CN102902951A - System and method for vehicle target location and event detection on basis of high-definition video monitoring images - Google Patents
System and method for vehicle target location and event detection on basis of high-definition video monitoring images Download PDFInfo
- Publication number
- CN102902951A CN102902951A CN2012102229529A CN201210222952A CN102902951A CN 102902951 A CN102902951 A CN 102902951A CN 2012102229529 A CN2012102229529 A CN 2012102229529A CN 201210222952 A CN201210222952 A CN 201210222952A CN 102902951 A CN102902951 A CN 102902951A
- Authority
- CN
- China
- Prior art keywords
- vehicle target
- image
- video monitoring
- definition video
- detection area
- 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
Images
Landscapes
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a system and a method for vehicle target location and event detection on the basis of high-definition video monitoring images. The system comprises a high-definition video monitoring image enhancing processing module, a vehicle target quick detection location module, a setting detection area grayscale image binarization processing module, a vehicle target and traveling track image gradient correction module, a vehicle target traveling track tracking and event feature extraction module and a vehicle target event detection and credibility assessment module. Compared with the prior art, the system and the method have the advantages of fine vehicle target quick location and intelligent analysis under the background of complex high-definition (more than two million pixels) video monitoring, fine high-definition video monitoring image enhancing processing effect, wide dynamic range, high vehicle target quick location and intelligent analysis (event detection) precision and low false report rate under the condition of uneven illumination. By the aid of the embedded system, credibility, reliability and stability of the software can be greatly improved, and difficulty in parameter setting of the front-end embedded system is lowered.
Description
Technical field
The present invention relates to a kind of can be used under public safety, parking management, intelligent transportation, the comprehensive complicated monitoring scene in field such as emergent based on the vehicle target of high-definition video monitoring image fast location, event detection system and method.
Background technology
In recent years, high-definition camera is applied to the high-definition video monitoring under public safety, parking management, intelligent transportation, the comprehensive field complex background such as emergent more and more.Vehicle target location and event detecting method based on traditional SD video monitoring image can't be converted into for the high-definition video monitoring image under the complex scene, main cause is that the above high-definition video monitoring image resolution ratio of 2,000,000 pixels is high, monitoring scene is large, image background is complicated, it is large to set the quick location of detection area vehicle target and event detection difficulty, and rate of false alarm is high.Have a plurality of vehicle targets to need simultaneously the location in the high-definition video monitoring image under the complex scene and in conjunction with field management demand estimation event detection type, and existing vehicle target identification and event detecting method based on the SD video monitoring image is general only for the simple target under the simple background.In addition, fast location and event detecting method of vehicle target in the high-definition video monitoring image setting detection area requires not only that accuracy rate is high, rate of false alarm is low, and requires locating speed fast.Therefore how positioned vehicle target and implement event detection quickly and accurately in high-definition video monitoring image (setting detection area) is generally to face and problem demanding prompt solution in the existing Intellectual Analysis Technology.
Summary of the invention
The present invention is directed to the prior art defective, provide a kind of figure image intensifying effective, locating speed is fast, the quick location of the vehicle target based on the high-definition video monitoring image and event detection system and method that the event detection accuracy rate is high.
For achieving the above object, the invention provides a kind of vehicle mark based on the high-definition video monitoring image and locate fast and event detection system, this system sets detection area vehicle target fast detecting locating module, setting detection area Binary Sketch of Grey Scale Image processing module, vehicle target and driving trace image inclination degree correction module, the tracking of vehicle target driving trace and affair character extraction module and vehicle target event detection and reliability assessment module by high-definition video monitoring image enhancement processing module and forms;
Described high-definition video monitoring image enhancement processing module realizes the numeral of front end high definition video monitoring camera real-time image acquisition is strengthened processing, determine in real time image filter template type (adaptive wiener filter) and weighting coefficient according to background/scene and content/target image in the high-definition video monitoring image, obtain optimum signal-noise ratio and strengthen image, improve follow-up vehicle location and event detection precision;
Set detection area vehicle target fast detecting locating module and realize setting between detection area and dynamic background image and compare in real time, employing self-adaption gradient detection and location algorithm carries out fast detecting, location to vehicle target wherein;
Setting detection area Binary Sketch of Grey Scale Image processing modules implement setting detection area image transitions is the binary conversion treatment behind the gray level image;
Vehicle target and driving trace image inclination degree correction module are based on the long vehicle target of adding up of vertical runs and driving trace image inclination degree correcting algorithm (horizontal tilt degree correcting algorithm is similar) realizes setting the detection area vehicle target and the correction of track of vehicle image inclination degree is processed;
The vehicle target driving trace is followed the tracks of and the affair character extraction module is implemented in that vehicle target driving trace image segmentation and affair character extract in the binary image after the image inclination degree is proofreaied and correct;
Vehicle target event detection and reliability assessment module adopt the dynamic sample clustering methodology to realize optimization, the adjustment of feature samples in the identification of vehicle target driving trace images match and local vehicle target driving trace image (feature) Sample Storehouse.
