CN109086708A - A kind of parking space detection method and system based on deep learning - Google Patents
A kind of parking space detection method and system based on deep learning Download PDFInfo
- Publication number
- CN109086708A CN109086708A CN201810824584.2A CN201810824584A CN109086708A CN 109086708 A CN109086708 A CN 109086708A CN 201810824584 A CN201810824584 A CN 201810824584A CN 109086708 A CN109086708 A CN 109086708A
- Authority
- CN
- China
- Prior art keywords
- training
- parking
- deep learning
- parking space
- parking stall
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/56—Context or environment of the image exterior to a vehicle by using sensors mounted on the vehicle
- G06V20/58—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads
- G06V20/586—Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads of parking space
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biophysics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Evolutionary Biology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of parking space detection methods based on deep learning, comprising the following steps: obtains the target image on parking stall；The training set and test set of the parking stall target image are set；Label is arranged to interesting target region, marks the coordinate and classification of the target area；Initialize neural network parameter；The training set and label information are placed in the neural network and participate in training；Quantitative evaluation is carried out to training result.A kind of parking site detecting system based on deep learning, comprising: image collection module, initial setup module and Training Control module.The higher disadvantage of parking space's environmental requirement is treated in the traditional images method detection of its effective solution, adaptability is stronger, and perfectly it can detect and position treating the characteristic point of parking space in extreme circumstances, convenient for the automatic accurate parking contraposition of vehicle, it is good to have the advantages that robustness, while also improving user experience.It can be widely applied to parking stall identification field.
Description
Technical field
The present invention relates to parking stalls to detect identification field, specially the parking space detection method based on deep learning and is
System.
Background technique
For current standard parking stall design situation, driver parks and mainly determines vehicle and vehicle according to parking stall floor line
The relative positional relationship of position, but the deficiency that the prior art is poor there are environmental suitability for parking stall measure, such as parking stall graticule
Cause that image is fuzzy, parking stall earth background difference, parking stall there are reflective, vehicle-mounted camera are unfocused at insufficient light, graticule
The extreme environments such as line heterochromia, parking stall characteristic point to be detected be blocked, dirty and rainwater environment, traditional detection method will be examined
Dendrometry loses.
For these disadvantages, it is necessary to design a kind of new parking space detection method and system, realize that extreme environment waits for
The reliable detection of parking space's characteristic point.
Summary of the invention
The present invention is directed to solve at least some of the technical problems in related technologies.For this purpose, of the invention
One purpose is to provide that a kind of environmental suitability is strong, the good parking space detection method and system based on deep learning of robustness.
The technical scheme adopted by the invention is that:
The present invention provides a kind of parking space detection method based on deep learning, comprising the following steps:
Obtain the target image on parking stall；
The training set and test set of the parking stall target image are set；
Label is arranged to interesting target region, marks the coordinate and classification of the target area；
Initialize neural network parameter；
The training set and label information are placed in the neural network and participate in training；
Quantitative evaluation is carried out to training result.
As the improvement of the technical solution, the target area includes the corner and/or target point region on parking stall.
As the improvement of the technical solution, corner and/or the target point region rectangle frame on the parking stall are marked
Coordinate and classification.
Further, the information of the label includes length and width, depth and/or the label item name and/or label of image
The top left co-ordinate and lower right corner coordinate value of rectangle frame.
Further, the target image on parking stall is trained using batch.
Further, after training, quantitative evaluation is carried out to training result using test set；If training result meets
The training result is then put into and is applied by preset requirement；If training result is unsatisfactory for preset requirement, analyzes and modify related ginseng
Number, and continue to train.
On the other hand, the present invention also provides a kind of parking site detecting systems based on deep learning, comprising:
Image collection module obtains the target image on parking stall for executing step；
Initial setup module, the training set and test set that the parking stall target image is set for executing step；
Label is arranged to interesting target region, marks the coordinate and classification of the target area；
Initialize neural network parameter；
The training set and label information are placed in the neural network for executing step and participate in by Training Control module
Training；
Quantitative evaluation is carried out to training result.
