CN105868691A - Urban vehicle tracking method based on rapid region convolutional neural network - Google Patents
Urban vehicle tracking method based on rapid region convolutional neural network Download PDFInfo
- Publication number
- CN105868691A CN105868691A CN201610148321.5A CN201610148321A CN105868691A CN 105868691 A CN105868691 A CN 105868691A CN 201610148321 A CN201610148321 A CN 201610148321A CN 105868691 A CN105868691 A CN 105868691A
- Authority
- CN
- China
- Prior art keywords
- convolutional neural
- vehicle
- neural networks
- training
- search
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
- G06V20/42—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items of sport video content
-
- 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
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention provides an urban vehicle tracking method based on a rapid region convolutional neural network. The tracking method comprises: marking a to-be-tracked vehicle in a monitoring video; inputting the to-be-tracked vehicle to a neural network for a rapid training so as to obtain a model; judging whether the vehicle appears at the crossing by identifying the road monitoring video; marking positions of all cameras detecting the vehicle on a map; and connecting the positions according to time sequence so as to obtain a travelling trace of the vehicle. Thus, by use of the history trace of the vehicle, the travelling direction of the vehicle can be predicted and the position of the vehicle in the city can be found in a short time.
Description
Technical field
The present invention relates to image procossing, machine learning field, be specifically related to a kind of based on fast area convolution god
City vehicle method for tracing through network.
Background technology
In VS recognition methods, typically all carry out moving object segmentation, after background removal, obtain institute
Some moving object, is identified each moving object.This method is simply effective, but in video
If moving object is more, environment is more complicated, and this method will be interfered, and accuracy rate is relatively low.
In image object detection method, region convolutional neural networks effect is fine, and this method first obtains very
Multiple target assumes region, is then identified all of goal hypothesis region.But due to a pictures target
Assuming that region great majority are overlapping, cause substantial amounts of computing repeatedly, therefore the algorithm speed of service is relatively slow,
Inefficient, it is not suitable for Video processing.
During the training of neutral net, all have employed the mode that GPU accelerates, this mode compares CPU
The fast hundred times of mode, however, still needs several hours for catenet training, the training time
The longest tracking degree of difficulty is the highest, and this is the most inapplicable for the demand of training network model within the shortest time,
In the case of algorithm is constant, using GPU cluster training pattern is best solution.
Summary of the invention
For solving shortcoming and defect of the prior art, the present invention proposes a kind of based on fast area convolution god
Through the city vehicle method for tracing of network, set up fast area convolutional neural networks, and use bigger data
Collection carries out pre-training, demarcates vehicle to be followed the trail of in video, is entered into training network in neutral net
Model, uses the network model trained to scan in the search radius of prediction, once finds this vehicle,
Just use and continue to follow the trail of vehicle by the mode of route search.
The technical scheme is that and be achieved in that:
A kind of city vehicle method for tracing based on fast area convolutional neural networks, including network training and car
Follow the trail of two processes；
In network training process, set up a kind of fast area convolutional neural networks；
During car tracing, use by half path search and the mode that combines by route search；
Obtain pre-training model by pre-training, monitor video marks vehicle to be followed the trail of, is inputted
In fast area convolutional neural networks, pre-training model is adjusted, quickly obtains final mask；
Then use and follow the trail of vehicle by radius and the mode combined by route search, map marks all discoveries
The position of this vehicle, connects sequentially in time, obtains vehicle driving trace, according to the pre-measuring car of driving trace
The position that will arrive.
Alternatively, in network training process, set up a kind of fast area convolutional neural networks, concrete steps
For:
(11) set up complete convolutional neural networks, input an image in complete convolutional neural networks, at volume
Last layer long-pending obtains characteristic pattern；
(12) the characteristic pattern enterprising line slip scanning obtained in last convolution, the network of slip is every time and feature
On figure, the window of n*n connects entirely, is then mapped to a low dimensional vector；
(13) described low dimensional vector is finally sent to two full articulamentums, i.e. box returns layer and box divides
Class layer.
