CN112182294A - Video structured human-vehicle detection algorithm - Google Patents

Video structured human-vehicle detection algorithm Download PDF

Info

Publication number
CN112182294A
CN112182294A CN202011044567.0A CN202011044567A CN112182294A CN 112182294 A CN112182294 A CN 112182294A CN 202011044567 A CN202011044567 A CN 202011044567A CN 112182294 A CN112182294 A CN 112182294A
Authority
CN
China
Prior art keywords
algorithm
vehicle
license plate
video
target
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
Application number
CN202011044567.0A
Other languages
Chinese (zh)
Inventor
薛超
王健
王景彬
邓晔
梁飒
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Tiandy Technologies Co Ltd
Original Assignee
Tiandy Technologies Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Tiandy Technologies Co Ltd filed Critical Tiandy Technologies Co Ltd
Priority to CN202011044567.0A priority Critical patent/CN112182294A/en
Publication of CN112182294A publication Critical patent/CN112182294A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
    • G06F16/73—Querying
    • G06F16/732—Query formulation
    • G06F16/7328—Query by example, e.g. a complete video frame or video sequence
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
    • G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/783—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • G06F16/7837—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using objects detected or recognised in the video content
    • G06F16/784—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using objects detected or recognised in the video content the detected or recognised objects being people
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
    • G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/783—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • G06F16/7847—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using low-level visual features of the video content
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
    • G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/783—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • G06F16/7847—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using low-level visual features of the video content
    • G06F16/785—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using low-level visual features of the video content using colour or luminescence
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • 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
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/20—Analysis of motion
    • G06T7/246—Analysis of motion using feature-based methods, e.g. the tracking of corners or segments
    • 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
    • G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
    • G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
    • 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
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/60—Type of objects
    • G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
    • G06V20/63—Scene text, e.g. street names
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10016—Video; Image sequence
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/60—Type of objects
    • G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
    • G06V20/625—License plates
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00—Indexing scheme relating to image or video recognition or understanding
    • G06V2201/07—Target detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00—Indexing scheme relating to image or video recognition or understanding
    • G06V2201/08—Detecting or categorising vehicles
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/178—Human faces, e.g. facial parts, sketches or expressions estimating age from face image; using age information for improving recognition

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Library & Information Science (AREA)
  • Databases & Information Systems (AREA)
  • Computational Linguistics (AREA)
  • Mathematical Physics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Computation (AREA)
  • Biophysics (AREA)
  • Computing Systems (AREA)
  • Software Systems (AREA)
  • Biomedical Technology (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Molecular Biology (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Human Computer Interaction (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Image Analysis (AREA)
  • Traffic Control Systems (AREA)

Abstract

The invention provides a video structured human-vehicle detection algorithm, which comprises the following steps: acquiring a video frame through a camera; carrying out a target detection tracking algorithm on the obtained video frame; obtaining a target area through a target detection tracking algorithm, and sending the target area obtained through detection into a data reading model; reading a target area in the data reading model through a data reading algorithm to obtain corresponding data; the camera transmits the obtained data to the console for outputting. According to the video structured man-vehicle detection algorithm, the target attribute is extracted, and if a case occurs, a policeman can find a target which is consistent with the attribute from a photo library only according to the characteristics of suspects, so that the manpower time resource is saved, and the case handling efficiency is improved.