The beneficial effects of the present invention are:
Parking space detection method and system provided by the invention based on deep learning, by obtaining target parking position figure
Picture, and the label of characteristic area is set；By the way that training set is arranged, repeatedly training, the standard until can achieve application.It is effectively
Solve traditional images method detection treat the higher disadvantage of parking space's environmental requirement, adaptability is stronger, and even if in pole
The characteristic point that parking space is treated under end ring border also perfectly can be detected and be positioned, and be aligned convenient for the automatic accurate parking of vehicle,
It is good to have the advantages that robustness, while also improving user experience.
Detailed description of the invention
Fig. 1 is the parking space detection method flow chart based on deep learning of one embodiment of the invention；
Fig. 2 is training and the cognitive phase schematic diagram of the deep learning of one embodiment of the invention；
Fig. 3 is the parking site detecting system schematic diagram based on deep learning of one embodiment of the invention；
Fig. 4 is the bicycle position feature schematic diagram of one embodiment of the invention.
Specific embodiment
It should be noted that in the absence of conflict, the features in the embodiments and the embodiments of the present application can phase
Mutually combination.
It referring to Fig.1, is the parking space detection method flow chart based on deep learning of one embodiment of the invention.The present invention mentions
For a kind of parking space detection method based on deep learning, comprising the following steps:
Obtain the target image on parking stall；
The training set and test set of the parking stall target image are set；
Label is arranged to interesting target region, marks the coordinate and classification of the target area；
Initialize neural network parameter；
The training set and label information are placed in the neural network and participate in training；
Quantitative evaluation is carried out to training result.
The training set test set on parking stall is made first, and label is made to particular region of interest；Then net is carried out
Network training, tests network parameter, judges whether test result is more excellent；If so, putting into practical application；If not most
It is excellent, then by trim network parameter and data set, network training is then carried out again, until meeting more excellent condition, can put into reality
In the application of border.
Specifically, it wherein the parking stall characteristic detection method for the embodiment trains deep learning network parameter, needs
Parking stall target image production training set and test set are acquired, and label, marker characteristic parking stall are done to interested target area
The coordinate and classification of feature angle point region rectangle frame；Then to the batch size of deep learning network training, initial study
The parameters such as rate and learning rate rule change are initialized；Send the training set pre-processed to the depth having had been built up
Neural network participates in training, and observes the situation of change of each parameter in training process.After training, training process is joined
Number carries out data analysis, determines and uses training result parameter, carries out quantitative evaluation to training result using test set afterwards, and according to this
Verifying collection, test set and video are handled in real time, whether judging result is more excellent, if meets requirement of experiment.If so, can be with
The training result is put into practical application；If it is not, the reason of analyzing output data, finding out shortcomings then is needed, adjusting parameter,
Or shortcoming then needs to modify on data set, then participates in network again in the production of training set
In training, until test result is more excellent, training result can just be put into application.
It is training and the cognitive phase schematic diagram of the deep learning of one embodiment of the invention referring to Fig. 2.The instruction of the present embodiment
Practicing target image is multiple parking stall corner images, and the training stage uses batch training method, reads a batch picture every time and makees
An iteration training is participated in for training data, corresponding picture tag also assists in the training of the batch；Wherein label information
(w, h, d, name, xmin, ymin, xmax, ymanx) including training picture, the i.e. length and width of picture, depth, label class name
Title (label in the present embodiment is divided into four classifications, is characteristic point L0, characteristic point L1, characteristic point R0, characteristic point R1 respectively),
Top left co-ordinate and lower right corner coordinate value of tab rectangle frame etc..Both above-mentioned data are sent into training in deep neural network,
Network parameter after saving lower training, is used for Qualify Phase and cognitive phase.In Qualify Phase and cognitive phase, network is read every time
Enter a picture, be sent into network, and exports and predict coming as a result, wherein result includes id, conf_prob, xmin, ymin,
The information such as xmax, ymanx, i.e. picture sequence numbers, the top left co-ordinate of confidence level and output result rectangle frame position, the lower right corner are sat
Mark.Training terminates, then carries out quantitative evaluation to training result using test set, and determines whether training result is more excellent according to this.If
It is that can then put into the training result in practical application；If it is not, the reason of analyzing output data, finding out shortcomings then is needed,
Adjusting parameter or shortcoming then need to modify on data set, then join again in the production of training set
With into network training, until test result is more excellent, training result can just be put into application.