Alternatively, during car tracing, use by half path search and the mode that combines by route search,
Concretely comprise the following steps:
(21) after training network model and obtaining final mask, pass through the consumed time and work as Front St
District's speed situation, it was predicted that the maximum distance that vehicle can travel, determines search radius, enters in search radius
Line search；
(22) in search radius, once find this vehicle, with this crossing as initial point, diffuse to this crossing energy
All crossings of enough connections, continue search for the monitor video at these crossings.
Alternatively, in the training stage of neural network model, Spark cluster is trained neutral net.
Alternatively, use Spark cluster to be trained, concretely comprise the following steps:
(31) use bigger, general data set to carry out pre-training, initialize the weight of neutral net；
(32) demarcate vehicle to be followed the trail of, be input in neutral net, the model of pre-training is adjusted
Whole, quickly obtain final model.
Alternatively, directly use existing convolutional neural networks, add up-samples, of parameter at end
Practise the backpropagation principle utilizing convolutional neural networks itself.
The invention has the beneficial effects as follows:
(1) convolutional neural networks learns good feature automatically, and accuracy rate is the highest, avoids people simultaneously
The limitation of work selected characteristic, decreases the manual operation of complexity, adapts to ability higher；
(2) identifying that aspect is chosen in region, be different from moving object segmentation, the method is to find video image
In all possible object be identified rather than the object of all motions, also can have under complex environment
Well adapt to ability；
(3) in Spark cluster, train neutral net, increase substantially training speed, can be the shortest
Final training pattern is obtained in time；
(4) employing is scanned for by radius and the mode combined by route, can search for targetedly
Possible region, reduces unnecessary work；
(5) convolutional neural networks can input the picture of arbitrary size completely, it is not necessary to enters video resolution
Row sum-equal matrix, it is easier to all of monitor video of adaptation.
Accompanying drawing explanation
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, below will be to enforcement
In example or description of the prior art, the required accompanying drawing used is briefly described, it should be apparent that, describe below
In accompanying drawing be only some embodiments of the present invention, for those of ordinary skill in the art, do not paying
On the premise of going out creative work, it is also possible to obtain other accompanying drawing according to these accompanying drawings.
Fig. 1 is the flow chart of present invention city vehicle based on fast area convolutional neural networks method for tracing；
Fig. 2 is fast area convolutional neural networks structure chart of the present invention.
Detailed description of the invention
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clearly
Chu, be fully described by, it is clear that described embodiment be only a part of embodiment of the present invention rather than
Whole embodiments.Based on the embodiment in the present invention, those of ordinary skill in the art are not making creation
The every other embodiment obtained under property work premise, broadly falls into the scope of protection of the invention.
Chase after as it is shown in figure 1, the present invention proposes a kind of city vehicle based on fast area convolutional neural networks
Track method, is divided into network training and two processes of car tracing.
In network training process, set up a kind of fast area convolutional neural networks, as in figure 2 it is shown, specifically
Step is:
(11) set up complete convolutional neural networks, input an image in complete convolutional neural networks, at volume
Last layer long-pending obtains characteristic pattern；
(12) the characteristic pattern enterprising line slip scanning that a little network obtains is used in last convolution, this
The network slided is connected with the window of n*n on characteristic pattern every time entirely, and usual n value is 3, is then mapped to one
Individual low dimensional vector；
(13) this low dimensional vector is finally sent to two full articulamentums, i.e. box returns layer and box divides
Class layer.
During car tracing, use by half path search with by the mode that route search combines, specifically walk
Suddenly it is:
(21) after training network model, consumed time and current block speed situation are passed through,
The maximum distance that prediction vehicle can travel, determines search radius, scans in this search radius；
(22) in search radius, once find this vehicle, with this crossing as initial point, diffuse to this crossing energy
All crossings of enough connections, continue search for the monitor video at these crossings.
The method of the present invention sets up fast area convolutional neural networks, uses bigger data set to carry out pre-training
Obtain pre-training model, monitor video mark vehicle to be followed the trail of, is entered in neutral net,
Pre-training model is adjusted, quickly obtains final mask.Then use and press radius and by route search
The mode combined follows the trail of vehicle, marks the position of all this vehicles of discovery, sequentially in time on map
Connect, it is possible to obtain vehicle driving trace, and can predict what vehicle will arrive according to driving trace
Position.
