CN107944017A - The search method of non-motor vehicle in a kind of video - Google Patents
The search method of non-motor vehicle in a kind of video Download PDFInfo
- Publication number
- CN107944017A CN107944017A CN201711308824.5A CN201711308824A CN107944017A CN 107944017 A CN107944017 A CN 107944017A CN 201711308824 A CN201711308824 A CN 201711308824A CN 107944017 A CN107944017 A CN 107944017A
- Authority
- CN
- China
- Prior art keywords
- motor vehicle
- image
- driver
- unstructured
- feature
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
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
- G06F16/78—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
- G06F16/73—Querying
- G06F16/738—Presentation of query results
-
- 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
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Library & Information Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of search method of non-motor vehicle in video, include the following steps：Step 1：The image containing non-motor vehicle and driver in image library is obtained, using the non-motor vehicle in every image and driver as a target, each target is calculated and is extracted unstructured feature, the unstructured feature of all targets is inserted into search library；Step 2：For an image to be retrieved, the unstructured feature of target in the image to be retrieved is calculated and extracted；Step 3：Calculate and image more to be retrieved in target and search library the unstructured feature of all targets similarity, sequencing of similarity is obtained, using sequencing of similarity as retrieval result.The present invention can effectively improve the tracking and investigation efficiency to non-motor vehicle；Improve retrieval rate；The data for making full use of public security camera to collect, improve the service efficiency of monitoring data, present invention reduces use cost, implementation and perform very convenient.
Description
Technical field
The present invention relates to a kind of video image search method, and in particular to the search method of non-motor vehicle in a kind of video.
Belong to intelligent transportation, criminal investigation field.
Background technology
Road traffic bayonet, electronic police, the first-class monitoring device of general public security shooting are substantial amounts of at home at present
Installation and use, carry out data mining, object content analysis and the target in later stage on the video data that existing device collects
Retrieval has become a research hotspot of scientific research and industrial quarters.
Non-motor vehicle is that people use very extensive a kind of vehicles, and compared with motor vehicle, non-motor vehicle is not advised
The management rules of model and effective executable unit, can not effectively manage, and also can not effectively associate car owner's identity and information, very
In more illegal activities is all non-motor vehicle, because non-motor vehicle is easier to hide the fact that some are broken laws and commit crime, is escaped
People's lives and properties and public safety are caused great threat by the punishment of the serious consequence caused by it.Therefore in magnanimity
Security monitoring video in analysis, search and positioning non-motor vehicle and its driver, illegal violate is investigated and analyzed to traffic police
Guilty activity is of great significance.
Apply not yet retrieving during this patent disclosed by security monitoring video retrieval non-motor vehicle and its driver
Method, the method for relevant management and lookup non-motor vehicle《Non-motor vehicle management method, apparatus and system》In 106447009A,
The identification information entrained by RFID tag bound on mainly advance typing non-motor vehicle, collects the RFID detection knots of monitoring point
Fruit data and ambient video data, according to the identification information of advance typing, with reference to the RFID testing result data of the currently monitored point
Non-motor vehicle is positioned with ambient video data.Non-motor vehicle must bind RFID tag in this method, also need what is detected
Monitoring point is established in section, and of high cost, implementation and difficulty of implementation are also very big.
The content of the invention
To solve the deficiencies in the prior art, it is an object of the invention to provide a kind of retrieval side of non-motor vehicle in video
Method.
In order to realize above-mentioned target, the present invention adopts the following technical scheme that：
The search method of non-motor vehicle in a kind of video, it is characterised in that include the following steps：
Step 1：The image containing non-motor vehicle and driver in image library is obtained, by the non-motor vehicle in every image
With driver as a target, each target is calculated and extracts unstructured feature, by the unstructured spy of all targets
Sign insertion search library；
Step 2：For an image to be retrieved, the unstructured feature of target in the image to be retrieved is calculated and extracted；
Step 3：Calculate and image more to be retrieved in target and search library the unstructured feature of all targets phase
Like degree, sequencing of similarity is obtained, using sequencing of similarity as retrieval result.
