CN113033449A - Vehicle detection and marking method and system and electronic equipment - Google Patents
Vehicle detection and marking method and system and electronic equipment Download PDFInfo
- Publication number
- CN113033449A CN113033449A CN202110361601.5A CN202110361601A CN113033449A CN 113033449 A CN113033449 A CN 113033449A CN 202110361601 A CN202110361601 A CN 202110361601A CN 113033449 A CN113033449 A CN 113033449A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- video
- marking
- video stream
- tracking
- 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.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 32
- 238000000034 method Methods 0.000 title claims abstract description 16
- 238000002372 labelling Methods 0.000 claims description 52
- 238000013500 data storage Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 9
- 238000012937 correction Methods 0.000 claims description 8
- 238000009877 rendering Methods 0.000 claims description 5
- 230000008901 benefit Effects 0.000 abstract description 8
- 238000005516 engineering process Methods 0.000 abstract description 6
- 238000012545 processing Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 235000019800 disodium phosphate Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
- G06V10/56—Extraction of image or video features relating to colour
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a vehicle detection and marking method, a vehicle detection and marking system and electronic equipment, wherein the vehicle detection and marking system comprises: a video stream tracking system and a video stream annotation system; the video stream tracking system is used for tracking a vehicle track appearing in a section of video stream and obtaining the position coordinates of the vehicle in the video stream frame by frame; the video stream marking system is used for marking the vehicle type and the color of the tracked vehicle and marking all frames of the same vehicle in the video. The invention can make full use of the advantages of vehicle identification and tracking technology, and avoids the complexity and low efficiency of marking vehicles in video stream frame by frame while ensuring the available marking accuracy.
Description
Technical Field
The invention relates to the field of vehicle identification, vehicle tracking and data marking, in particular to a vehicle detection and marking method, a vehicle detection and marking system and electronic equipment.
Background
With the continuous development of image recognition and deep learning technologies in recent years, many fields need to train own automobile recognition models. However, due to different requirements of various fields on the automobile recognition models, in many cases, data set enhancement needs to be performed on the existing models, or the models of the automobile need to be trained again by using the automobile data.
Conventional vehicle data annotation uses manual annotation from frame to frame with images or video. During the labeling process of tools such as LabelImg, OpenCV/CVAT, Ybat, etc., the annotator needs to outline the bounding box or outline of the vehicle on the image frame by frame. Such labeling has the advantage of high accuracy, but also has a significant disadvantage of being inefficient.
If the tracked vehicle is marked by using the vehicle tracking technology, after the track connection is established, only one identification frame needs to be marked, and all subsequent continuous identification frames can be marked. Ideally, if several cars appear in a video, only a few annotations are needed. A vehicle often appears hundreds of frames or more in a video, and the marking efficiency can be improved greatly by using the vehicle tracking technology.
Disclosure of Invention
In view of the above drawbacks of the prior art, an object of the present invention is to provide a vehicle detecting and labeling method, system and electronic device, which are used to solve the technical problems that the prior art cannot label vehicle data efficiently, and is time-consuming and labor-consuming.
To achieve the above and other related objects, the present invention provides a vehicle detecting and labeling method, comprising: tracking the vehicle track appearing in a section of video stream, and obtaining the position coordinates of the vehicle in the video stream frame by frame; after the video stream is tracked, creating an item which can be read by a video stream marking system, and providing vehicle tracking information for subsequent marking; and marking the vehicle type and color of the tracked vehicle, and marking all frames of the same vehicle in the video.
In an embodiment of the present invention, the tracking a vehicle track appearing in a segment of the video stream, and obtaining the position coordinates of the vehicle in the video stream frame by frame includes: matching and predicting according to the position coordinates output by the vehicle identification model and the vehicle characteristic information in the video stream; the position coordinates of the vehicle in the video stream are identified on a frame-by-frame basis.
In an embodiment of the present invention, all frames of the marked video where the same vehicle appears include: marking a tracked vehicle track; manually marking the untracked vehicle track; and deleting a plurality of vehicles with continuous cutting tracks and the wrong vehicle tracking bounding boxes.
In an embodiment of the present invention, the vehicle detecting and labeling method further includes: cutting the video into a part of the original video; and rendering the video according to the identified frame serial number and the vehicle position coordinates, and marking the vehicle information in the video by using the bright color.