Description

Video structured human-vehicle detection algorithm
Technical Field
The invention belongs to the technical field of traffic management, and particularly relates to a video structured human-vehicle detection algorithm.
Background
In recent years, with the rapid advance of the urbanization process of China, the construction of safe cities and smart cities is accelerated, the security operation and maintenance cost is greatly increased by huge video monitoring data, in the traditional video monitoring, if relevant information of a certain area is required to be accurately obtained, the relevant information needs to be searched from thousands of hours of high-definition videos, the searching speed is low, and the searching efficiency is low; therefore, the video structuring of the regional information greatly improves the video searching speed, solves the problem of bandwidth pressure in video transmission and reduces the video storage capacity.
Disclosure of Invention
In view of this, the present invention provides a video structured human-vehicle detection algorithm to solve the problems of slow search speed and low search efficiency when searching for relevant information of a certain area in video monitoring, and solve the problems of bandwidth pressure in video transmission and reduction of video storage capacity.
In order to achieve the purpose, the technical scheme of the invention is realized as follows:
a video structured people and vehicle detection algorithm comprises the following steps:
s1, acquiring a video frame through a camera;
s2, carrying out a target detection tracking algorithm on the obtained video frame;
s3, obtaining a target area through a target detection tracking algorithm, and sending the target area obtained through detection into a data reading model;
s4, reading a target area in the data reading model through a data reading algorithm to obtain corresponding data;
and S5, the camera transmits the obtained data to the console for outputting.
The target detection and tracking algorithm in the step S1 includes the following steps: the method comprises the steps that a camera is used for acquiring a video, an algorithm is used for detecting the video, detected targets form a continuous track, a tracker is arranged in the algorithm, all targets of front and back video frames can be matched by the tracker, each target has a unique ID number, the matching between the targets is realized by utilizing algorithms such as DSST (direct sequence identification), KCF (KCF) and the like, whether the targets are the same target or not is determined by combining IOU (input object Unit) information of the front and back targets, the ID number of the previous frame is maintained to be unchanged by the same target, and new ID numbers are created by different targets; the entire video stream forms a continuous track after the target detection and tracking steps.
The data reading model in step S3 includes: the system comprises a license plate recognition model, a vehicle type recognition model and a pedestrian structural analysis model.
The data reading algorithm in step S4 includes: a license plate recognition algorithm, a vehicle type recognition algorithm and a pedestrian structural analysis algorithm.
The license plate recognition algorithm realizes the acquisition of the color, the type and the number of the license plate, and the realization process is as follows:
and (4) sending the vehicle target region detected in the step (S3) into a license plate positioning model to realize the positioning and type division of the license plate, sending the positioned license plate region into a license plate segmentation model to segment characters in the license plate, and finally outputting the content, confidence and color of the license plate.
The vehicle type recognition algorithm realizes the acquisition of the brand, the type and the color of the vehicle, and the realization process is as follows:
the method comprises the steps of realizing the positioning and type division of a vehicle type, sending a positioned vehicle type region into a vehicle type division model, dividing the brand, type and color of the vehicle in the vehicle type, and finally outputting the brand, type and color of a license plate of the vehicle.
The pedestrian structured analysis algorithm realizes the acquisition of the pedestrian structured information;
the pedestrian structured information includes: age of the person, belongings, upper body style, lower body style.
Compared with the prior art, the video structured human-vehicle detection algorithm has the following advantages:
the video structured man-vehicle detection algorithm effectively extracts information which is really valuable to clients from video big data and is the value of video structured representation; the video structuralization is used for proposing all required target information from the video big data and storing the information in a picture mode, so that the management and the search are facilitated; whether the target moves is judged to be an abnormal event or not by analyzing the behavior of the target in the video, such as illegal parking, illegal lane change and the like. By extracting the target attributes, if a case occurs, the policeman can find the target which is consistent with the target from the photo library only according to the characteristics of the suspects, so that the manpower time resource is saved, and the case handling efficiency is improved.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and, together with the description, serve to explain the invention without limitation. In the drawings:
fig. 1 is a flow chart of a video structured human-vehicle detection algorithm according to an embodiment of the present invention;
fig. 2 is a flow chart of the pedestrian structured information according to the embodiment of the present invention.
Detailed Description
It should be noted that the embodiments and features of the embodiments of the present invention may be combined with each other without conflict.
In the description of the present invention, it is to be understood that the terms "central," "longitudinal," "lateral," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," and the like are used in the orientation or positional relationship indicated in the drawings, which are merely for convenience in describing the invention and to simplify the description, and are not intended to indicate or imply that the referenced device or element must have a particular orientation, be constructed and operated in a particular orientation, and are therefore not to be construed as limiting the invention. Furthermore, the terms "first", "second", etc. are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first," "second," etc. may explicitly or implicitly include one or more of that feature. In the description of the invention, the meaning of "a plurality" is two or more unless otherwise specified.
In the description of the invention, it is to be noted that, unless otherwise explicitly specified or limited, the terms "mounted", "connected" and "connected" are to be construed broadly, e.g. as being fixed or detachable or integrally connected; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meaning of the above terms in the creation of the present invention can be understood by those of ordinary skill in the art through specific situations.
The invention will be described in detail with reference to the following embodiments with reference to the attached drawings.
A video structured people and vehicle detection algorithm comprises the following steps:
s1, acquiring a video frame through a camera;
s2, carrying out a target detection tracking algorithm on the obtained video frame;
s3, obtaining a target area through a target detection tracking algorithm, and sending the target area obtained through detection into a data reading model;
s4, reading a target area in the data reading model through a data reading algorithm to obtain corresponding data;
and S5, the camera transmits the obtained data to the console for outputting.
The target detection and tracking algorithm in the step S1 includes the following steps: the method comprises the steps that a camera is used for acquiring a video, an algorithm is used for detecting the video, detected targets form a continuous track, a tracker is arranged in the algorithm, all targets of front and back video frames can be matched by the tracker, each target has a unique ID number, the matching between the targets is realized by utilizing algorithms such as DSST (direct sequence identification), KCF (KCF) and the like, whether the targets are the same target or not is determined by combining IOU (input object Unit) information of the front and back targets, the ID number of the previous frame is maintained to be unchanged by the same target, and new ID numbers are created by different targets; the entire video stream forms a continuous track after the target detection and tracking steps.
The data reading model in step S3 includes: the system comprises a license plate recognition model, a vehicle type recognition model and a pedestrian structural analysis model.
The data reading algorithm in step S4 includes: a license plate recognition algorithm, a vehicle type recognition algorithm and a pedestrian structural analysis algorithm.
The license plate recognition algorithm realizes the acquisition of the color, the type and the number of the license plate, and the realization process is as follows:
and (4) sending the vehicle target region detected in the step (S3) into a license plate positioning model to realize the positioning and type division of the license plate, sending the positioned license plate region into a license plate segmentation model to segment characters in the license plate, and finally outputting the content, confidence and color of the license plate.
The vehicle type recognition algorithm realizes the acquisition of the brand, the type and the color of the vehicle, and the realization process is as follows:
the method comprises the steps of realizing the positioning and type division of a vehicle type, sending a positioned vehicle type region into a vehicle type division model, dividing the brand, type and color of the vehicle in the vehicle type, and finally outputting the brand, type and color of a license plate of the vehicle.
The pedestrian structured analysis algorithm realizes the acquisition of the pedestrian structured information;
the pedestrian structured information includes: age of the person, belongings, upper body style, lower body style.
The specific introduction is as follows:
target detection tracking algorithm
The algorithm can detect and track targets such as automobiles, buses, trucks, pedestrians, two-wheel vehicles, tricycles and the like in a traffic scene, and lays a foundation for acquiring real-time information of the targets. The target detection part is based on a YOLO detection algorithm, the algorithm is finally deployed on a front-end camera, the calculation force of the camera is limited, other operations such as video streaming and the like are considered when the algorithm is processed, therefore, a model needs to be optimized, the model finally takes the dark net-53 as a backbone network, and the detection speed is increased by deleting the number of channels and reducing the number of network layers on the premise of ensuring the detection precision so as to adapt to the detection of vehicles with different speeds on urban roads and expressways; in order to ensure the model effect, data required by model training is acquired from each traffic site and is enhanced (color enhancement, image cutting and the like) to meet the multi-scene requirement; the tracking part forms a continuous track for the detected targets, a tracker is maintained in the algorithm, the tracker can match all targets of front and back video frames to enable each target to have a unique ID number, the matching between the targets utilizes DSST, KCF and other algorithms, simultaneously, the IOU information of the front and back targets is combined to confirm whether the targets are the same target, the ID number of the previous frame is maintained to be the same target, and new ID numbers are created for different targets; the entire video stream forms a continuous track after the target detection and tracking steps.
Second, license plate recognition algorithm
The algorithm consists of a license plate positioning algorithm and a license plate segmentation algorithm, wherein the license plate positioning algorithm realizes the determination of the position of the license plate on the basis of YOLO, CENTERNET and the like, and because the target of the license plate is small and the information contained in the image is relatively less, the model takes darknet-19 as a main network and is deleted to adapt to the deployment of the front end part, firstly, the YOLO part realizes the coarse positioning of the license plate, finds the rough range of the license plate and determines the types of the license plate (blue plate, yellow-green plate and the like), secondly, CENTERNET is used for further carrying out the corner point detection of the license plate on the result of the coarse positioning to obtain four corner points of the license plate, and finally, the detected corner points are subjected to the rotation of the whole license plate, and; the license plate segmentation algorithm is used for segmenting and recognizing characters of a license plate, a YOLO model is also used for segmenting the license plate, the positions of all characters of the license plate are detected, and then the detected characters are sent to a classification network to accurately obtain character information; the whole process is as follows: the vehicle target area detected in the target detection model is sent to a license plate positioning model to realize the positioning and type division of the license plate, the positioned license plate area is sent to a license plate segmentation model to segment characters in the license plate, and finally the content, confidence and color of the license plate are output.
Vehicle type recognition algorithm
And sending the vehicle target area detected in the target detection model into the existing vehicle type identification model to realize identification of the brand, the type and the color of the vehicle body. Wherein the vehicle brand will output: vehicle major brand-vehicle sub brand-year money, vehicle type will output: 17 types of cars, minibuses, pickup trucks, off-road vehicles/SUVs, business vehicles/MPVs, light buses, medium buses, large buses, school buses, mini-trucks, light trucks, medium trucks, large trucks, heavy trucks, container vehicles, tricycles and the like, the body color will be output: black, blue, brown, green, gray, orange, pink, purple, red, silver, white, yellow, etc. 12 colors.
Fourth, pedestrian structured analysis algorithm
And (3) sending the pedestrian region detected by the target detection model in the target detection tracking algorithm into the existing pedestrian structural analysis model to realize the structural analysis of the pedestrian.
Wherein:
age: divided into 4 segments, below 15 years old, 15-30 years old, 30-50 years old, and above 50 years old. Wherein the probability of 30-50 years old is a default value;
accessories: carrying articles, backpack, handbag, single-shoulder bag or messenger bag, baby carriage, luggage case;
the style of the upper part of the body is as follows: stripes, solid colors, patterns, lattices;
the style of the lower part of the body is as follows: trousers, skirts, shorts.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and should not be taken as limiting the invention, so that any modifications, equivalents, improvements and the like, which are within the spirit and principle of the present invention, should be included in the scope of the present invention.