The search method of non-motor vehicle in a kind of foregoing video, it is characterised in that calculate and extract unstructured feature
Include the following steps：
Non-motor vehicle and driver in automatic detection and positioning image；
Position and be partitioned into non-motor vehicle region and driver region；
The unstructured feature of non-motor vehicle part and driver part is calculated respectively, and merging obtains the non-knot of a target
Structure feature.
The search method of non-motor vehicle in a kind of foregoing video, it is characterised in that
The neural network model obtained according to training detects automatically and the non-motor vehicle in positioning image and driver；
The neural network model obtained according to training positions and is partitioned into non-motor vehicle region and driver region；
The unstructured of non-motor vehicle part and driver part is calculated according to the obtained neural network model of training respectively
Feature.
The search method of non-motor vehicle in a kind of foregoing video, it is characterised in that training neural network model is included such as
Lower step：
The multiple images with target are collected, form image pattern collection；
Mark image pattern and concentrate non-motor vehicle and position of driver, and be divided into non-motor vehicle region and driver
Region；
Different non-motor vehicles and the class label of driver are marked, as markup information；
Training sample set N is formed by all image pattern collection and corresponding markup information；
Based on training sample set N, training obtains the inspection for detecting and positioning non-motor vehicle and driver in image automatically
Survey device D；
Based on training sample set N, it is respectively trained to obtain the model M for calculating the unstructured feature of non-motor vehicle1With with
In the model M for calculating the unstructured feature of driver2。
The search method of non-motor vehicle in a kind of foregoing video, it is characterised in that step 1 includes：
Every imagery exploitation detector D is detected to obtain target location, positions and be partitioned into non-motor vehicle region and driving
Member region；
Model M is used to non-motor vehicle part1Unstructured feature F is calculated1, model M is used to driver part2
Unstructured feature F is calculated2, merge and obtain the unstructured feature F of overall goals；
By unstructured feature F insertion search libraries Θ.
The search method of non-motor vehicle in a kind of foregoing video, it is characterised in that step 2 includes：
For an image to be retrieved, detect to obtain target location using detector D, position and be partitioned into image to be retrieved
Middle non-motor vehicle region and driver region；
Model M is used to non-motor vehicle part in image to be retrieved1Unstructured feature f is calculated1, to driver portion
Divide and use model M2Unstructured feature f is calculated2, merge and obtain the unstructured feature f of image object to be retrieved.
The search method of non-motor vehicle in a kind of foregoing video, it is characterised in that step 3 includes：Calculate figure to be retrieved
As target unstructured feature f and search library Θ in the unstructured feature F of each target similarity, and to similarity knot
Fruit is ranked up, and the target sequences of corresponding ranking results are retrieval result.
The invention has the beneficial effects that：The present invention can effectively improve the tracking and investigation efficiency to non-motor vehicle；Carry
High retrieval rate；The data for making full use of public security camera to collect, improve the service efficiency of monitoring data, present invention reduces
Use cost, implementation and execution are very convenient.
Brief description of the drawings
Fig. 1 is the flow chart of non-motor vehicle search method in the embodiment of the present invention；
Fig. 2 is the particular flow sheet of the search method of non-motor vehicle in the embodiment of the present invention.
Embodiment
Make specific introduce to the present invention below in conjunction with the drawings and specific embodiments.
As shown in Figure 1, in a kind of video of the present invention non-motor vehicle search method, include the following steps：
Step 1：The image containing non-motor vehicle and driver in image library is obtained, by the non-motor vehicle in every image
With driver as a target, each target is calculated and extracts unstructured feature, by the unstructured spy of all targets
Sign insertion search library；
Step 2：For an image to be retrieved, the unstructured feature of target in the image to be retrieved is calculated and extracted；
Step 3：Calculate and image more to be retrieved in target and search library the unstructured feature of all targets phase
Like degree, sequencing of similarity is obtained, using sequencing of similarity as retrieval result.