The embodiment of the invention also provides a vehicle detection and marking system, which comprises: a video stream tracking system and a video stream annotation system; the video stream tracking system is used for tracking a vehicle track appearing in a section of video stream and obtaining the position coordinates of the vehicle in the video stream frame by frame; the video stream marking system is used for marking the vehicle type and the color of the tracked vehicle and marking all frames of the same vehicle in the video.
In an embodiment of the present invention, the system further includes a vehicle data storage system respectively connected to the video stream tracking system and the video stream annotation system; the vehicle data storage system is used for creating an item which can be read by the video stream marking system after the video stream is tracked, and providing vehicle tracking information for subsequent marking.
In an embodiment of the present invention, the video stream tracking system includes a vehicle identification model and a vehicle tracking model; the vehicle identification model is used for identifying the position coordinates of the vehicle in the video stream frame by frame; the vehicle tracking model is used for matching and predicting according to the position coordinates output by the vehicle identification model and the vehicle characteristic information in the video stream.
In an embodiment of the present invention, the video stream annotation system includes a track annotation system, a manual annotation system, an error correction system and a connected video system; the track marking system is used for marking a vehicle track traced by the vehicle tracing model; the manual marking system is used for manually marking the vehicle track which is not tracked by the vehicle tracking model; the error correction system is used for deleting a plurality of vehicles with continuous cutting tracks and wrong vehicle tracking bounding boxes.
In an embodiment of the present invention, the video system includes a video editing system and a video display system; the video editing system is used for cutting the video into a part of the original video; and the video display system is used for rendering the video according to the frame number and the vehicle position coordinates output by the vehicle tracking model and the vehicle identification model, and marking the vehicle information in the video by using the bright color.
Embodiments of the present invention also provide an electronic device comprising a memory for storing a computer program; and the processor is connected with the memory and is used for operating the computer program to realize the vehicle detection and marking method.
As described above, the vehicle detection and labeling method, system and electronic device of the present invention have the following beneficial effects:
the invention can make full use of the advantages of vehicle identification and tracking technology, and avoid the complexity and low efficiency of marking vehicles in video stream frame by frame while ensuring the available marking accuracy.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a general flowchart of a vehicle detecting and labeling method according to an embodiment of the present application.
FIG. 2 is a schematic block diagram of a vehicle detection and labeling system according to an embodiment of the present application.
FIG. 3 is a schematic block diagram of a preferred vehicle detection and labeling system in an embodiment of the present application.
FIG. 4 is a schematic block diagram of an implementation of the vehicle detection and labeling system in an embodiment of the present application.
Fig. 5 is a schematic block diagram of an electronic device according to an embodiment of the present application.
Description of the element reference numerals
100 vehicle detection and labeling system
110 video stream tracking system
111 vehicle recognition model
112 vehicle tracking model
120 video stream annotation system
121 track marking system
122 manual annotation system
123 error correction system
130 vehicle data storage system
140 video system
141 video editing system
142 video display system
10 electronic device
101 processor
102 memory
S100 to S300
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.
An object of the present embodiment is to provide a vehicle detecting and labeling method, system and electronic device, which are intended to fully utilize the advantages of a vehicle tracking system, so that a user can directly mark a tracked vehicle track, the trouble of frame-by-frame marking of a video stream is avoided, and the technical problems of low efficiency, time consuming and labor consuming of vehicle data labeling in the prior art are solved.
The principles and embodiments of the vehicle detection and labeling method, system and electronic device of the present invention will be described in detail below, so that those skilled in the art can understand the vehicle detection and labeling method, system and electronic device without creative efforts.
Example 1
As shown in fig. 1, the present embodiment provides a vehicle detecting and labeling method, which includes:
step S100, tracking a vehicle track appearing in a section of video stream, and obtaining the position coordinates of the vehicle in the video stream frame by frame;
step S200, after the video stream is tracked, creating an item which can be read by a video stream marking system, and providing vehicle tracking information for subsequent marking;
and step S300, marking the vehicle type and the color of the tracked vehicle, and marking all frames of the same vehicle in the video.
The following describes the steps S100 to S300 in the vehicle detecting and labeling method according to the present embodiment in detail.
And step S100, tracking the vehicle track appearing in a section of video stream, and obtaining the position coordinates of the vehicle in the video stream frame by frame.
In this embodiment, the tracking a vehicle track appearing in a segment of the video stream, and obtaining the position coordinates of the vehicle in the video stream frame by frame includes: matching and predicting according to the position coordinates output by the vehicle identification model and the vehicle characteristic information in the video stream; the position coordinates of the vehicle in the video stream are identified on a frame-by-frame basis.