The method of the present invention directly uses existing convolutional neural networks, adds up-samples, parameter at end
Study utilize the backpropagation principle of convolutional neural networks itself.
Preferably, in the training stage of neural network model, Spark cluster is trained neutral net, specifically
Step is:
(31) use bigger, general data set to carry out pre-training, initialize the weight of neutral net；
(32) demarcate vehicle to be followed the trail of, be input in neutral net, the model of pre-training is adjusted
Whole, quickly obtain final model.
Present invention city vehicle based on fast area convolutional neural networks method for tracing, sets up fast area volume
Long-pending neutral net, will produce goal hypothesis region, identify in object two Process fusions to the network of region,
Not only reduce red tape, also speeded up the speed of service so that it is real-time video analysis can be carried out；Press
Half path search and combining by the mode of route search, can search target vehicle more efficiently；?
Spark cluster is trained neutral net, increases substantially training speed, within the shortest time, complete training,
Improve the success rate of search.
The present invention can be tracked for the hit-and-run vehicle in city, cannot determine car plate is covered
In the case of information of vehicles, according to the resemblance of vehicle, train neutral net, analyze the prison at each crossing
Control video, is accurately positioned escape vehicle, and this method saves substantial amounts of manual labor, it is to avoid owing to seeing
The person's of examining fatigue is omitted vehicle and is occurred that picture loses the situation of target, and convolutional neural networks accuracy rate is the highest,
In the case of a crossing multi-frame video image recognition, it is ensured that identify this vehicle.
The foregoing is only presently preferred embodiments of the present invention, not in order to limit the present invention, all at this
Within bright spirit and principle, any modification, equivalent substitution and improvement etc. made, should be included in this
Within bright protection domain.
Claims (6)
1. a city vehicle method for tracing based on fast area convolutional neural networks, its feature is, bag
Include network training and two processes of car tracing；
In network training process, set up a kind of fast area convolutional neural networks；
During car tracing, use by half path search and the mode that combines by route search；
Obtain pre-training model by pre-training, monitor video marks vehicle to be followed the trail of, is inputted
In fast area convolutional neural networks, pre-training model is adjusted, quickly obtains final mask；
Then use and follow the trail of vehicle by radius and the mode combined by route search, map marks all discoveries
The position of this vehicle, connects sequentially in time, obtains vehicle driving trace, according to the pre-measuring car of driving trace
The position that will arrive.
2. city vehicle method for tracing based on fast area convolutional neural networks as claimed in claim 1,
Its feature is, in network training process, sets up a kind of fast area convolutional neural networks, concrete steps
For:
(11) set up complete convolutional neural networks, input an image in complete convolutional neural networks, at volume
Last layer long-pending obtains characteristic pattern；
(12) the characteristic pattern enterprising line slip scanning obtained in last convolution, the network of slip is every time and feature
On figure, the window of n*n connects entirely, is then mapped to a low dimensional vector；
(13) described low dimensional vector is finally sent to two full articulamentums, i.e. box returns layer and box divides
Class layer.
3. city vehicle method for tracing based on fast area convolutional neural networks as claimed in claim 1,
Its feature is, during car tracing, uses by half path search and the mode that combines by route search,
Concretely comprise the following steps:
(21) after training network model and obtaining final mask, pass through the consumed time and work as Front St
District's speed situation, it was predicted that the maximum distance that vehicle can travel, determines search radius, enters in search radius
Line search；
(22) in search radius, once find this vehicle, with this crossing as initial point, diffuse to this crossing energy
All crossings of enough connections, continue search for the monitor video at these crossings.
4. city vehicle method for tracing based on fast area convolutional neural networks as claimed in claim 2,
Its feature is, in the training stage of neural network model, trains neutral net on Spark cluster.
5. city vehicle method for tracing based on fast area convolutional neural networks as claimed in claim 4,
Its feature is, uses Spark cluster to be trained, concretely comprises the following steps:
(31) use bigger, general data set to carry out pre-training, initialize the weight of neutral net；
(32) demarcate vehicle to be followed the trail of, be input in neutral net, the model of pre-training is adjusted
Whole, quickly obtain final model.