As it can be seen that present invention employs with the different new technology of prior art principle, realized based on image and video data
Non-motor vehicle and the lookup of its driver and the function of retrieval.For the prior art, non-motor vehicle is not required to this technology
Bind any identification module, it is not required that establish monitoring point in the section for needing to detect, it is only necessary to set extensively using existing
The data collected of public security camera can be carried out the analysis and processing of data, and therefrom retrieve relevant non-motor vehicle and its
Driver, therefore the service efficiency of existing monitoring data is improved, the use cost of technology is on the other hand reduced, implements and holds
Row is very convenient.
In processing this part based on image, in general, what the target retrieval based on image used is mainly characterized by face
Color and texture, non-motor vehicle and its driver are under actual monitored scene due to information changes such as environment, posture, clothing and accessories
It is difficult for being matched and being retrieved to cause the color of target and general texture information.We are to non-motor vehicle and driving for this
Member is positioned and is split, and non-motor vehicle and driver is collected and is marked respectively great amount of samples, learned respectively using neutral net
Habit can describe non-motor vehicle and the unstructured feature of driver.The unstructured spy obtained by mass data repetitive exercise
Sign is obviously improved compared to the differentiation performance of general color and textural characteristics to target；To non-motor vehicle in itself and driver at the same time
Positioning and segmentation be capable of it is very effective reduce different target variance within clusters, improve retrieval and matching accuracy rate.
For expansion, in step 1 and step 2 of the present invention, calculate and extract unstructured feature and include the following steps：
Non-motor vehicle and driver in automatic detection and positioning image；
Position and be partitioned into non-motor vehicle region and driver region；
The unstructured feature of non-motor vehicle part and driver part is calculated respectively, and merging obtains the non-knot of a target
Structure feature.
Further, preferably, above-mentioned calculating and the unstructured feature of extraction include the following steps：Obtained according to training
Neural network model detects automatically and the non-motor vehicle in positioning image and driver；The neural network model obtained according to training
Position and be partitioned into non-motor vehicle region and driver region；The neural network model obtained according to training calculates non-maneuver respectively
Car part and the unstructured feature of driver part.
Here neural network model is proposed, the present invention does not limit the training method of the model, but preferably, trains
Neural network model includes the following steps：
The multiple images with target are collected, form image pattern collection；
Mark image pattern and concentrate non-motor vehicle and position of driver, and be divided into non-motor vehicle region and driver
Region；
Different non-motor vehicles and the class label of driver are marked, as markup information；
Training sample set N is formed by all image pattern collection and corresponding markup information；
Based on training sample set N, training obtains the inspection for detecting and positioning non-motor vehicle and driver in image automatically
Survey device D；
Based on training sample set N, it is respectively trained to obtain the model M for calculating the unstructured feature of non-motor vehicle1With with
In the model M for calculating the unstructured feature of driver2。
Illustrated with reference to an implementation.Non-motor vehicle of the present embodiment based on image and the retrieval side of its driver
A kind of embodiment of method, comprises the following steps that：
1st, collect the largely image pattern collection comprising non-motor vehicle and driver's target；Manually mark image pattern collection
In non-motor vehicle and position of driver, and be divided into two parts of non-motor vehicle and driver；Manually mark is different non-
Motor vehicle and the class label of driver, training sample set N is formed by all image pattern collection and corresponding markup information.
2nd, using deep learning theory and method, with reference to the training sample set N marked, training obtains that figure can be detected
Non-motor vehicle and the detector D of driver's target as in.
3rd, using deep learning theory and method, with reference to the training sample set N marked, being respectively trained to obtain to count
Calculate the model M of the unstructured feature of non-motor vehicle1With the model M for calculating the unstructured feature of driver2。
4th, every is needed to detect to obtain target location, positioning and segmentation as the imagery exploitation detector D in retrieval source
Go out non-motor vehicle region and driver region；Model M is used to non-motor vehicle part1Unstructured feature F is calculated1, to driving
The person of sailing part uses model M2Unstructured feature F is calculated2, merge and obtain the unstructured feature F of overall goals；
5th, by unstructured feature F insertion search libraries Θ.Specifically, i.e., all need are handled using the method in the 4th
All non-motor vehicles and the unstructured characteristic key storehouse Θ of driver's target are obtained as the image in retrieval source.