Step S200, after the video stream is tracked, creating an item that can be read by the video stream annotation system, and providing vehicle tracking information for subsequent annotation.
And step S300, marking the vehicle type and the color of the tracked vehicle, and marking all frames of the same vehicle in the video.
In this embodiment, all frames in the marked video where the same vehicle appears include:
1) marking a tracked vehicle track;
2) manually marking the untracked vehicle track;
3) and deleting a plurality of vehicles with continuous cutting tracks and the wrong vehicle tracking bounding boxes.
In this embodiment, the vehicle detecting and labeling method further includes:
1) cutting the video into a part of the original video;
2) and rendering the video according to the identified frame serial number and the vehicle position coordinates, and marking the vehicle information in the video by using the bright color.
One specific implementation process of the vehicle detection and labeling method of the embodiment is as follows:
first, using a vehicle identification model (preferably, YOLOv5 is used as the identification model in the present embodiment), vehicle position information occurring in each frame in a video is identified and the information is saved to a vehicle data saving system. Thereafter, a vehicle tracking model (preferably, deppsort is used as a tracking model in the present embodiment) is used to acquire information of vehicle identification from the vehicle identification model, and tracking and matching are performed based on the video. Ideally, each tracked vehicle is assigned a specific number after completion.
Wherein the video is cropped and then saved before video stream tracking of the video. After the vehicle in the video is detected and tracked, the vehicle position data and the video are read from the vehicle data storage system for display. And correspondingly displaying by adopting a display system similar to a common video player and the like, wherein the display system supports playing, pausing, fast forwarding, fast rewinding and dragging of a video progress bar. Further, the embodiment also includes drawing identification frames with different colors in the video, and labeling information about the vehicle on the identification frames.
Specifically, for example, the display system provides a window with a video player on the left and a GUI on the right to mark the vehicle identified in the video. The user can select a vehicle number from the current frame to label, label the vehicle type and the color, label all vehicles under the same vehicle number, and store. The vehicle detection and marking method of the embodiment can enable a user to manually mark the identification frame of one vehicle, draw the track of the vehicle in interpolation and other modes, and then mark the vehicle. In some cases, a vehicle number may correspond to the trajectory of two or more vehicles. The vehicle detecting and labeling method of the present embodiment may further divide the vehicle number into two or more segments, so that each segment can be individually labeled.
Example 2
As shown in fig. 2, the present embodiment provides a vehicle detecting and labeling system 100, forming an automatic auxiliary tool for detecting and labeling a vehicle, wherein the vehicle detecting and labeling system 100 includes: a video stream tracking system 110 and a video stream annotation system 120.
The video stream tracking system 110 is configured to track a vehicle track appearing in a section of video stream, and obtain position coordinates of a vehicle in the video stream frame by frame; the video stream labeling system 120 is used for labeling the vehicle type and color of the tracked vehicle, and labeling all frames of the same vehicle in the video.
Specifically, in the present embodiment, as shown in fig. 3, the vehicle detecting and labeling system 100 further includes a vehicle data storage system 130 respectively connected to the video stream tracking system 110 and the video stream labeling system 120. The vehicle data storage system 130 is used to create an item that can be read by the video stream annotation system 120 after the video stream is tracked, and provide vehicle tracking information for subsequent annotation.
Specifically, in the present embodiment, as shown in fig. 4, the video stream tracking system 110 includes a vehicle identification model 111 and a vehicle tracking model 112. The vehicle identification model 111 is used for identifying the position coordinates of the vehicle in the video stream frame by frame; the vehicle tracking model 112 is used for matching and predicting according to the position coordinates output by the vehicle identification model 111 and the vehicle characteristic information in the video stream.
Specifically, in the embodiment, as shown in fig. 4, the video stream annotation system 120 includes a track annotation system 121, a manual annotation system 122, an error correction system 123 and a video system 140 connected thereto.
The trajectory labeling system 121 is configured to label a vehicle trajectory tracked by the vehicle tracking model 112; the manual labeling system 122 is used for manually labeling the vehicle track not tracked by the vehicle tracking model 112; the error correction system 123 is used to remove the wrong vehicle tracking bounding box, several vehicles with consecutive cutting tracks.
Specifically, in the present embodiment, as shown in fig. 4, the video system 140 includes a video editing system 141 and a video display system 142. The video editing system 141 is configured to cut the video into a part of the original video; the video display system 142 is configured to render a video according to the frame number and the vehicle position coordinates output by the vehicle tracking model 112 and the vehicle identification model 111, and mark vehicle information in the video with a bright color.