Described vehicle target based on the high-definition video monitoring image is located fast and event detecting method comprises:
Step 1, high-definition video monitoring image to the high-definition camera Real-time Collection strengthens processing, detection area image and dynamic background image are set in real time comparison, carry out fast detecting, location to setting the detection area vehicle target in the high-definition video monitoring image of Real-time Collection;
Step 2, with the setting detection area vehicle target image mapped that detects in real time in original high-definition video monitoring image setting detection area dynamic background image, detect interfering components in the vehicle target according to presetting the eliminating of alarm threshold and field management demand, follow the tracks of the vehicle target driving trace, the vehicle target affair character is classified;
Step 3 is gray level image with setting the detection area image transitions in the high-definition video monitoring image, and carries out binary conversion treatment to setting the detection area gray level image in the high-definition video monitoring image;
Step 4 is compared vehicle target driving trace and management Sample Storehouse template in real time, determines to set detection area vehicle target affair character and event (detection) type;
Step 5, real-time learning, optimum management Sample Storehouse vehicle target affair character and event (detection) type, real-time assessment is set detection area vehicle target event (detection) type confidence level.
Further, described method step 5 adopts the dynamic sample clustering methodology that vehicle target affair character and event detection credible result degree are assessed.
For achieving the above object, the present invention also provides the Embedded Software Design technology of the quick location of a kind of vehicle target based on the high-definition video monitoring image and event detecting method, and described embedded software function comprises:
High-definition video monitoring image enhancement processing function is used for realizing that high definition (more than the 2000000 pixels) video monitoring image under the complicated monitoring scene strengthens processing, with the removal of images noise;
Vehicle target fast detecting positioning function is used for realizing high-definition video monitoring image setting detection area vehicle target fast detecting location under the complicated monitoring scene, to determine fast vehicle target;
Vehicle target image motion compensation function, be used for realizing the motion compensation function such as high-definition video monitoring image setting detection area vehicle target and the correction of driving trace image inclination degree under the inhomogeneous illumination condition, set vehicle target location and accuracy of identification in the detection area image to improve;
The vehicle target driving trace is followed the tracks of and the affair character abstraction function, carry out sample matches according to vehicle target driving trace and affair character in the high-definition video monitoring image setting detection area that detects in real time, realize vehicle target affair character Fast Classification and identification.
High definition (more than 2,000,000 pixels) the video monitoring image vehicle target that the present invention is directed under the complex background is located and the event detection demand fast, credible, the reliability of high-definition video monitoring image enhancement processing and software under the embedded software Functional Design realization inhomogeneous illumination condition, vehicle target fast detecting, locating speed are fast, the adaptation dynamic range is large, the event detection precision is high, improve front end embedded system (intelligent camera) reliability and stability, reduce on-site parameters requirement and difficulty are set.
Description of drawings
Fig. 1 is that the vehicle target of high-definition video monitoring image of the present invention is located fast, the event detecting method FB(flow block);
Fig. 2 is that the vehicle target of high-definition video monitoring image of the present invention is located fast, the event detection system logic diagram.
Embodiment
Below by drawings and Examples, technical solution of the present invention is described in further detail.
Fig. 1 is that the vehicle target of high-definition video monitoring image of the present invention is located fast, the event detecting method process flow diagram, and as shown in the figure, the concrete technic relization scheme of the present invention comprises the steps:
Described step 305 adopts the dynamic sample clustering methodology that vehicle target driving trace, affair character and event detection credible result degree are assessed.