6. city vehicle method for tracing based on fast area convolutional neural networks as claimed in claim 2,
Its feature is, directly uses existing convolutional neural networks, adds up-samples, of parameter at end
Practise the backpropagation principle utilizing convolutional neural networks itself.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610148321.5A CN105868691B (en) | 2016-03-08 | 2016-03-08 | City vehicle method for tracing based on fast area convolutional neural networks |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610148321.5A CN105868691B (en) | 2016-03-08 | 2016-03-08 | City vehicle method for tracing based on fast area convolutional neural networks |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105868691A true CN105868691A (en) | 2016-08-17 |
| CN105868691B CN105868691B (en) | 2019-05-21 |
Family
ID=56624732
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610148321.5A Active CN105868691B (en) | 2016-03-08 | 2016-03-08 | City vehicle method for tracing based on fast area convolutional neural networks |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105868691B (en) |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106372571A (en) * | 2016-08-18 | 2017-02-01 | 宁波傲视智绘光电科技有限公司 | Road traffic sign detection and identification method |
| CN106709936A (en) * | 2016-12-14 | 2017-05-24 | 北京工业大学 | Single target tracking method based on convolution neural network |
| CN106971563A (en) * | 2017-04-01 | 2017-07-21 | 中国科学院深圳先进技术研究院 | Intelligent traffic lamp control method and system |
| CN107092883A (en) * | 2017-04-20 | 2017-08-25 | 上海极链网络科技有限公司 | Object identification method for tracing |
| CN107316463A (en) * | 2017-07-07 | 2017-11-03 | 深圳市诺龙技术股份有限公司 | A kind of method and apparatus of vehicle monitoring |
| CN107609633A (en) * | 2017-05-03 | 2018-01-19 | 同济大学 | The position prediction model construction method of vehicle traveling influence factor based on deep learning in car networking complex network |
| CN107665355A (en) * | 2017-09-27 | 2018-02-06 | 重庆邮电大学 | A kind of agricultural pests detection method based on region convolutional neural networks |
| CN107730905A (en) * | 2017-06-13 | 2018-02-23 | 银江股份有限公司 | Multitask fake license plate vehicle vision detection system and method based on depth convolutional neural networks |
| CN107944390A (en) * | 2017-11-24 | 2018-04-20 | 西安科技大学 | Motor-driven vehicle going objects in front video ranging and direction localization method |
| CN108765978A (en) * | 2018-04-27 | 2018-11-06 | 榛硕（武汉）智能科技有限公司 | A kind of novel speed early warning system |
| CN108960330A (en) * | 2018-07-09 | 2018-12-07 | 西安电子科技大学 | Remote sensing images semanteme generation method based on fast area convolutional neural networks |
| CN109061705A (en) * | 2018-06-27 | 2018-12-21 | 千寻位置网络有限公司 | Data processing method and terminal, Differential positioning platform based on tensorflow |
| CN109376572A (en) * | 2018-08-09 | 2019-02-22 | 同济大学 | Real-time vehicle detection and trace tracking method in traffic video based on deep learning |
| CN109829936A (en) * | 2019-01-29 | 2019-05-31 | 青岛海信网络科技股份有限公司 | A kind of method and apparatus of target tracking |
| CN109891897A (en) * | 2016-10-27 | 2019-06-14 | 诺基亚技术有限公司 | Method for analyzing media content |
| CN110321949A (en) * | 2019-06-29 | 2019-10-11 | 天津大学 | A kind of distributed car tracing method and system based on observed terminals network |
| CN110517495A (en) * | 2019-09-05 | 2019-11-29 | 四川东方网力科技有限公司 | Confirmation method, device, equipment and the storage medium of track of vehicle classification |
| CN110633707A (en) * | 2018-06-21 | 2019-12-31 | 北京京东尚科信息技术有限公司 | Method and device for predicting speed |
| CN110852243A (en) * | 2019-11-06 | 2020-02-28 | 中国人民解放军战略支援部队信息工程大学 | Improved YOLOv 3-based road intersection detection method and device |