Referring to Fig. 3, the present invention also provides a kind of parking site detecting systems based on deep learning, comprising:
Image collection module obtains the target image on parking stall for executing step；
Initial setup module, the training set and test set that the parking stall target image is set for executing step；
Label is arranged to interesting target region, marks the coordinate and classification of the target area；
Initialize neural network parameter；
The training set and label information are placed in the neural network for executing step and participate in by Training Control module
Training；
Quantitative evaluation is carried out to training result.
It is the bicycle position feature schematic diagram of one embodiment of the invention referring to Fig. 4, wherein garage design and traditional garage one
It causes, parking stall characteristic point is to be distributed in four corners on parking stall periphery, opposite according to the opening direction of characteristic point corner and parking stall line
Position feature is classified as four classifications, respectively by four feature corners of a parking stall be defined as characteristic point L0, characteristic point R0,
Characteristic point L1, characteristic point R1 detected four feature corners classifications using the deep learning method in the present invention respectively, and
If icon is remembered, and the centre coordinate of characteristic point is provided.Wherein, characteristic point L0, characteristic point R0 and r horizontal line have collectively constituted block 1；
Characteristic point L0, characteristic point L1 and c vertical line have collectively constituted block 2；Characteristic point L1, characteristic point R1 and r horizontal line have collectively constituted area
Block 3；Characteristic point R0, characteristic point R1 and c vertical line have collectively constituted block 4.By setting to parking stall characteristic information acquisition, study
Training set, and repeatedly train, the standard until can achieve practical application.
Parking space detection method and system provided by the invention based on deep learning, by obtaining target parking position figure
Picture, and the label of characteristic area is set；By the way that training set is arranged, repeatedly training, the standard until can achieve application.It is effectively
Solve traditional images method detection treat the higher disadvantage of parking space's environmental requirement, adaptability is stronger, and even if in pole
The characteristic point that parking space is treated under end ring border also perfectly can be detected and be positioned, and be aligned convenient for the automatic accurate parking of vehicle,
It is good to have the advantages that robustness, while also improving user experience.
It is to be illustrated to preferable implementation of the invention, but the invention is not limited to the implementation above
Example, those skilled in the art can also make various equivalent variations on the premise of without prejudice to spirit of the invention or replace
It changes, these equivalent deformations or replacement are all included in the scope defined by the claims of the present application.
Claims (7)
1. a kind of parking space detection method based on deep learning, which comprises the following steps:
Obtain the target image on parking stall；
The training set and test set of the parking stall target image are set；
Label is arranged to interesting target region, marks the coordinate and classification of the target area；
Initialize neural network parameter；
The training set and label information are placed in the neural network and participate in training；
Quantitative evaluation is carried out to training result.
2. the parking space detection method according to claim 1 based on deep learning, which is characterized in that the target area
Corner and/or target point region including parking stall.
3. the parking space detection method according to claim 2 based on deep learning, which is characterized in that mark the parking
The corner of position and/or the coordinate and classification of target point region rectangle frame.
4. the parking space detection method according to claim 3 based on deep learning, which is characterized in that the letter of the label
Breath includes that length and width, depth and/or the label item name of image and/or the top left co-ordinate of tab rectangle frame and the lower right corner are sat
Scale value.