One specific implementation process of the vehicle detecting and labeling system 100 of the embodiment is as follows:
first, the vehicle identification model 111 in the video stream tracking system 110 (preferably, YOLOv5 is used as the identification model in the present embodiment) identifies the vehicle position information occurring in each frame in the video, and stores the information to the vehicle data storage system 130. Thereafter, the vehicle tracking model 112 (preferably, deppsort is used as a tracking model in the present embodiment) acquires information of vehicle identification from the vehicle identification model 111, and performs tracking and matching based on the video. Ideally, each tracked vehicle is given a specific number after completion.
Wherein the video editing system 141 clips the video before inputting the video to the video stream tracking system 110 and then outputs the video to the vehicle data storage system 130. After the vehicle in the video is detected and tracked, the video display system 142 reads the vehicle position data and the video from the vehicle data storage system 130. Similar to a normal video player, the video display system 142 supports play, pause, fast forward, fast reverse, and dragging of a video progress bar. Further, the video display system 142 draws different colored identification frames in the video and marks information about the vehicle on the identification frames.
The video display system 142 provides a window with a video player on the left and a GUI on the right to mark the vehicle identified in the video. The user can select a vehicle number from the current frame for labeling, and the labeled vehicle type and color result is transmitted to the trajectory labeling system 121, so as to label all vehicles under the same vehicle number and store the same vehicle number in the vehicle data storage system 130. The manual labeling system 122 allows a user to manually label an identification frame of a vehicle, and draw a track of the vehicle by interpolation or the like, and then label the vehicle. In some cases, a vehicle number may correspond to the trajectory of two or more vehicles. The error correction system 123 may divide such vehicle numbers into two or more segments, allowing each segment to be individually labeled.
It should be noted that the division of the modules of the above system is only a logical division, and the actual implementation may be wholly or partially integrated into one physical entity or may be physically separated. And the modules can be realized in the form that software is called by a processing element; or may be implemented entirely in hardware; and part of the modules can be realized in the form of calling software by the processing element, and part of the modules can be realized in the form of hardware. For example, some modules may be processing elements that are separately set up, or may be implemented by being integrated in a chip of the system, or may be stored in a memory of the system in the form of program codes, and called by a processing element of the system and executed as functions of some modules. Other modules are implemented similarly. In addition, all or part of the modules can be integrated together or can be independently realized. The processing element described herein may be an integrated circuit having signal processing capabilities. In the implementation process, each step of the above method or each module above can be completed by the integrated logic circuit of hardware in the processor element or instructions in the form of software.
For example, the above modules may be one or more integrated circuits configured to implement the above methods, such as: one or more Application Specific Integrated Circuits (ASICs), or one or more microprocessors (DSPs), or one or more Field Programmable Gate Arrays (FPGAs), among others. For another example, when one of the above modules is implemented in the form of a Processing element scheduler code, the Processing element may be a general-purpose processor, such as a Central Processing Unit (CPU) or other processor capable of calling program code. For another example, these modules may be integrated together and implemented in the form of a system-on-a-chip (SOC).
Example 3
As shown in fig. 5, the embodiment further provides an electronic device 10, where the electronic device 10 is, but not limited to, a smart phone, a tablet, a smart wearable device, a personal desktop computer, a notebook computer, a server cluster, and the like.
The electronic device 10 comprises a memory 102 for storing a computer program; a processor 101 for running the computer program to implement the steps of the vehicle detection and labeling method according to embodiment 1.
The memory 102 is connected to the processor 101 through a system bus and is used for completing communication between the processor and the memory 102, the processor 101 is used for running a computer program, so that the electronic device 10 executes the vehicle detection and labeling method. In embodiment 1, the vehicle detecting and labeling method has already been described, and is not described herein again.
It should be noted that the above-mentioned system bus may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The system bus may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown in FIG. 5, but this is not intended to represent only one bus or type of bus. The communication interface is used for realizing communication between the database access system and other devices (such as a client, a read-write library and a read-only library). The Memory 102 may include a Random Access Memory (RAM) and may further include a non-volatile Memory (non-volatile Memory), such as at least one disk Memory.
The Processor 101 may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the Integrated Circuit may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, or discrete hardware components.
Example 4
The present embodiment provides a storage medium storing program instructions, which when executed by a processor implement the steps of the vehicle detection and labeling method described in embodiment 1. The vehicle detecting and labeling method has already been described in embodiment 1, and is not described herein again.