6th, to the image object of primary retrieval request, the unstructured spy of target to be retrieved is generated using method in the 4th
Levy f.Specifically, for an image to be retrieved, detect to obtain target location using detector D, position and be partitioned into and is to be checked
Non-motor vehicle region and driver region in rope image；Model M is used to non-motor vehicle part in image to be retrieved1It is calculated
Unstructured feature f1, model M is used to driver part2Unstructured feature f is calculated2, merge and obtain image to be retrieved
The unstructured feature f of target.
7th, calculate the unstructured spy of each target in unstructured the feature f and search library Θ of image object to be retrieved
The similarity of F is levied, and similarity result is ranked up, the target sequences of corresponding ranking results are retrieval result.
The present invention applies tracking and the investigation efficiency that in fields such as criminal investigation work, can be effectively improved to non-motor vehicle；This
Information of both people and Che are made full use of in inventive principle, improves retrieval rate；Make full use of what public security camera was collected
Data, improve the service efficiency of monitoring data, present invention reduces use cost, implementation and perform very convenient.
The basic principles, main features and advantages of the invention have been shown and described above.The technical staff of the industry should
Understand, the invention is not limited in any way for above-described embodiment, all to be obtained by the way of equivalent substitution or equivalent transformation
Technical solution, all falls within protection scope of the present invention.
Claims (7)
1. the search method of non-motor vehicle in a kind of video, it is characterised in that include the following steps：
Step 1：The image containing non-motor vehicle and driver in image library is obtained, by the non-motor vehicle in every image and is driven
The person of sailing calculates each target and extracts unstructured feature, the unstructured feature of all targets is inserted as a target
Enter search library；
Step 2：For an image to be retrieved, the unstructured feature of target in the image to be retrieved is calculated and extracted；
Step 3：Calculate and image more to be retrieved in target and search library the unstructured feature of all targets it is similar
Degree, obtains sequencing of similarity, using sequencing of similarity as retrieval result.
2. the search method of non-motor vehicle in video according to claim 1, it is characterised in that calculate and extract and is non-structural
Change feature to include the following steps：
Non-motor vehicle and driver in automatic detection and positioning image；
Position and be partitioned into non-motor vehicle region and driver region；
The unstructured feature of non-motor vehicle part and driver part is calculated respectively, is merged and is obtained the unstructured of target
Feature.
3. the search method of non-motor vehicle in video according to claim 2, it is characterised in that
The neural network model obtained according to training detects automatically and the non-motor vehicle in positioning image and driver；
The neural network model obtained according to training positions and is partitioned into non-motor vehicle region and driver region；
The neural network model obtained according to training calculates the unstructured feature of non-motor vehicle part and driver part respectively.
4. the search method of non-motor vehicle in video according to claim 3, it is characterised in that training neural network model
Include the following steps：
The multiple images with target are collected, form image pattern collection；
Mark image pattern and concentrate non-motor vehicle and position of driver, and be divided into non-motor vehicle region and driver area
Domain；
Different non-motor vehicles and the class label of driver are marked, in this, as markup information；
Training sample set N is formed by all image pattern collection and corresponding markup information；
Based on training sample set N, training is obtained for detecting and positioning non-motor vehicle and the detector of driver in image automatically
D；
Based on training sample set N, it is respectively trained to obtain the model M for calculating the unstructured feature of non-motor vehicle1With for calculating
The model M of the unstructured feature of driver2。
5. the search method of non-motor vehicle in video according to claim 4, it is characterised in that step 1 includes：
Every imagery exploitation detector D is detected to obtain target location, positions and be partitioned into non-motor vehicle region and driver area
Domain；Model M is used to non-motor vehicle part1Unstructured feature F is calculated1, model M is used to driver part2Calculate
To unstructured feature F2, merge and obtain the unstructured feature F of overall goals；
By unstructured feature F insertion search libraries Θ.