| CN110889318A (en) * | 2018-09-05 | 2020-03-17 | 斯特拉德视觉公司 | Lane detection method and apparatus using CNN |
| US10600208B2 (en) | 2017-12-21 | 2020-03-24 | Industrial Technology Research Institute | Object detecting device, object detecting method and non-transitory computer-readable medium |
| CN111386561A (en) * | 2018-10-05 | 2020-07-07 | 松下电器（美国）知识产权公司 | Information processing method and information processing system |
| CN111754785A (en) * | 2020-07-03 | 2020-10-09 | 重庆智者炎麒科技有限公司 | Specific vehicle identification and tracking method |
| CN111746557A (en) * | 2019-03-26 | 2020-10-09 | 通用汽车环球科技运作有限责任公司 | Path planning fusion for vehicles |
| CN112863186A (en) * | 2021-01-18 | 2021-05-28 | 南京信息工程大学 | Vehicle-mounted unmanned aerial vehicle-based escaping vehicle rapid identification and tracking method |
| CN116504068A (en) * | 2023-06-26 | 2023-07-28 | 创辉达设计股份有限公司江苏分公司 | Statistical method, device, computer equipment and storage medium for lane-level traffic flow |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2398976A (en) * | 2003-02-28 | 2004-09-01 | Samsung Electronics Co Ltd | Neural network decoder for convolutionally-coded data |
| CN102567380A (en) * | 2010-12-28 | 2012-07-11 | 沈阳聚德视频技术有限公司 | Method for searching vehicle information in video image |
| CN103985257A (en) * | 2014-05-14 | 2014-08-13 | 南通大学 | Intelligent traffic video analysis method |
| CN104036323A (en) * | 2014-06-26 | 2014-09-10 | 叶茂 | Vehicle detection method based on convolutional neural network |
| CN105184271A (en) * | 2015-09-18 | 2015-12-23 | 苏州派瑞雷尔智能科技有限公司 | Automatic vehicle detection method based on deep learning |
-
2016
- 2016-03-08 CN CN201610148321.5A patent/CN105868691B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2398976A (en) * | 2003-02-28 | 2004-09-01 | Samsung Electronics Co Ltd | Neural network decoder for convolutionally-coded data |
| CN102567380A (en) * | 2010-12-28 | 2012-07-11 | 沈阳聚德视频技术有限公司 | Method for searching vehicle information in video image |
| CN103985257A (en) * | 2014-05-14 | 2014-08-13 | 南通大学 | Intelligent traffic video analysis method |
| CN104036323A (en) * | 2014-06-26 | 2014-09-10 | 叶茂 | Vehicle detection method based on convolutional neural network |
| CN105184271A (en) * | 2015-09-18 | 2015-12-23 | 苏州派瑞雷尔智能科技有限公司 | Automatic vehicle detection method based on deep learning |
Non-Patent Citations (1)
| Title |
|---|
| 卢宏涛 张秦川: ""深度卷积神经网络在计算机视觉中的应用研究综述"", 《数据采集与处理》 * |
Cited By (38)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106372571A (en) * | 2016-08-18 | 2017-02-01 | 宁波傲视智绘光电科技有限公司 | Road traffic sign detection and identification method |
| CN109891897B (en) * | 2016-10-27 | 2021-11-05 | 诺基亚技术有限公司 | Method for analyzing media content |
| CN109891897A (en) * | 2016-10-27 | 2019-06-14 | 诺基亚技术有限公司 | Method for analyzing media content |
| US11068722B2 (en) | 2016-10-27 | 2021-07-20 | Nokia Technologies Oy | Method for analysing media content to generate reconstructed media content |
| CN106709936A (en) * | 2016-12-14 | 2017-05-24 | 北京工业大学 | Single target tracking method based on convolution neural network |
| CN106971563A (en) * | 2017-04-01 | 2017-07-21 | 中国科学院深圳先进技术研究院 | Intelligent traffic lamp control method and system |
| CN106971563B (en) * | 2017-04-01 | 2020-05-19 | 中国科学院深圳先进技术研究院 | Intelligent traffic signal lamp control method and system |
| CN107092883A (en) * | 2017-04-20 | 2017-08-25 | 上海极链网络科技有限公司 | Object identification method for tracing |
| CN107609633A (en) * | 2017-05-03 | 2018-01-19 | 同济大学 | The position prediction model construction method of vehicle traveling influence factor based on deep learning in car networking complex network |
| CN107609633B (en) * | 2017-05-03 | 2020-08-14 | 同济大学 | Method for constructing position prediction model of vehicle driving influence factors based on deep learning in Internet of vehicles complex network |