Fig. 2 is the logic diagram that the present invention is based on the vehicular events detection system of high-definition video monitoring image, based on the vehicular events detection system of high-definition video monitoring image, this system is followed the tracks of by high-definition video monitoring image enhancement processing module 1, vehicle target fast detecting locating module 2, Binary Sketch of Grey Scale Image processing module 3, vehicle target and driving trace image inclination degree correction module 4, vehicle target driving trace and affair character extraction module 5 and vehicle target event detection and reliability assessment module 6 form module 1, high-definition video monitoring image enhancement processing
In high-definition video monitoring system, installation, parameter setting and the environmental factor of on-the-spot high-definition video monitoring video camera, cause the high-definition video monitoring image degradation (anamorphose, noise covering etc.) of Real-time Collection, with vehicle target location and the event detection precision that directly affects based on the high-definition video monitoring image.
" high-definition video monitoring image enhancement processing " module realizes the numeral of front end high definition video monitoring camera real-time image acquisition is strengthened processing, determine in real time image filter template type (adaptive wiener filter) and weighting coefficient according to background (scene) in the high-definition video monitoring image and content (target), obtain optimum signal-noise ratio and strengthen image, improve vehicle target location and event detection precision.
Set detection area vehicle target fast detecting locating module
The high-definition video monitoring image of on-the-spot high-definition video monitoring video camera Real-time Collection, resolution is 200
Processing speed, thereby the system that affects follow-up vehicle target location and event detection real-time.
In the on-the-spot high-definition video monitoring video camera real-time image acquisition, according to system for field monitoring scene and related application regulatory requirement, the effective coverage that can be used for the quick location of vehicle target and event detection, it is the regional area in the high-definition video monitoring image, can arrange according to on-site supervision scene and application management demand, to improve high-definition video monitoring image (effective coverage) processing speed and vehicle target location and event detection real-time and validity." set detection area vehicle target fast detecting location " module realizes setting between detection area and dynamic background image and compares in real time, adopts self-adaption gradient detection and location algorithm that vehicle target is wherein carried out fast detecting, location.
The self-adaption gradient detection and location algorithm that adopts can detect a plurality of vehicle targets simultaneously, and according to the vehicle target feature vehicle target is mated identification, according to driving trace and the characteristics of image of setting vehicle target in the detection area, the present invention adopts pyramid algorith to decompose (subimage) to setting detection area vehicle target driving trace, tracking detects vehicle target driving trace and affair character, at last sample in vehicle target driving trace and affair character and the local Sample Storehouse is mated (coupling thresholding and accuracy of detection are set), and vehicle target driving trace and affair character classified, finally determine the vehicle target type also (self study) optimize sample image in the local Sample Storehouse.Level, vertical direction driving trace coefficient of dissociation that the present invention sets pyramid algorith are respectively γ
x(＜1.0) and γ
yDecompose by original detection area driving trace image I horizontal direction and vertical direction difference convergent-divergent γ (＜1.0), the first order
xAnd γ
yDoubly, obtain first order pyramid image I
1, again by I
1Horizontal direction and vertical direction driving trace be convergent-divergent γ respectively
xAnd γ
yDoubly, obtain second level pyramid image I
2..., the rest may be inferred can do N (N=I, 2,3 ...) and level decomposes (according to vehicle target quantity, accuracy of identification and field management requirements set).Generally get γ
x=0.5, γ
y=0.5 in order to improve to set detection area vehicle target driving trace picture breakdown speed, setting detection area (to be identified) destination number≤20 o'clock, and General N gets 2.
Every one-level pyramid diagram is looked like to carry out color space transformation (being converted to gray level image), establish reducing
Feature extraction algorithm carries out vehicle target fast detecting, location, and the speed that is characterized in is fast, rate of false alarm is low.
