CN101567097B - Bus passenger flow automatic counting method based on two-way parallactic space-time diagram and system thereof - Google Patents
Bus passenger flow automatic counting method based on two-way parallactic space-time diagram and system thereof Download PDFInfo
- Publication number
- CN101567097B CN101567097B CN2009100525973A CN200910052597A CN101567097B CN 101567097 B CN101567097 B CN 101567097B CN 2009100525973 A CN2009100525973 A CN 2009100525973A CN 200910052597 A CN200910052597 A CN 200910052597A CN 101567097 B CN101567097 B CN 101567097B
- Authority
- CN
- China
- Prior art keywords
- target
- counting
- parallax
- line
- moving
- 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.)
- Expired - Fee Related
Links
Images
Abstract
The invention discloses a bus passenger flow automatic counting method based on two-way parallactic space-time diagram and a system thereof which comprises a left camera, a right camera, a microprocessor, an infrared LED lamp and the like. The method comprises the steps of: paralleling the left camera and the right camera which are synchronous so as to obtain 4 row gray space-time diagrams generated on an in-counting line and an out-counting line; forming 2 moving target row parallactic space-time diagrams on the in-counting line and the out-counting line formed by the row gray space-time diagrams; extracting and marking moving targets in the row parallactic space-time diagrams; segmenting and merging the moving targets; matching optimally the moving targets so as to obtain judgment of passenger flow moving direction and finish automatic counting. The method and the system thereof are applied to buses with complex environment for passenger flow counting, and have compact system structure and high robustness. The adoption of two-way counting lines and stereoscopic vision technology improves the anti-interference performance and real-time performance of the system, thus being appliedin counting scenes with rapid light variation and removing the interference caused by shadows to counting result.
Description
Technical field
The present invention is used for the bus passenger flow statistics at a kind of relating to, and specifically relates to a kind of bus passenger flow automatic counting method and system thereof based on two-way parallactic space-time diagram.This method adopts stereovision technique to carry out motion target detection, coupling and counting, is particularly useful for the passenger flow counting in this complex scene of bus.
Background technology
Frequent along with the sharp increase of population and people's trip, the traffic and transportation system of China faces huge pressure, a series of problems such as traffic jam, the wasting of resources, environmental pollution occurred.And realize that intelligent transportation system (ITS) is the key that solves a series of traffic problems.In whole traffic and transportation system, urban public tranlport system is its important ingredient.Advantages such as urban public transport has that freight volume is big, intensive management, the saving energy and path space, environmental pollution are little.Each big city has all proposed to first develop the information-based and intelligentized strategy of city bus, quickening realization public transport in succession both at home and abroad.Obtain the bus passenger flow data in the public transportation system timely and accurately, be the main foundation that public traffic management department rationally arranges public bus network, Optimization Dispatching public transit vehicle, raising efficiency of operation, therefore the research to the bus passenger flow data statistical approach has great practical value.
The automatic passenger flow counting method that has proposed at present mainly contains based on methods such as active infrared induction, passive infrared induction, pedal pressing force sensing, video image processing.Based on the system of active infrared induction, this technology maturation, antijamming capability is strong, but no matter is to adopt single bundle or multi beam infrared light, all can not solve the counting of crowded passenger flow; The thermal infrared that passive type infrared counting technology is sent by human body is counted, and can distinguish life and abiotic object, but is subject to the influence of passenger's dressing, environment temperature etc., also can't adapt to the counting of crowded passenger flow.Method of counting based on the pedal pressing force sensor is less to people's individual difference requirement, but requires the passenger to get on the bus successively, can not crowd, and can't differentiate the turnover direction of passenger flow preferably, and the failure rate of pressure transducer is also higher.
Method based on video image processing technology is the most rising method of counting at present, is divided into based on monocular and binocular camera shooting two classes.Preceding a kind of method utilizes the gray scale of target, chrominance information to carry out cutting apart of moving target, but extremely responsive to the variation of light in the counting scene, shade and chaff interference are also very big to the influence that moving target extracts, and are difficult to count exactly; A kind of method in back has been utilized the three-dimensional depth information of moving target, the illumination variation that a kind of method existed before this method can solve preferably and the problem of shade, but existing method calculated amount is big, global motion target following difficulty, and the real-time and the accuracy of system are greatly limited.