6. the search method of non-motor vehicle in video according to claim 4, it is characterised in that step 2 includes：
For an image to be retrieved, detect to obtain target location using detector D, position and be partitioned into and is non-in image to be retrieved
Motor vehicle region and driver region；
Model M is used to non-motor vehicle part in image to be retrieved1Unstructured feature f is calculated1, driver part is made
Use model M2Unstructured feature f is calculated2, merge and obtain the unstructured feature f of image object to be retrieved.
7. the search method of non-motor vehicle in a kind of video according to claim 4, it is characterised in that step 3 includes：
The similarity of the unstructured feature F of each target in unstructured the feature f and search library Θ of image object to be retrieved is calculated,
And similarity result is ranked up, the target sequences of corresponding ranking results are retrieval result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711308824.5A CN107944017B (en) | 2017-12-11 | 2017-12-11 | Method for searching non-motor vehicle in video |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711308824.5A CN107944017B (en) | 2017-12-11 | 2017-12-11 | Method for searching non-motor vehicle in video |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107944017A true CN107944017A (en) | 2018-04-20 |
| CN107944017B CN107944017B (en) | 2021-06-25 |
Family
ID=61946516
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711308824.5A Active CN107944017B (en) | 2017-12-11 | 2017-12-11 | Method for searching non-motor vehicle in video |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107944017B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110427814A (en) * | 2019-06-24 | 2019-11-08 | 深圳云天励飞技术有限公司 | A kind of bicyclist recognition methods, device and equipment again |
| CN110516518A (en) * | 2018-05-22 | 2019-11-29 | 杭州海康威视数字技术股份有限公司 | A kind of illegal manned detection method of non-motor vehicle, device and electronic equipment |
| CN111191561A (en) * | 2019-12-25 | 2020-05-22 | 北京迈格威科技有限公司 | Method, apparatus and computer storage medium for re-identification of non-motor vehicles |
| WO2020134839A1 (en) * | 2018-12-29 | 2020-07-02 | 深圳云天励飞技术有限公司 | Image searching method and apparatus |
| CN111898572A (en) * | 2020-08-05 | 2020-11-06 | 杭州云栖智慧视通科技有限公司 | Case intelligent serial-parallel method based on shape recognition |
| CN112347307A (en) * | 2020-09-17 | 2021-02-09 | 浙江大华技术股份有限公司 | Non-motor vehicle image retrieval method, device, system and storage medium |
| CN113190701A (en) * | 2021-05-07 | 2021-07-30 | 北京百度网讯科技有限公司 | Image retrieval method, device, equipment, storage medium and computer program product |
| CN114550492A (en) * | 2022-04-21 | 2022-05-27 | 深圳市龙光云众智慧科技有限公司 | Vehicle information processing method and device, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102156707A (en) * | 2011-02-01 | 2011-08-17 | 刘中华 | Video abstract forming and searching method and system |
| CN103824067A (en) * | 2014-03-18 | 2014-05-28 | 北京理工大学 | Method for positioning and identifying main objective in image |
| US20160350333A1 (en) * | 2015-05-29 | 2016-12-01 | Microsoft Technology Licensing, Llc | Task-focused search by image |
| CN106354735A (en) * | 2015-07-22 | 2017-01-25 | 杭州海康威视数字技术股份有限公司 | Image target searching method and device |
-
2017
- 2017-12-11 CN CN201711308824.5A patent/CN107944017B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102156707A (en) * | 2011-02-01 | 2011-08-17 | 刘中华 | Video abstract forming and searching method and system |
| CN103824067A (en) * | 2014-03-18 | 2014-05-28 | 北京理工大学 | Method for positioning and identifying main objective in image |
| US20160350333A1 (en) * | 2015-05-29 | 2016-12-01 | Microsoft Technology Licensing, Llc | Task-focused search by image |
| CN106354735A (en) * | 2015-07-22 | 2017-01-25 | 杭州海康威视数字技术股份有限公司 | Image target searching method and device |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110516518A (en) * | 2018-05-22 | 2019-11-29 | 杭州海康威视数字技术股份有限公司 | A kind of illegal manned detection method of non-motor vehicle, device and electronic equipment |