Set detection area Binary Sketch of Grey Scale Image processing module
Binary conversion treatment is the basis of Digital Image Processing, also is the important step of setting the identification of detection area image vehicle target.Gray level image is than the easier binary conversion treatment of carrying out of coloured image, the present invention carries out binary conversion treatment immediately after will setting the detection area image transitions to be gray level image, the image binaryzation disposal route is a lot, the present invention is directed to the field management demand and set detection area vehicle target feature of image, detection (location) precision is selected, in setting detection area vehicle target location algorithm, if ambient lighting is even and contrast is stronger, then adopts histogram method to set the detection area image binaryzation and process; When if ambient lighting is inhomogeneous, then can't directly adopt histogram method to set the detection area image binaryzation processes, the setting detection area image binaryzation that the present invention adopts setting detection area image segmentation and the horizontal technology GLLT of gray level logic (Gray Logical Level Technique) algorithm effectively to solve under the even low contrast condition of uneven illumination is processed---according to setting detection area image and vehicle target feature of image, to set the detection area image and be divided into several subregions (according to regulatory requirement and destination number), and in all subregion image, the vehicle target image be carried out fast detecting, location and successor Check processing.The GLLT algorithm flow is as follows:
1). establish f (x, y) for setting (x, y) some gray-scale value in the detection area image, g (x, y) is its level and smooth rear gray-scale value.According to setting vehicle target image template W (generally getting W=3) in the detection area, calculate (2W+l) * (2W+l) template window average gray with the vehicle target picture centre:
2). the 8 adjacent pixels points of setting W pixel of detection area image mid-range objectives pixel (x, y) are P
0, P
1... P
7If g (x, y) is than its 4 adjacent pixels P
i, P
(i+4) mod8, P
(i+1) mod8, P
(i+5) mod8(i=0,1,2,3) high T gray level, then (x, y) is divided into " white pixel " (value 255); If g (x, y) is than its 4 adjacent pixels P
i, P
(i+4) mod8, P
(i+1) mod8, P
(i+5) mod8(i=0,1,2,3) hang down T gray level, and then (x, y) is divided into " black pixel " (value 128); Otherwise this pixel is labeled as " unfiled pixel " (value 0).Decision rule is:
Wherein, H (P) is true, if
L (P) is true, if
Pixel P '
iAnd P '
I+1Respectively pixel P
iAnd P
I+1(i=0,1,2,3) are over against (180 ° of directions) pixel.
3). the corresponding average gray image value G of pixel of value 255 and 128 is calculated in the subregion
1And G
2
4). be that 0 unfiled pixel is classified to value according to the following rules:
GLLT algorithm strong adaptability, fast, the strong robustness of speed do not need complicated parameter setting, the more difficult problem identificatioin of threshold value in the time of can effectively solving such as the histogram method binary conversion treatment.
Vehicle target and driving trace image inclination degree correction module
Vehicle target and driving trace image inclination degree are proofreaied and correct directly affects vehicle target location and event detection precision, and degree of tilt correction proportion in whole vehicle target location and event detection flow process is larger, therefore, vehicle target and driving trace image inclination degree correcting algorithm efficient are based on the Focal point and difficult point of the vehicular events detection algorithm of high-definition video monitoring image.In vehicle target and driving trace image thereof, mainly contain horizontal tilt and vertical bank two classes.The present invention is based on vehicle target and the driving trace image inclination degree correcting algorithm (horizontal tilt degree correcting algorithm is similar) of the long statistics of vertical runs.
1). find out vehicle target framing mask coordinate, x
0, x
1, y
0, y
iAnd calculate its centre coordinate (x
c, y
c);
2). establishing the boundary position off-set value is D
k, then pixel (x, y) is displaced to (x
s, y
s):
y
s＝y；
3). to given D
kThe displacement diagram picture, calculate vertical direction black and white run length quadratic sum;
The vehicle target driving trace is followed the tracks of and the affair character extraction module
Vehicle target driving trace image segmentation is in the binary image after vehicle target image inclination degree is proofreaied and correct, and adopts vertical projection method to mark off vehicle target driving trace subimage and interrelated relation thereof.This module difficult point is that vehicle target driving trace image adhesion (comprising the adhesion between vehicle target and the background) and noise image disturb, and comes the guiding vehicle target to travel cutting apart of trace image adhesion and noise image by the prediction of vehicle target driving trace subimage and estimation.