Summary of the invention
The objective of the invention is to the technical matters that exists in the existing passenger flow counting technology, a kind of bus passenger flow automatic counting method and system thereof based on two-way parallactic space-time diagram is provided, it is adapted at carrying out passenger flow counting in the complexity counting scene on the bus, and counting algorithm can satisfy the real-time and the accuracy requirement of system well.
In order to achieve the above object, technical scheme of the present invention is:
Above-mentioned bus passenger flow automatic counting system based on two-way parallactic space-time diagram, it comprises parallel synchronous left and right video camera, the microprocessor that is contained in the bus door top, microprocessor comprises cutting apart of the extraction of capable gray scale spacetime diagram generation module, row parallax spacetime diagram generation module, moving target and serial mark module, moving target and merges module, moving target coupling and direction and judge and counting module, left and right video camera links to each other with microprocessor respectively, and has the infrared LED lamp to link to each other with microprocessor.
The bus passenger flow automatic counting method of above-mentioned two-way parallactic space-time diagram, it is characterized in that this method of counting comprises the steps: (1), obtains left and right two synchronization video image sequences with parallel synchronous left and right video camera, the direction vertical with the passenger moving direction and keep the in counting line of a determining deviation and the out counting line on generate the capable gray scale spacetime diagram of 4 width of cloth; (2), calculate the parallax of the moving target in counting line and the out counting line, form 2 width of cloth moving target parallax spacetime diagrams in counting line and the out counting line respectively by above line gray scale spacetime diagram; (3), to the moving target in the above line parallax spacetime diagram extract, mark; (4), above-mentioned target is cut apart and merged; (5), moving target is carried out optimum matching, obtain the judgement of passenger flow direction of motion and finish automatic counting.
The present invention compares with existing passenger flow acquisition technique, and have following feature and advantage: the present invention adopts the duplicate rows counting line, only the data on the counting line is handled and target detection and coupling, can significantly reduce calculated amount, and improves the anti-interference of system; Utilize the row frame difference method to extract all possible moving target, extract real moving target by the parallax threshold value again, compare, be subjected to the influence of illumination variation and shade hardly with the method for only utilizing the frame difference to extract moving target.The counting place that bus passenger flow automatic counting method and the system thereof based on two-way parallactic space-time diagram that the present invention proposes is applicable to circumstance complication, and can satisfy the real-time and the accuracy requirement of number system well.
Description of drawings
Fig. 1 is based on the structured flowchart of the bus passenger flow automatic counting system of two-way parallactic space-time diagram.
Fig. 2 is contained in the parallel synchronous left and right video camera at bus door top and the in that is provided with across a certain distance on the direction vertical with the passenger getting on/off direction and mutually and the synoptic diagram of two counting lines of out.
Fig. 3 is the processing block diagram that system software is realized.
Fig. 4 is based on the workflow synoptic diagram of the bus passenger flow automatic counting method of two-way parallactic space-time diagram.
Embodiment
Below with reference to accompanying drawing bus passenger flow automatic counting method and the system thereof based on two-way parallactic space-time diagram of the present invention is described in further detail.
As shown in Figure 1, 2, above-mentioned bus passenger flow automatic counting system based on two-way parallactic space-time diagram, it comprises parallel synchronous left and right video camera A1, A2, DSP microprocessor B, the infrared LED lamp C that is contained in the bus door top, DSP microprocessor B comprises cutting apart of the extraction of capable gray scale spacetime diagram generation module B1, row parallax spacetime diagram generation module B2, moving target and serial mark module B3, moving target and merges module B4, moving target coupling and direction and judge and counting module B5 that left and right video camera A1, A2 link to each other with DSP microprocessor B respectively.This system can pass through RS-485 interface and onboard system real-time Communication for Power, transmits count results, and accepts its control; Carry out the output of system parameter setting and real-time digital video by the 100base-T network interface; Configuration analog video output interface is used for the monitoring of video image; Configuration is subjected to the infrared LED lamp of microprocessor control to realize the night illumination light filling.
Shown in Fig. 1 ~ 3, the bus passenger flow automatic counting method of above-mentioned two-way parallactic space-time diagram, it is characterized in that this method of counting comprises the steps: (1), obtains left and right two synchronization video image sequences with parallel synchronous left and right video camera, the direction vertical with the passenger moving direction and keep the in counting line of a determining deviation and the out counting line on generate the capable gray scale spacetime diagram of 4 width of cloth; (2), calculate the parallax of the moving target in counting line and the out counting line, form the capable parallax spacetime diagram of 2 width of cloth moving targets in counting line and the out counting line respectively by above line gray scale spacetime diagram; (3), to the moving target in the above line parallax spacetime diagram extract, mark; (4), above-mentioned target is cut apart and merged; (5), moving target is carried out optimum matching, obtain the judgement of passenger flow direction of motion and finish automatic counting.