| CN107730905A (en) * | 2017-06-13 | 2018-02-23 | 银江股份有限公司 | Multitask fake license plate vehicle vision detection system and method based on depth convolutional neural networks |
| CN107316463A (en) * | 2017-07-07 | 2017-11-03 | 深圳市诺龙技术股份有限公司 | A kind of method and apparatus of vehicle monitoring |
| CN107665355A (en) * | 2017-09-27 | 2018-02-06 | 重庆邮电大学 | A kind of agricultural pests detection method based on region convolutional neural networks |
| CN107944390B (en) * | 2017-11-24 | 2018-08-24 | 西安科技大学 | Motor-driven vehicle going objects in front video ranging and direction localization method |
| CN107944390A (en) * | 2017-11-24 | 2018-04-20 | 西安科技大学 | Motor-driven vehicle going objects in front video ranging and direction localization method |
| US10600208B2 (en) | 2017-12-21 | 2020-03-24 | Industrial Technology Research Institute | Object detecting device, object detecting method and non-transitory computer-readable medium |
| CN108765978A (en) * | 2018-04-27 | 2018-11-06 | 榛硕（武汉）智能科技有限公司 | A kind of novel speed early warning system |
| CN110633707A (en) * | 2018-06-21 | 2019-12-31 | 北京京东尚科信息技术有限公司 | Method and device for predicting speed |
| CN109061705B (en) * | 2018-06-27 | 2022-07-12 | 千寻位置网络有限公司 | Data processing method and terminal based on tensoflow and differential positioning platform |
| CN109061705A (en) * | 2018-06-27 | 2018-12-21 | 千寻位置网络有限公司 | Data processing method and terminal, Differential positioning platform based on tensorflow |
| CN108960330B (en) * | 2018-07-09 | 2021-09-10 | 西安电子科技大学 | Remote sensing image semantic generation method based on fast regional convolutional neural network |
| CN108960330A (en) * | 2018-07-09 | 2018-12-07 | 西安电子科技大学 | Remote sensing images semanteme generation method based on fast area convolutional neural networks |
| CN109376572B (en) * | 2018-08-09 | 2022-05-03 | 同济大学 | Real-time vehicle detection and trajectory tracking method in traffic video based on deep learning |
| CN109376572A (en) * | 2018-08-09 | 2019-02-22 | 同济大学 | Real-time vehicle detection and trace tracking method in traffic video based on deep learning |
| CN110889318A (en) * | 2018-09-05 | 2020-03-17 | 斯特拉德视觉公司 | Lane detection method and apparatus using CNN |
| CN110889318B (en) * | 2018-09-05 | 2024-01-19 | 斯特拉德视觉公司 | Lane detection method and device using CNN |
| CN111386561A (en) * | 2018-10-05 | 2020-07-07 | 松下电器（美国）知识产权公司 | Information processing method and information processing system |
| CN109829936B (en) * | 2019-01-29 | 2021-12-24 | 青岛海信网络科技股份有限公司 | Target tracking method and device |
| CN109829936A (en) * | 2019-01-29 | 2019-05-31 | 青岛海信网络科技股份有限公司 | A kind of method and apparatus of target tracking |
| CN111746557B (en) * | 2019-03-26 | 2024-03-29 | 通用汽车环球科技运作有限责任公司 | Path plan fusion for vehicles |
| CN111746557A (en) * | 2019-03-26 | 2020-10-09 | 通用汽车环球科技运作有限责任公司 | Path planning fusion for vehicles |
| CN110321949B (en) * | 2019-06-29 | 2023-05-05 | 天津大学 | Distributed vehicle tracking method and system based on observation terminal network |
| CN110321949A (en) * | 2019-06-29 | 2019-10-11 | 天津大学 | A kind of distributed car tracing method and system based on observed terminals network |
| CN110517495A (en) * | 2019-09-05 | 2019-11-29 | 四川东方网力科技有限公司 | Confirmation method, device, equipment and the storage medium of track of vehicle classification |
| CN110852243A (en) * | 2019-11-06 | 2020-02-28 | 中国人民解放军战略支援部队信息工程大学 | Improved YOLOv 3-based road intersection detection method and device |
| CN111754785A (en) * | 2020-07-03 | 2020-10-09 | 重庆智者炎麒科技有限公司 | Specific vehicle identification and tracking method |
| CN112863186A (en) * | 2021-01-18 | 2021-05-28 | 南京信息工程大学 | Vehicle-mounted unmanned aerial vehicle-based escaping vehicle rapid identification and tracking method |