Vehicle target event detection and reliability assessment module
Adopt the dynamic sample clustering methodology that vehicle target driving trace image is mated identification, by with local vehicle target driving trace image (feature) Sample Storehouse in feature samples compare (obtaining weight coefficient by the training self-adaptation to these samples), to vehicle target driving trace image (feature) sample size, the indexs such as degree of fitting are assessed, optimize, adjust vehicle target driving trace image (feature) sample data, adopt mode of learning and the vehicle target affair character sample that forms of evaluation algorithm preferentially, with raising vehicle target event detection precision.
The present invention have for high definition under the complex background (more than 2,000,000 pixels) video monitoring image vehicle target fast location and inhomogeneous illumination condition hypograph strengthen that treatment effect is good, dynamic range large, target localization and event detection precision advantages of higher, Embedded Software Design can improve software trust, fiduciary level and stability greatly simultaneously, reduces front end embedded system parameter requirement is set.
The professional also can further recognize, in conjunction with each exemplary module of embodiment disclosed herein and algorithm steps, can electronic hardware, computer software or the two combination realize, this paper has pressed general each illustrative functions and the realization flow described of correlation function, these functions realize in which way, depend on related art scheme application ﹠ design constraint condition.The professional and technical personnel can realize institute's representation function with the different technologies implementation to application-specific, but this realization should not thought and exceeds the scope of the invention.
In conjunction with embodiment method disclosed herein or technic relization scheme, can software, embedded software hardware or the mode of combining carry out.Software module can place known any other form storage medium in random access memory (RAM), internal memory, ROM (read-only memory) (ROM), electrically programmable ROM, electrically erasable ROM, register, hard disk, moveable magnetic disc, CD-ROM or the technical field.The above is based on pedestrian's event detecting method and the systems technology implementation of high-definition video monitoring image; purpose of the present invention, technical scheme and beneficial effect are further described; institute is understood that; the above only is the concrete technic relization scheme of the present invention; the protection domain that is not intended to limit the present invention; within the spirit and principles in the present invention all, any modification of making, be equal to replacement, improvement etc., all should.
Claims (3)
1. the vehicle target of high-definition video monitoring image location, event detection system is characterized in that, this system is by high-definition video monitoring image enhancement processing module, vehicle target fast detecting locating module, setting detection area Binary Sketch of Grey Scale Image processing module
, vehicle target and driving trace image inclination degree correction module, the vehicle target driving trace is followed the tracks of and affair character extraction module and vehicle target event detection and reliability assessment module form;
Wherein, described high-definition video monitoring image enhancement processing module is used for realizing that the numeral to front end high definition video monitoring camera real-time image acquisition strengthens processing, determine in real time image filter template type and weighting coefficient according to background/scene and content/target image in the high-definition video monitoring image, obtain optimum signal-noise ratio and strengthen image, improve follow-up vehicle location and event detection precision, the removal of images noise;
Described vehicle target fast detecting locating module is realized setting between detection area and dynamic background image and is compared in real time, and employing self-adaption gradient detection and location algorithm carries out fast detecting, location to vehicle target wherein;
Described setting detection area Binary Sketch of Grey Scale Image processing modules implement setting detection area image transitions is the binary conversion treatment behind the gray level image;
Described vehicle target and driving trace image inclination degree correction module are for realizing high-definition video monitoring image vehicle target and driving trace image inclination degree correcting algorithm realization setting detection area vehicle target and track of vehicle image inclination degree correction processing under the inhomogeneous illumination condition;
Described vehicle target driving trace is followed the tracks of and the affair character extraction module is used for being implemented in after the image inclination degree is proofreaied and correct binary image vehicle target driving trace image segmentation and affair character extract;
Described vehicle target event detection and reliability assessment module adopt the dynamic sample clustering methodology to realize optimization, the adjustment of feature samples in the identification of vehicle target driving trace images match and the local vehicle target driving trace image/feature samples storehouse.