5. the parking space detection method according to claim 1 based on deep learning, which is characterized in that the method packet
It includes: the target image on parking stall is trained using batch.
6. the parking space detection method according to any one of claims 1 to 5 based on deep learning, which is characterized in that institute
The method of stating includes: to carry out quantitative evaluation to training result using test set after training；If training result meets default want
It asks, then the training result is put into and applied；If training result is unsatisfactory for preset requirement, relevant parameter is analyzed and modifies, and
Continue to train.
7. a kind of parking site detecting system based on deep learning characterized by comprising
Image collection module obtains the target image on parking stall for executing step；
Initial setup module, the training set and test set that the parking stall target image is set for executing step；
Label is arranged to interesting target region, marks the coordinate and classification of the target area；
Initialize neural network parameter；
The training set and label information are placed in participation instruction in the neural network for executing step by Training Control module
Practice；
Quantitative evaluation is carried out to training result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810824584.2A CN109086708A (en) | 2018-07-25 | 2018-07-25 | A kind of parking space detection method and system based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810824584.2A CN109086708A (en) | 2018-07-25 | 2018-07-25 | A kind of parking space detection method and system based on deep learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109086708A true CN109086708A (en) | 2018-12-25 |
Family
ID=64838513
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810824584.2A Pending CN109086708A (en) | 2018-07-25 | 2018-07-25 | A kind of parking space detection method and system based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109086708A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109740584A (en) * | 2019-04-02 | 2019-05-10 | 纽劢科技(上海)有限公司 | Automatic parking parking space detection method based on deep learning |
| CN109800658A (en) * | 2018-12-26 | 2019-05-24 | 中汽研（天津）汽车工程研究院有限公司 | Parking position type online recognition neural network based and positioning system and method |
| CN110276287A (en) * | 2019-06-17 | 2019-09-24 | 百度在线网络技术（北京）有限公司 | Method for detecting parking stalls, device, computer equipment and storage medium |
| CN110310254A (en) * | 2019-05-17 | 2019-10-08 | 广东技术师范大学 | A kind of room angle image automatic grading method based on deep learning |
| CN110348297A (en) * | 2019-05-31 | 2019-10-18 | 纵目科技（上海）股份有限公司 | A kind of detection method, system, terminal and the storage medium of parking systems for identification |
| CN110705359A (en) * | 2019-09-05 | 2020-01-17 | 北京智行者科技有限公司 | Parking space detection method |
| CN111243024A (en) * | 2020-01-14 | 2020-06-05 | 上海钧正网络科技有限公司 | Parking area identification system and method, detection system and method and security system |
| CN111488977A (en) * | 2019-01-25 | 2020-08-04 | 北京地平线机器人技术研发有限公司 | Neural network model training method and device |
| CN112016349A (en) * | 2019-05-29 | 2020-12-01 | 北京市商汤科技开发有限公司 | Parking space detection method and device and electronic equipment |
| CN112349091A (en) * | 2019-08-07 | 2021-02-09 | 爱信精机株式会社 | Specific area detecting device |
| CN112417926A (en) * | 2019-08-22 | 2021-02-26 | 广州汽车集团股份有限公司 | Parking space identification method and device, computer equipment and readable storage medium |
| CN112464934A (en) * | 2020-12-08 | 2021-03-09 | 广州小鹏自动驾驶科技有限公司 | Parking space number detection method, device and equipment |