Claims (7)

1. A video structured human-vehicle detection algorithm is characterized by comprising the following steps:
s1, acquiring a video frame through a camera;
s2, carrying out a target detection tracking algorithm on the obtained video frame;
s3, obtaining a target area through a target detection tracking algorithm, and sending the target area obtained through detection into a data reading model;
s4, reading a target area in the data reading model through a data reading algorithm to obtain corresponding data;
and S5, the camera transmits the obtained data to the console for outputting.
2. The video structured people-vehicle detection algorithm of claim 1, wherein: the target detection and tracking algorithm in the step S1 includes the following steps: the method comprises the steps that a camera is used for acquiring a video, an algorithm is used for detecting the video, detected targets form a continuous track, a tracker is arranged in the algorithm, all targets of front and back video frames can be matched by the tracker, each target has a unique ID number, the matching between the targets is realized by utilizing algorithms such as DSST (direct sequence identification), KCF (KCF) and the like, whether the targets are the same target or not is determined by combining IOU (input object Unit) information of the front and back targets, the ID number of the previous frame is maintained to be unchanged by the same target, and new ID numbers are created by different targets; the entire video stream forms a continuous track after the target detection and tracking steps.
3. The video structured people-vehicle detection algorithm of claim 1, wherein: the data reading model in step S3 includes: the system comprises a license plate recognition model, a vehicle type recognition model and a pedestrian structural analysis model.
4. The video structured people-vehicle detection algorithm of claim 1, wherein: the data reading algorithm in step S4 includes: a license plate recognition algorithm, a vehicle type recognition algorithm and a pedestrian structural analysis algorithm.
5. The video structured people-vehicle detection algorithm of claim 1, wherein: the license plate recognition algorithm realizes the acquisition of the color, the type and the number of the license plate, and the realization process is as follows:
and (4) sending the vehicle target region detected in the step (S3) into a license plate positioning model to realize the positioning and type division of the license plate, sending the positioned license plate region into a license plate segmentation model to segment characters in the license plate, and finally outputting the content, confidence and color of the license plate.
6. The video structured people-vehicle detection algorithm of claim 1, wherein: the vehicle type recognition algorithm realizes the acquisition of the brand, the type and the color of the vehicle, and the realization process is as follows:
the method comprises the steps of realizing the positioning and type division of a vehicle type, sending a positioned vehicle type region into a vehicle type division model, dividing the brand, type and color of the vehicle in the vehicle type, and finally outputting the brand, type and color of a license plate of the vehicle.
7. The video structured people-vehicle detection algorithm of claim 1, wherein: the pedestrian structured analysis algorithm realizes the acquisition of the pedestrian structured information;
the pedestrian structured information includes: age of the person, belongings, upper body style, lower body style.
CN202011044567.0A 2020-09-28 2020-09-28 Video structured human-vehicle detection algorithm Pending CN112182294A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011044567.0A CN112182294A (en) 2020-09-28 2020-09-28 Video structured human-vehicle detection algorithm

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011044567.0A CN112182294A (en) 2020-09-28 2020-09-28 Video structured human-vehicle detection algorithm

Publications (1)

Publication Number Publication Date
CN112182294A true CN112182294A (en) 2021-01-05

Family

ID=73946547

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011044567.0A Pending CN112182294A (en) 2020-09-28 2020-09-28 Video structured human-vehicle detection algorithm

Country Status (1)

Country Link
CN (1) CN112182294A (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112926540A (en) * 2021-04-08 2021-06-08 天津天地伟业智能安全防范科技有限公司 Method and device for detecting helmet wearing of two-wheeled vehicle and electronic equipment
CN113674318A (en) * 2021-08-16 2021-11-19 支付宝(杭州)信息技术有限公司 Target tracking method, device and equipment
CN114140726A (en) * 2021-12-03 2022-03-04 湖北微模式科技发展有限公司 Method for detecting continuity of front and back display actions of target

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120320510A1 (en) * 2011-06-20 2012-12-20 Real Time Company Mobile networked optimized supply, data, and power generation & distribution system
CN104050450A (en) * 2014-06-16 2014-09-17 西安通瑞新材料开发有限公司 Vehicle license plate recognition method based on video
CN106571039A (en) * 2016-08-22 2017-04-19 中海网络科技股份有限公司 Automatic snapshot system for highway traffic offence
CN109697420A (en) * 2018-12-17 2019-04-30 长安大学 A kind of Moving target detection and tracking towards urban transportation
CN110390292A (en) * 2018-10-26 2019-10-29 西安电子科技大学 Based on the remote sensing video frequency vehicle object detecting and tracking method for dynamically associating model
CN110472496A (en) * 2019-07-08 2019-11-19 长安大学 A kind of traffic video intelligent analysis method based on object detecting and tracking