2. the vehicle target of high-definition video monitoring image location, event detecting method is characterized in that the method specifically comprises the steps:
Step 1, high-definition video monitoring image enhancement processing module strengthens processing to the high-definition video monitoring image of high-definition camera Real-time Collection, detection area image and dynamic background image are set in real time comparison, carry out fast detecting, location to setting the detection area vehicle target in the high-definition video monitoring image of Real-time Collection;
Step 2, the setting detection area vehicle target image mapped that vehicle target fast detecting locating module will detect in real time is in original high-definition video monitoring image setting detection area dynamic background image, detect interfering components in the vehicle target according to presetting the eliminating of alarm threshold and field management demand, follow the tracks of the vehicle target driving trace, the vehicle target affair character is classified;
Step 3 is gray level image with setting the detection area image transitions in the high-definition video monitoring image, and carries out binary conversion treatment to setting the detection area gray level image in the high-definition video monitoring image;
Step 4 is compared vehicle target driving trace and management Sample Storehouse template in real time, determines to set detection area vehicle target affair character and event/type of detection;
Step 5, real-time learning, optimum management Sample Storehouse vehicle target affair character and event/type of detection, real-time assessment is set detection area vehicle target event/type of detection confidence level.
3. the vehicle target of high-definition video monitoring image according to claim 2 location, event detecting method, it is characterized in that described method step 5 adopts the dynamic sample clustering methodology that vehicle target affair character and event detection credible result degree are assessed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012102229529A CN102902951A (en) | 2012-06-29 | 2012-06-29 | System and method for vehicle target location and event detection on basis of high-definition video monitoring images |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012102229529A CN102902951A (en) | 2012-06-29 | 2012-06-29 | System and method for vehicle target location and event detection on basis of high-definition video monitoring images |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102902951A true CN102902951A (en) | 2013-01-30 |
Family
ID=47575175
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2012102229529A Pending CN102902951A (en) | 2012-06-29 | 2012-06-29 | System and method for vehicle target location and event detection on basis of high-definition video monitoring images |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102902951A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103400159A (en) * | 2013-08-05 | 2013-11-20 | 中国科学院上海微系统与信息技术研究所 | Target classification identifying method in quick mobile context and classifier obtaining method for target classification and identification in quick mobile context |
| CN105678217A (en) * | 2015-12-29 | 2016-06-15 | 安徽海兴泰瑞智能科技有限公司 | Vehicle parking guidance positioning method |
| CN105718750A (en) * | 2016-01-29 | 2016-06-29 | 长沙理工大学 | Prediction method and system for vehicle travelling track |
| CN105761504A (en) * | 2016-05-17 | 2016-07-13 | 重庆大学 | Vehicle speed real-time measuring method based on inhomogeneous video image frame collection |
| CN106874928A (en) * | 2016-12-28 | 2017-06-20 | 中国科学院长春光学精密机械与物理研究所 | Tracking target the burst automatic decision method of critical event and system |
| CN108460972A (en) * | 2018-05-17 | 2018-08-28 | 南京云思创智信息科技有限公司 | A kind of more car plates based on unmanned plane independently detection and positioning system and method |
| CN109785641A (en) * | 2019-03-08 | 2019-05-21 | 黄河水利职业技术学院 | A kind of traffic behavior monitoring device and method |
| CN110991485A (en) * | 2019-11-07 | 2020-04-10 | 成都傅立叶电子科技有限公司 | Performance evaluation method and system of target detection algorithm |
| CN112149476A (en) * | 2019-06-28 | 2020-12-29 | 北京海益同展信息科技有限公司 | Target detection method, device, equipment and storage medium |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101630360A (en) * | 2008-07-14 | 2010-01-20 | 上海分维智能科技有限公司 | Method for identifying license plate in high-definition image |
-
2012
- 2012-06-29 CN CN2012102229529A patent/CN102902951A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101630360A (en) * | 2008-07-14 | 2010-01-20 | 上海分维智能科技有限公司 | Method for identifying license plate in high-definition image |
Non-Patent Citations (1)
| Title |
|---|