| CN113470416A (en) * | 2020-03-31 | 2021-10-01 | 上汽通用汽车有限公司 | System, method and storage medium for realizing parking space detection by using embedded system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140200970A1 (en) * | 2012-08-06 | 2014-07-17 | Cloudparc, Inc. | Controlling Use of Parking Spaces Using a Smart Sensor Network |
| CN105539430A (en) * | 2015-12-29 | 2016-05-04 | 北京理工大学 | Intelligent man-car interaction parking method based on hand-held terminal |
| CN105975941A (en) * | 2016-05-31 | 2016-09-28 | 电子科技大学 | Multidirectional vehicle model detection recognition system based on deep learning |
| CN106952308A (en) * | 2017-04-01 | 2017-07-14 | 上海蔚来汽车有限公司 | The location determining method and system of moving object |
| CN107067813A (en) * | 2017-06-14 | 2017-08-18 | 大连海事大学 | A kind of parking stall bootstrap technique and system based on image procossing and pattern-recognition |
| CN107424116A (en) * | 2017-07-03 | 2017-12-01 | 浙江零跑科技有限公司 | Position detecting method of parking based on side ring depending on camera |
| CN108052929A (en) * | 2017-12-29 | 2018-05-18 | 湖南乐泊科技有限公司 | Parking space state detection method, system, readable storage medium storing program for executing and computer equipment |
-
2018
- 2018-07-25 CN CN201810824584.2A patent/CN109086708A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140200970A1 (en) * | 2012-08-06 | 2014-07-17 | Cloudparc, Inc. | Controlling Use of Parking Spaces Using a Smart Sensor Network |
| CN105539430A (en) * | 2015-12-29 | 2016-05-04 | 北京理工大学 | Intelligent man-car interaction parking method based on hand-held terminal |
| CN105975941A (en) * | 2016-05-31 | 2016-09-28 | 电子科技大学 | Multidirectional vehicle model detection recognition system based on deep learning |
| CN106952308A (en) * | 2017-04-01 | 2017-07-14 | 上海蔚来汽车有限公司 | The location determining method and system of moving object |
| CN107067813A (en) * | 2017-06-14 | 2017-08-18 | 大连海事大学 | A kind of parking stall bootstrap technique and system based on image procossing and pattern-recognition |
| CN107424116A (en) * | 2017-07-03 | 2017-12-01 | 浙江零跑科技有限公司 | Position detecting method of parking based on side ring depending on camera |
| CN108052929A (en) * | 2017-12-29 | 2018-05-18 | 湖南乐泊科技有限公司 | Parking space state detection method, system, readable storage medium storing program for executing and computer equipment |
Non-Patent Citations (1)
| Title |
|---|
| 江浩斌: "基于信息融合的自动泊车系统车位智能识别", 《机械工程学报》 * |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109800658A (en) * | 2018-12-26 | 2019-05-24 | 中汽研（天津）汽车工程研究院有限公司 | Parking position type online recognition neural network based and positioning system and method |
| CN111488977A (en) * | 2019-01-25 | 2020-08-04 | 北京地平线机器人技术研发有限公司 | Neural network model training method and device |
| CN111488977B (en) * | 2019-01-25 | 2023-11-07 | 北京地平线机器人技术研发有限公司 | Neural network model training method and device |
| CN109740584B (en) * | 2019-04-02 | 2019-06-25 | 纽劢科技(上海)有限公司 | Automatic parking parking space detection method based on deep learning |
| CN109740584A (en) * | 2019-04-02 | 2019-05-10 | 纽劢科技(上海)有限公司 | Automatic parking parking space detection method based on deep learning |
| CN110310254A (en) * | 2019-05-17 | 2019-10-08 | 广东技术师范大学 | A kind of room angle image automatic grading method based on deep learning |
| WO2020238284A1 (en) * | 2019-05-29 | 2020-12-03 | 北京市商汤科技开发有限公司 | Parking space detection method and apparatus, and electronic device |
| CN112016349A (en) * | 2019-05-29 | 2020-12-01 | 北京市商汤科技开发有限公司 | Parking space detection method and device and electronic equipment |
| CN110348297A (en) * | 2019-05-31 | 2019-10-18 | 纵目科技（上海）股份有限公司 | A kind of detection method, system, terminal and the storage medium of parking systems for identification |
| CN110348297B (en) * | 2019-05-31 | 2023-12-26 | 纵目科技（上海）股份有限公司 | Detection method, system, terminal and storage medium for identifying stereo garage |
| CN110276287A (en) * | 2019-06-17 | 2019-09-24 | 百度在线网络技术（北京）有限公司 | Method for detecting parking stalls, device, computer equipment and storage medium |