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20120320510A1 (en) * 2011-06-20 2012-12-20 Real Time Company Mobile networked optimized supply, data, and power generation & distribution system
CN104050450A (en) * 2014-06-16 2014-09-17 西安通瑞新材料开发有限公司 Vehicle license plate recognition method based on video
CN106571039A (en) * 2016-08-22 2017-04-19 中海网络科技股份有限公司 Automatic snapshot system for highway traffic offence
CN110390292A (en) * 2018-10-26 2019-10-29 西安电子科技大学 Based on the remote sensing video frequency vehicle object detecting and tracking method for dynamically associating model
CN109697420A (en) * 2018-12-17 2019-04-30 长安大学 A kind of Moving target detection and tracking towards urban transportation
CN110472496A (en) * 2019-07-08 2019-11-19 长安大学 A kind of traffic video intelligent analysis method based on object detecting and tracking

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112926540A (en) * 2021-04-08 2021-06-08 天津天地伟业智能安全防范科技有限公司 Method and device for detecting helmet wearing of two-wheeled vehicle and electronic equipment
CN113674318A (en) * 2021-08-16 2021-11-19 支付宝(杭州)信息技术有限公司 Target tracking method, device and equipment
CN114140726A (en) * 2021-12-03 2022-03-04 湖北微模式科技发展有限公司 Method for detecting continuity of front and back display actions of target
CN114140726B (en) * 2021-12-03 2022-06-21 湖北微模式科技发展有限公司 Method for detecting continuity of front and back display actions of target

Similar Documents

Publication Publication Date Title
CN112182294A (en) Video structured human-vehicle detection algorithm
CN104778444B (en) The appearance features analysis method of vehicle image under road scene
CN105702048B (en) Highway front truck illegal road occupation identifying system based on automobile data recorder and method
CN106127107A (en) The model recognizing method that multi-channel video information based on license board information and vehicle's contour merges
CN103824037B (en) Vehicle anti-tracking alarm device
CN107016362B (en) Vehicle weight recognition method and system based on vehicle front windshield pasted mark
CN112651293B (en) Video detection method for road illegal spreading event
CN102708691B (en) False license plate identification method based on matching between license plate and automobile type
CN101944292A (en) Suspected vehicle analysis method based on track collision
CN110619277A (en) Multi-community intelligent deployment and control method and system
US11948366B2 (en) Automatic license plate recognition (ALPR) and vehicle identification profile methods and systems
CN102902957A (en) Video-stream-based automatic license plate recognition method
CN107103314A (en) A kind of fake license plate vehicle retrieval system based on machine vision
CN103914682A (en) Vehicle license plate recognition method and system
CN106710225A (en) Identification method and monitoring platform for illegal operation related with vehicle license plate
CN112381859A (en) System, method, device, processor and storage medium for realizing intelligent analysis, identification and processing for video image data
Hampapur et al. Searching surveillance video
KR101066081B1 (en) Smart information detection system mounted on the vehicle and smart information detection method using the same
Dubuisson et al. Object contour extraction using color and motion
CN104408431A (en) Vehicle model identification method under traffic monitoring
CN112669615B (en) Parking space detection method and system based on camera
Coronado et al. Detection and classification of road signs for automatic inventory systems using computer vision
KR100942409B1 (en) Method for detecting a moving vehicle at a high speed
CN109325755A (en) Electronics charge system based on automotive hub
Matsuda et al. A Method for Detecting Street Parking Using Dashboard Camera Videos.

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
RJ01 Rejection of invention patent application after publication

Application publication date: 20210105