| 邹依峰: "智能视频监控中的行人检测与跟踪方法研究", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103400159A (en) * | 2013-08-05 | 2013-11-20 | 中国科学院上海微系统与信息技术研究所 | Target classification identifying method in quick mobile context and classifier obtaining method for target classification and identification in quick mobile context |
| CN103400159B (en) * | 2013-08-05 | 2016-09-07 | 中国科学院上海微系统与信息技术研究所 | Target classification identification method in fast moving scenes and grader acquisition methods |
| CN105678217A (en) * | 2015-12-29 | 2016-06-15 | 安徽海兴泰瑞智能科技有限公司 | Vehicle parking guidance positioning method |
| CN105718750A (en) * | 2016-01-29 | 2016-06-29 | 长沙理工大学 | Prediction method and system for vehicle travelling track |
| CN105718750B (en) * | 2016-01-29 | 2018-08-17 | 长沙理工大学 | A kind of prediction technique and system of vehicle driving trace |
| CN105761504B (en) * | 2016-05-17 | 2018-02-09 | 重庆大学 | Speed method for real-time measurement based on the collection of non-homogeneous video frame image |
| CN105761504A (en) * | 2016-05-17 | 2016-07-13 | 重庆大学 | Vehicle speed real-time measuring method based on inhomogeneous video image frame collection |
| CN106874928A (en) * | 2016-12-28 | 2017-06-20 | 中国科学院长春光学精密机械与物理研究所 | Tracking target the burst automatic decision method of critical event and system |
| CN106874928B (en) * | 2016-12-28 | 2020-05-19 | 中国科学院长春光学精密机械与物理研究所 | Automatic judgment method and system for tracking target emergency key event |
| CN108460972A (en) * | 2018-05-17 | 2018-08-28 | 南京云思创智信息科技有限公司 | A kind of more car plates based on unmanned plane independently detection and positioning system and method |
| CN109785641A (en) * | 2019-03-08 | 2019-05-21 | 黄河水利职业技术学院 | A kind of traffic behavior monitoring device and method |
| CN112149476A (en) * | 2019-06-28 | 2020-12-29 | 北京海益同展信息科技有限公司 | Target detection method, device, equipment and storage medium |
| CN110991485A (en) * | 2019-11-07 | 2020-04-10 | 成都傅立叶电子科技有限公司 | Performance evaluation method and system of target detection algorithm |
| CN110991485B (en) * | 2019-11-07 | 2023-04-14 | 成都傅立叶电子科技有限公司 | Performance evaluation method and system of target detection algorithm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102902951A (en) | System and method for vehicle target location and event detection on basis of high-definition video monitoring images | |
| CN102799862A (en) | System and method for pedestrian rapid positioning and event detection based on high definition video monitor image | |
| CN102768731A (en) | Method and system for automatic positioning and identifying target based on high definition video images | |
| CN106935035B (en) | Parking offense vehicle real-time detection method based on SSD neural network | |
| US9292750B2 (en) | Method and apparatus for detecting traffic monitoring video | |
| CN101630360B (en) | Method for identifying license plate in high-definition image | |
| CN106022243B (en) | A kind of retrograde recognition methods of the car lane vehicle based on image procossing | |
| KR100912746B1 (en) | Method for traffic sign detection | |
| CN101916383B (en) | Vehicle detecting, tracking and identifying system based on multi-camera | |
| CN107301405A (en) | Method for traffic sign detection under natural scene | |
| US8019157B2 (en) | Method of vehicle segmentation and counting for nighttime video frames | |
| CN106652468A (en) | Device and method for detection of violation of front vehicle and early warning of violation of vehicle on road | |
| CN101937508A (en) | License plate localization and identification method based on high-definition image | |
| CN101739686A (en) | Moving object tracking method and system thereof | |
| CN101286239A (en) | Aerial shooting traffic video frequency vehicle rapid checking method | |
| CN101872546A (en) | Video-based method for rapidly detecting transit vehicles | |
| CN108804987B (en) | Door opening and closing state detection method and device and people flow detection system | |
| CN101996307A (en) | Intelligent video human body identification method | |
| CN103530640A (en) | Unlicensed vehicle detection method based on AdaBoost and SVM (support vector machine) | |
| CN108520528B (en) | Mobile vehicle tracking method based on improved difference threshold and displacement matching model | |
| KR101686558B1 (en) | Multilane camera recognition system and method for analysing image to learning type thereof | |
| CN106446929B (en) | Type of vehicle detection method based on edge gradient potential energy | |
| CN203020184U (en) | Electric vehicle lane marking line detecting device based on double charge coupled devices (CCD) | |
| CN114141022B (en) | Emergency lane occupation behavior detection method and device, electronic equipment and storage medium | |
| CN108268866B (en) | Vehicle detection method and 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 | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20130130 |