| CN112349091A (en) * | 2019-08-07 | 2021-02-09 | 爱信精机株式会社 | Specific area detecting device |
| CN112417926A (en) * | 2019-08-22 | 2021-02-26 | 广州汽车集团股份有限公司 | Parking space identification method and device, computer equipment and readable storage medium |
| CN112417926B (en) * | 2019-08-22 | 2024-02-27 | 广州汽车集团股份有限公司 | Parking space identification method and device, computer equipment and readable storage medium |
| CN110705359A (en) * | 2019-09-05 | 2020-01-17 | 北京智行者科技有限公司 | Parking space detection method |
| CN110705359B (en) * | 2019-09-05 | 2023-03-03 | 北京智行者科技股份有限公司 | Parking space detection method |
| CN111243024A (en) * | 2020-01-14 | 2020-06-05 | 上海钧正网络科技有限公司 | Parking area identification system and method, detection system and method and security system |
| CN113470416A (en) * | 2020-03-31 | 2021-10-01 | 上汽通用汽车有限公司 | System, method and storage medium for realizing parking space detection by using embedded system |
| CN113470416B (en) * | 2020-03-31 | 2023-02-17 | 上汽通用汽车有限公司 | System, method and storage medium for realizing parking space detection by using embedded system |
| CN112464934A (en) * | 2020-12-08 | 2021-03-09 | 广州小鹏自动驾驶科技有限公司 | Parking space number detection method, device and equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109086708A (en) | A kind of parking space detection method and system based on deep learning | |
| CN108875911A (en) | One kind is parked position detecting method | |
| CN108806371B (en) | Intelligent judgment method and system based on driving test subject training | |
| CN106407875B (en) | Target's feature-extraction method and device | |
| CN105574543B (en) | A kind of vehicle brand type identifier method and system based on deep learning | |
| CN109800689A (en) | A kind of method for tracking target based on space-time characteristic fusion study | |
| CN105488454A (en) | Monocular vision based front vehicle detection and ranging method | |
| CN105046206B (en) | Based on the pedestrian detection method and device for moving prior information in video | |
| CN107657639A (en) | A kind of method and apparatus of quickly positioning target | |
| CN109521019A (en) | A kind of bridge bottom crack detection method based on unmanned plane vision | |
| CN101094413A (en) | Real time movement detection method in use for video monitoring | |
| CN106128115A (en) | A kind of fusion method based on twin camera detection Traffic Information | |
| CN105719318A (en) | Educational toy set and HSV based color identification method for Rubik's cube | |
| CN106297492B (en) | A kind of Educational toy external member and the method using color and outline identification programming module | |
| CN105741324A (en) | Moving object detection identification and tracking method on moving platform | |
| CN107452015A (en) | A kind of Target Tracking System with re-detection mechanism | |
| CN110309768A (en) | The staff's detection method and equipment of car test station | |
| CN102446355B (en) | Method for detecting target protruding from plane based on double viewing fields without calibration | |
| CN102214290B (en) | License plate positioning method and license plate positioning template training method | |
| CN112001219B (en) | Multi-angle multi-face recognition attendance checking method and system | |
| CN107480607A (en) | A kind of method that standing Face datection positions in intelligent recording and broadcasting system | |
| CN107491764A (en) | A kind of violation based on depth convolutional neural networks drives detection method | |
| CN109740654A (en) | A kind of tongue body automatic testing method based on deep learning | |
| CN106504262A (en) | A kind of small tiles intelligent locating method of multiple features fusion | |
| CN109800654A (en) | Vehicle-mounted camera detection processing method, apparatus and vehicle |
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: 20181225 |