| CN116504068A (en) * | 2023-06-26 | 2023-07-28 | 创辉达设计股份有限公司江苏分公司 | Statistical method, device, computer equipment and storage medium for lane-level traffic flow |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105868691B (en) | 2019-05-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105868691A (en) | Urban vehicle tracking method based on rapid region convolutional neural network | |
| CN104751634B (en) | The integrated application method of freeway tunnel driving image acquisition information | |
| WO2018153304A1 (en) | Map road mark and road quality collection apparatus and method based on adas system | |
| CN110532896A (en) | A kind of road vehicle detection method merged based on trackside millimetre-wave radar and machine vision | |
| CN105185118B (en) | A kind of vehicles peccancy detection means and its method based on video detection | |
| CN106919978A (en) | A kind of high ferro contact net support meanss parts recognition detection method | |
| CN109460709A (en) | The method of RTG dysopia analyte detection based on the fusion of RGB and D information | |
| CN108537197A (en) | A kind of lane detection prior-warning device and method for early warning based on deep learning | |
| CN105488454A (en) | Monocular vision based front vehicle detection and ranging method | |
| CN108230254A (en) | A kind of full lane line automatic testing method of the high-speed transit of adaptive scene switching | |
| CN108198417B (en) | A kind of road cruising inspection system based on unmanned plane | |
| CN106096504A (en) | A kind of model recognizing method based on unmanned aerial vehicle onboard platform | |
| CN107909012B (en) | Real-time vehicle tracking detection method and device based on disparity map | |
| CN111564015A (en) | Method and device for monitoring perimeter intrusion of rail transit | |
| CN108804539A (en) | A kind of track method for detecting abnormality under time and space double-visual angle | |
| CN110197494A (en) | A kind of pantograph contact point real time detection algorithm based on monocular infrared image | |
| CN105069451A (en) | License plate identifying and positioning method based on binocular camera | |
| CN113450573A (en) | Traffic monitoring method and traffic monitoring system based on unmanned aerial vehicle image recognition | |
| CN104463104B (en) | A kind of stationary vehicle target rapid detection method and device | |
| CN111444916A (en) | License plate positioning and identifying method and system under unconstrained condition | |
| CN103605960B (en) | A kind of method for identifying traffic status merged based on different focal video image | |
| CN112926425B (en) | Road state detection method, device and equipment | |
| CN112507867B (en) | Lane line detection method based on EDLines line characteristics | |
| CN115223107A (en) | Detection method for fit moving target detection frame | |
| CN115965926B (en) | Vehicle-mounted road sign marking inspection system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20190412 Address after: 266000 room 2107, building 2, exhibition hall, 1777 Binhai Road, Huangdao District, Qingdao, Shandong. Applicant after: Qingdao Sui Zhi Information technologies Co.,Ltd. Address before: 266000 No. 66 Changjiang West Road, Qingdao economic and Technological Development Zone, Shandong Applicant before: CHINA University OF PETROLEUM (EAST CHINA) |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20220701 Address after: 266000 No. 500, Wangjiang Road, Huangdao District, Qingdao, Shandong Patentee after: QINGDAO WINDAKA TECHNOLOGY Co.,Ltd. Address before: 266000 room 2107, building 2, exhibition hall, 1777 Binhai Road, Huangdao District, Qingdao, Shandong. Patentee before: Qingdao Sui Zhi Information technologies Co.,Ltd. |
|
| TR01 | Transfer of patent right |