Those of ordinary skill in the art will understand that: all or part of the steps for implementing the above method embodiments may be performed by hardware associated with a computer program. The aforementioned computer program may be stored in a computer readable storage medium. The program, when executed, performs the steps comprising the method embodiments of embodiment 1; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
In conclusion, the invention can make full use of the advantages of the vehicle identification and tracking technology, and avoid the complexity and low efficiency of marking the vehicle in the video stream frame by frame while ensuring the available marking accuracy. Therefore, the invention effectively overcomes various defects in the prior art and has high industrial utilization value.
The foregoing embodiments are merely illustrative of the principles and utilities of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present invention. Accordingly, it is intended that all equivalent modifications or changes which may be accomplished by those skilled in the art without departing from the spirit and scope of the present invention as set forth in the appended claims.
Claims (10)
1. A vehicle detection and labeling method is characterized in that: the method comprises the following steps:
tracking a vehicle track appearing in a section of video stream, and obtaining the position coordinates of the vehicle in the video stream frame by frame;
after the video stream is tracked, creating an item which can be read by a video stream marking system, and providing vehicle tracking information for subsequent marking;
and marking the vehicle type and color of the tracked vehicle, and marking all frames of the same vehicle in the video.
2. The vehicle detection and labeling method of claim 1, wherein: the tracking a vehicle track appearing in a section of video stream, and the obtaining the position coordinates of the vehicle in the video stream frame by frame comprises the following steps:
matching and predicting according to the position coordinates output by the vehicle identification model and the vehicle characteristic information in the video stream;
the position coordinates of the vehicle in the video stream are identified on a frame-by-frame basis.
3. The vehicle detection and labeling method of claim 1, wherein: all frames in the marked video where the same vehicle appears include:
marking a tracked vehicle track;
manually marking the untracked vehicle track;
and deleting a plurality of vehicles with continuous cutting tracks and the wrong vehicle tracking bounding boxes.
4. The vehicle detection and labeling method of claim 1 or 3, further comprising: the vehicle detection and labeling method further comprises the following steps:
cutting the video into a part of the original video;
and rendering the video according to the identified frame serial number and the vehicle position coordinates, and marking the vehicle information in the video by using the bright color.
5. A vehicle detection and labeling system, characterized by: the method comprises the following steps: a video stream tracking system and a video stream annotation system;
the video stream tracking system is used for tracking a vehicle track appearing in a section of video stream and obtaining the position coordinates of the vehicle in the video stream frame by frame;
the video stream marking system is used for marking the vehicle type and the color of the tracked vehicle and marking all frames of the same vehicle in the video.
6. The vehicle detection and labeling system of claim 5, wherein: the vehicle data storage system is respectively connected with the video stream tracking system and the video stream marking system;
the vehicle data storage system is used for creating an item which can be read by the video stream marking system after the video stream is tracked, and providing vehicle tracking information for subsequent marking.
7. The vehicle detection and labeling system of claim 5, wherein: the video stream tracking system comprises a vehicle identification model and a vehicle tracking model;
the vehicle identification model is used for identifying the position coordinates of the vehicle in the video stream frame by frame;
the vehicle tracking model is used for matching and predicting according to the position coordinates output by the vehicle identification model and the vehicle characteristic information in the video stream.
8. The vehicle detection and labeling system of claim 6, wherein: the video stream marking system comprises a track marking system, a manual marking system, an error correction system and a connected video system;
the track marking system is used for marking a vehicle track traced by the vehicle tracing model;
the manual marking system is used for manually marking the vehicle track which is not tracked by the vehicle tracking model;
the error correction system is used for deleting a plurality of vehicles with continuous cutting tracks and wrong vehicle tracking bounding boxes.
9. The vehicle detection and labeling system of claim 8, wherein: the video system comprises a video editing system and a video display system;
the video editing system is used for cutting the video into a part of the original video;
and the video display system is used for rendering the video according to the frame number and the vehicle position coordinates output by the vehicle tracking model and the vehicle identification model, and marking the vehicle information in the video by using the bright color.