Above-mentioned steps (1) generates row gray scale spacetime diagram, the parallel synchronous left and right video camera that is contained in the bus door top monitors Same Scene from 2 positions, 2 counting lines (in counting line and out counting line) are set on the direction of vertical passenger getting on/off in monitoring scene mutually across a certain distance, obtain left and right 2 synchronous images sequences, it by microprocessor, is handled by row gray scale spacetime diagram generation module.In counting line and out counting line in 2 corresponding same physics scenes of counting lines difference respectively arranged in the left and right video image.The image line gradation data that extracts from every frame video image on the counting line is pressed time shaft expansion successively line by line, and gets each 2 width of cloth about nearest fixed line number formation, the dynamically capable gray scale spacetime diagram of totally 4 width of cloth.
Above-mentioned steps (2) generates row parallax spacetime diagram, and above-mentioned left and right capable gray scale spacetime diagram is handled by row parallax spacetime diagram generation module by microprocessor, and its concrete steps are as follows.
(2-1), utilize row frame difference to extract possible moving target on the counting line: in order to reduce calculated amount, reduce the influence of static background simultaneously, adopt 3 every trade frame difference methods in right view, to detect possible moving target candidate point, 3 row are meant current line and last 2 row, 3 row images gray scale difference absolute value sum between any two is poor as the current line frame, the threshold value of judging the motion candidate target is OBJ_TH, if the frame difference of current line pixel is greater than OBJ_TH, think that then this point is the moving region candidate point, otherwise think background dot.
(2-2), calculate the parallax of working as the pre-treatment row, if pixel is the target candidate point, then calculate the parallax of this pixel, otherwise its parallax is used as 0 to be handled, for being carried out successive image, handles the row disparity map, the parallax of pixel is done greyscale transformation, obtain the capable parallax of parallax gray scale in 0 ~ 255 scope at last.Pixel matching is the key that parallax calculates, and according to polar curve constraint condition, the match point of pixel is on the corresponding counting line of left view on the right view counting line.Parallax calculation method is as follows:
At first on the counting line of right view, detect motion candidate target point, to the corresponding counting line of left view, search for the optimum matching impact point then, and to adopt with target candidate point and pixel to be matched be that center length is that the gray scale cross correlation function of two one dimension windows of 2W+1 is as the measurement of similarity, according to the extreme value searching optimum matching pixel of related coefficient.Wherein, the length of match window is done dynamically to adjust according to the variance of window interior pixel gray scale, and variance is more little, and window is big more, is used to solve the parallax matching problem of gray scale flat site.In matching process, according to the rationality of the unique constraints of matching criterior, continuity constraint parallax that condition judgment is asked and adjust.
(2-3), the capable parallax gradation data that obtains on every frame count line is launched successively by time shaft, and get nearest fixed line number and form capable parallax spacetime diagram.
In counting line and out counting line are repeated above-mentioned steps (2-1) ~ (2-3), obtain the capable parallax spacetime diagram of 2 width of cloth in counting line and the out counting line respectively.
Above-mentioned steps (3), to extraction, the mark of the moving target in the above line parallax spacetime diagram, above-mentioned left and right capable parallax spacetime diagram is handled by the extraction and the serial mark module of moving target by microprocessor.The serial mark is meant that the mark of moving target only carries out at current line, and every frame is only handled the parallax data in and the out line, obtains moving target in the row parallax spacetime diagram by the serial computing on the time shaft.Self-defined 2 structure OBJ_TAG and RECT_TAG in this module, with target area information that does not enter fully of an OBJ_TAG structure variable record, write down and occur a plurality of disconnected target areas information simultaneously to set up the dynamic link table mode, with target area information that has entered fully of a RECT_TAG structure variable record, with a plurality of target area information that enter fully of this structural array storage.
(3-1), the morphology smoothing operator of employing 3 * 11 carries out smoothing processing to the parallax of current line.3 row parallaxes are current line parallax and each delegation's parallax of front and back, so row parallax spacetime diagram postpones a frame in time than capable gray scale spacetime diagram.
