |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112363847B (en) * | 2020-10-23 | 2023-04-11 | 苏宁金融科技(南京)有限公司 | Automatic identification method and system for license document |
CN114399773B (en) * | 2022-01-18 | 2024-06-28 | 平安科技(深圳)有限公司 | OCR (optical character recognition) system construction method and device, OCR method and device and medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130243329A1 (en) * | 2012-03-15 | 2013-09-19 | Herta Security, S.L. | Parallel object detection method for heterogeneous multithreaded microarchitectures |
CN105701446A (en) * | 2014-12-11 | 2016-06-22 | 想象技术有限公司 | Preforming object detection |
CN106358003A (en) * | 2016-08-31 | 2017-01-25 | 华中科技大学 | Video analysis and accelerating method based on thread level flow line |
CN106504242A (en) * | 2016-10-25 | 2017-03-15 | Tcl集团股份有限公司 | Object detection method and system |
Family Cites Families (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2013165048A1 (en) * | 2012-04-30 | 2013-11-07 | 전자부품연구원 | Image search system and image analysis server |
CN107018036A (en) * | 2016-01-28 | 2017-08-04 | 上海大唐移动通信设备有限公司 | A kind of online MOS method of testings, apparatus and system |
CN106210121A (en) * | 2016-07-29 | 2016-12-07 | 浪潮(北京)电子信息产业有限公司 | A kind of method and device realizing storing load balance |
CN106488197A (en) * | 2016-12-26 | 2017-03-08 | 旗瀚科技有限公司 | A kind of intelligent person recognition robot |
CN106789446B (en) * | 2017-02-17 | 2020-06-02 | 北京同有飞骥科技股份有限公司 | Node peer-to-peer cluster distributed test system and method |
CN108509912B (en) * | 2018-04-03 | 2021-09-28 | 深圳市智绘科技有限公司 | License plate recognition method and system for multi-channel network video stream |
CN108696578A (en) * | 2018-04-26 | 2018-10-23 | 昆明理工大学 | The communications framework design method that multiple machine distributing based on ZeroMQ calculates |
-
2018
- 2018-12-29 CN CN201811655208.1A patent/CN111382737A/en active Pending
-
2019
- 2019-10-22 WO PCT/CN2019/112485 patent/WO2020134408A1/en active Application Filing
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20130243329A1 (en) * | 2012-03-15 | 2013-09-19 | Herta Security, S.L. | Parallel object detection method for heterogeneous multithreaded microarchitectures |
CN105701446A (en) * | 2014-12-11 | 2016-06-22 | 想象技术有限公司 | Preforming object detection |
CN106358003A (en) * | 2016-08-31 | 2017-01-25 | 华中科技大学 | Video analysis and accelerating method based on thread level flow line |
CN106504242A (en) * | 2016-10-25 | 2017-03-15 | Tcl集团股份有限公司 | Object detection method and system |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113807235A (en) * | 2021-09-14 | 2021-12-17 | 温州大学大数据与信息技术研究院 | Target detector and target detection method |
CN113807235B (en) * | 2021-09-14 | 2024-03-15 | 温州大学大数据与信息技术研究院 | Target detector and target detection method |
CN114916336A (en) * | 2022-05-06 | 2022-08-19 | 山东理工大学 | Chemical topping method based on classification and identification of maturity stages of cotton top leaves |
CN114916336B (en) * | 2022-05-06 | 2024-03-15 | 山东理工大学 | Chemical topping method based on cotton top leaf maturity stage classification and identification |
CN115174941A (en) * | 2022-07-06 | 2022-10-11 | 灵羲科技(北京)有限公司 | Real-time motion performance analysis and real-time data sharing method based on multi-channel video streams |
CN117347888A (en) * | 2023-12-05 | 2024-01-05 | 深圳市易检车服科技有限公司 | Battery equalizer load measuring method and device, computer equipment and storage medium |
CN117347888B (en) * | 2023-12-05 | 2024-02-13 | 深圳市易检车服科技有限公司 | Battery equalizer load measuring method and device, computer equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN111382737A (en) | 2020-07-07 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2020134408A1 (en) | Multi-path load-balanced asynchronous target detection method, storage medium, and processor | |
US11403879B2 (en) | Method and apparatus for child state analysis, vehicle, electronic device, and storage medium | |
US20200026936A1 (en) | Vehicle lamp detection methods and apparatuses, methods and apparatuses for implementing intelligent driving, media and devices | |
EP1460851A2 (en) | A system and method for real-time whiteboard streaming | |
CN111325051B (en) | Face recognition method and device based on face image ROI selection | |
WO2019114145A1 (en) | Head count detection method and device in surveillance video | |
CN112364803B (en) | Training method, terminal, equipment and storage medium for living body identification auxiliary network | |
US11164004B2 (en) | Keyframe scheduling method and apparatus, electronic device, program and medium | |
WO2022082999A1 (en) | Object recognition method and apparatus, and terminal device and storage medium | |
WO2023040146A1 (en) | Behavior recognition method and apparatus based on image fusion, and electronic device and medium | |
CN111353338B (en) | Energy efficiency improvement method based on business hall video monitoring | |
CN110232340A (en) | Establish the method, apparatus of video classification model and visual classification | |
JP7270808B2 (en) | Vehicle parking violation identification method, device, electronic device, storage medium and computer program | |
US20210201501A1 (en) | Motion-based object detection method, object detection apparatus and electronic device | |
JP2021152966A (en) | Seat belt wearing state recognition method, recognition apparatus, electronic device, and recording medium | |
WO2023273344A1 (en) | Vehicle line crossing recognition method and apparatus, electronic device, and storage medium | |
CN111488805A (en) | Video behavior identification method based on saliency feature extraction | |
CN112614102A (en) | Vehicle detection method, terminal and computer readable storage medium thereof | |
CN114663871A (en) | Image recognition method, training method, device, system and storage medium | |
CN117710921A (en) | Training method, detection method and related device of target detection model | |
WO2024001617A1 (en) | Method and apparatus for identifying behavior of playing with mobile phone | |
CN116863376A (en) | Edge computing method and system for detecting abnormal event of elevator car passenger | |
CN112488054A (en) | Face recognition method, face recognition device, terminal equipment and storage medium | |
CN115861755A (en) | Feature fusion method and device, electronic equipment and automatic driving vehicle | |
CN114663953A (en) | Facial expression recognition method based on facial key points and deep neural network |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 19906165 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 19906165 Country of ref document: EP Kind code of ref document: A1 |