10. An electronic device, comprising a memory for storing a computer program; a processor, coupled to the memory, for executing the computer program to implement the vehicle detection and labeling method of any of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110361601.5A CN113033449A (en) | 2021-04-02 | 2021-04-02 | Vehicle detection and marking method and system and electronic equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110361601.5A CN113033449A (en) | 2021-04-02 | 2021-04-02 | Vehicle detection and marking method and system and electronic equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113033449A true CN113033449A (en) | 2021-06-25 |
Family
ID=76453606
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110361601.5A Pending CN113033449A (en) | 2021-04-02 | 2021-04-02 | Vehicle detection and marking method and system and electronic equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113033449A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130088600A1 (en) * | 2011-10-05 | 2013-04-11 | Xerox Corporation | Multi-resolution video analysis and key feature preserving video reduction strategy for (real-time) vehicle tracking and speed enforcement systems |
| US20180060684A1 (en) * | 2016-08-31 | 2018-03-01 | Beijing University Of Posts And Telecommunications | Progressive vehicle searching method and device |
| CN109190444A (en) * | 2018-07-02 | 2019-01-11 | 南京大学 | A kind of implementation method of the lane in which the drivers should pay fees vehicle feature recognition system based on video |
| CN112070071A (en) * | 2020-11-11 | 2020-12-11 | 腾讯科技（深圳）有限公司 | Method and device for labeling objects in video, computer equipment and storage medium |
| CN112101433A (en) * | 2020-09-04 | 2020-12-18 | 东南大学 | Automatic lane-dividing vehicle counting method based on YOLO V4 and DeepsORT |
-
2021
- 2021-04-02 CN CN202110361601.5A patent/CN113033449A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130088600A1 (en) * | 2011-10-05 | 2013-04-11 | Xerox Corporation | Multi-resolution video analysis and key feature preserving video reduction strategy for (real-time) vehicle tracking and speed enforcement systems |
| US20180060684A1 (en) * | 2016-08-31 | 2018-03-01 | Beijing University Of Posts And Telecommunications | Progressive vehicle searching method and device |
| CN109190444A (en) * | 2018-07-02 | 2019-01-11 | 南京大学 | A kind of implementation method of the lane in which the drivers should pay fees vehicle feature recognition system based on video |
| CN112101433A (en) * | 2020-09-04 | 2020-12-18 | 东南大学 | Automatic lane-dividing vehicle counting method based on YOLO V4 and DeepsORT |
| CN112070071A (en) * | 2020-11-11 | 2020-12-11 | 腾讯科技（深圳）有限公司 | Method and device for labeling objects in video, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8879894B2 (en) | Pixel analysis and frame alignment for background frames | |
| US20040161151A1 (en) | On-line handwritten character pattern recognizing and editing apparatus and method, and recording medium storing computer-executable program for realizing the method | |
| CN102576561A (en) | Apparatus and method for editing | |
| CN110866930A (en) | Semantic segmentation auxiliary labeling method and device | |
| CN110838105A (en) | Business process model image identification and reconstruction method | |
| CN109885929B (en) | Automatic driving decision planning data reproduction method and device | |
| CN113159212A (en) | OCR recognition model training method, device and computer readable storage medium | |
| CN107562710B (en) | Chart processing device and method | |
| CN115136209A (en) | Defect detection system | |
| CN112883926A (en) | Identification method and device for table medical images | |
| CN113111708B (en) | Vehicle matching sample generation method, device, computer equipment and storage medium | |
| CN112509097A (en) | Hand-drawn animation material editing method and device | |
| CN113033449A (en) | Vehicle detection and marking method and system and electronic equipment | |
| CN112084103B (en) | Interface test method, device, equipment and medium | |
| WO2022193460A1 (en) | Presentation template transition method and device | |
| US20230118401A1 (en) | Graph-based video instance segmentation | |
| CN114708239A (en) | Glue width detection method and device, electronic equipment and storage medium | |
| US20210073580A1 (en) | Method and apparatus for obtaining product training images, and non-transitory computer-readable storage medium | |
| CN117152563B (en) | Training method and device for hybrid target domain adaptive model and computer equipment | |
| CN113111709B (en) | Vehicle matching model generation method, device, computer equipment and storage medium | |
| TWI771908B (en) | Method for classifying and annotating image, device, electronic device, and storage medium | |
| CN117557786B (en) | Material quality detection method, device, computer equipment and storage medium | |
| CN113989703A (en) | Media resource labeling method, device, equipment and storage medium | |
| CN110991296B (en) | Video annotation method and device, electronic equipment and computer-readable storage medium | |
| US20230047459A1 (en) | Method and system for analyzing viewing direction of electronic component, computer program product with stored program, and computer readable medium with stored program |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210625 |
|
| RJ01 | Rejection of invention patent application after publication |