| WO2020134839A1 (en) * | 2018-12-29 | 2020-07-02 | 深圳云天励飞技术有限公司 | Image searching method and apparatus |
| CN110427814A (en) * | 2019-06-24 | 2019-11-08 | 深圳云天励飞技术有限公司 | A kind of bicyclist recognition methods, device and equipment again |
| CN111191561A (en) * | 2019-12-25 | 2020-05-22 | 北京迈格威科技有限公司 | Method, apparatus and computer storage medium for re-identification of non-motor vehicles |
| CN111898572A (en) * | 2020-08-05 | 2020-11-06 | 杭州云栖智慧视通科技有限公司 | Case intelligent serial-parallel method based on shape recognition |
| CN112347307A (en) * | 2020-09-17 | 2021-02-09 | 浙江大华技术股份有限公司 | Non-motor vehicle image retrieval method, device, system and storage medium |
| CN113190701A (en) * | 2021-05-07 | 2021-07-30 | 北京百度网讯科技有限公司 | Image retrieval method, device, equipment, storage medium and computer program product |
| CN114550492A (en) * | 2022-04-21 | 2022-05-27 | 深圳市龙光云众智慧科技有限公司 | Vehicle information processing method and device, electronic equipment and storage medium |
| CN114550492B (en) * | 2022-04-21 | 2022-08-05 | 深圳市龙光云众智慧科技有限公司 | Vehicle information processing method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107944017B (en) | 2021-06-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107944017A (en) | The search method of non-motor vehicle in a kind of video | |
| CN105702048B (en) | Highway front truck illegal road occupation identifying system based on automobile data recorder and method | |
| Vahab et al. | Applications of object detection system | |
| CN109977897A (en) | A kind of ship's particulars based on deep learning recognition methods, application method and system again | |
| CN103810717B (en) | A kind of human body behavioral value method and device | |
| CN106448160B (en) | Target person tracking method combining vehicle running track and monitoring video data | |
| CN103208190B (en) | Traffic flow detection method based on object detection | |
| CN111325048B (en) | Personnel gathering detection method and device | |
| CN106373406A (en) | Inspecting system against fake-licensed vehicles | |
| CN109829382B (en) | Abnormal target early warning tracking system and method based on intelligent behavior characteristic analysis | |
| CN102254394A (en) | Antitheft monitoring method for poles and towers in power transmission line based on video difference analysis | |
| CN102855508B (en) | Opening type campus anti-following system | |
| CN111353369A (en) | Application method and system of high-order video of urban roadside parking in assisting criminal investigation | |
| Šegvić et al. | A computer vision assisted geoinformation inventory for traffic infrastructure | |
| CN103390151A (en) | Face detection method and device | |
| Piciarelli et al. | Surveillance-oriented event detection in video streams | |
| CN113191273A (en) | Oil field well site video target detection and identification method and system based on neural network | |
| CN109934161A (en) | Vehicle identification and detection method and system based on convolutional neural network | |
| CN114241373A (en) | End-to-end vehicle behavior detection method, system, equipment and storage medium | |
| Sutjaritvorakul et al. | Simulation platform for crane visibility safety assistance | |
| Pinthong et al. | The License Plate Recognition system for tracking stolen vehicles | |
| CN112183164A (en) | Pedestrian attribute identification method under surveillance video | |
| CN110379173A (en) | A kind of Manpower Transportation unlawful practice recognition methods based on shared bicycle multi-modal data | |
| Tumrani et al. | PEVR: pose estimation for vehicle re-identification | |
| CN113392678A (en) | Pedestrian detection method, device and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230616 Address after: Room 802, Building 18, No. 998, Wenyi West Road, Wuchang Street, Yuhang District, Hangzhou City, Zhejiang Province, 310000 Patentee after: Zhejiang Lishi industrial Interconnection Technology Co.,Ltd. Address before: East Building, building 7, No. 998, Wenyi West Road, Wuchang Street, Yuhang District, Hangzhou City, Zhejiang Province 310000 Patentee before: ZHEJIANG ICARE VISION TECHNOLOGY Co.,Ltd. |
|
| TR01 | Transfer of patent right |