(3-2), judge according to the parallax of moving target whether current line is to have real moving target (passenger), if the pixel parallax value is greater than PARA_MIN then think the moving target point, otherwise just think because the spurious motion impact points that disturbing factor caused such as illumination variation are treated as a setting.Occur when detecting when the pre-treatment row has target, judge that this target phase is the part that has occurred the target area, or the beginning in fresh target zone, if the part of existing target area, then upgrade the information of this target area, and judge whether each target connected region finishes.If the information that a new chained list node is stored this fresh target zone is then opened up in the fresh target zone.
(3-3), detecting the target connected region finishes, calculate the width of its boundary rectangle, if width is during greater than OBJ_WIDTH_min, think that then this connected region is a target, in the RECT_TAG structural array, and the number of target connected domain appears in target-marking connected domain and record count line with the information stores of this target, if width is less than OBJ_WIDTH_min, think that then this connected region is a decoy, does discard processing to this object block.
Capable parallax in counting line and out counting line repeats above-mentioned steps (3-1) ~ (3-3), realizes that moving target extracts and the serial mark, and g_iObjCountIn and g_iObjCountOut write down object appearing number in and the out counting line respectively.
Above-mentioned steps (4), cutting apart and merging above-mentioned moving target: above-mentioned moving target is cut apart the merging resume module through microprocessor by moving target.Because the crowded and illumination variation of passenger flow, some moving target merges easily, and some moving target then divides, and need cut apart accordingly and merge.
(4-1), when the number of target-marking has been not 0 on the counting line, detect the parallax grey level histogram and the area of each target area in the RECT_TAG array, judge according to the area of target area whether needs are cut apart in this target area, if its area is during greater than OBJ_AREA_TH0, execution in step (4-2), otherwise, execution in step (4-3).
(4-2), according to the parallax grey level histogram of this target area, certain ratio of parallax gray-scale value dynamic range as segmentation threshold, the target area that is lower than this threshold value is labeled as background, cut apart the circumscribed rectangular region execution in step 3 of back, this rectangular area is carried out level and smooth and mark again this target.
(4-3), detect on the counting line number of target-marking, if greater than 1, judge whether satisfy the condition that target merges in twos between target in the target-marking, if satisfy, merge target, and upgrade the information and the target number of target area in the structural array.Two target needs that satisfy following condition merge:
(1) two target is interrupted on time shaft and is no more than 3 frames.
(2) two targets have intersection in the horizontal direction, and the width that requires the intersection region is greater than 50% of the less target width of width in two targets.
The difference of the parallax mean value of (3) two target areas is less than OBJ_GRAY_DIFmax.
To the moving target repeated execution of steps (4-1) ~ (4-3) in counting line in the right view and the out counting line, realize cutting apart and merging of target in counting line and the out counting line respectively.
The coupling of above-mentioned steps (5), moving target, direction are judged and counting: above-mentioned moving target after merging, cutting apart is handled by the coupling and the counting module of moving target by microprocessor processes.
(5-1), detecting on the in counting line, whether the number g_iObjCountIn of target-marking is 0, if be not 0, detect the frame number frame_pass of each target process, if frame_pass is greater than FRAME_END, execution in step (5-2), if frame_pass is greater than FRAME_START, and less than FRAME_END, execution in step (5-3).
(5-2), this target do not obtain mating target in the matching range of out counting line, this target area information is deleted from the object construction array of in counting line.
(5-3), on the out counting line in the object appearing, the target of this target optimum matching on search and the in counting line, if obtain the optimum matching target,, judge the target travel direction according to barycenter position relation on time shaft of two coupling targets, the renewal counter of getting on or off the bus, if on the in counting line barycenter of target on the time shaft prior to the out counting line on the barycenter of target, then this target is for getting on the bus, otherwise, then, upgrade the counter of getting on or off the bus for getting off.The information of two coupling targets is deleted from the structural array of in counting line and out counting line respectively.When on the out counting line, having a plurality of target to be matched, obtain the optimum matching target according to cost function, cost function is defined as follows:
F(x，y
n)＝aS(x，y
n)+bD
x(x，y
n)+cD
y(x，y
n)
Target y to be matched on target x and the out line on this function calculation in counting line
nSimilarity, wherein, S (x, y
n) be x and y
nThe absolute value of difference of parallax average gray, D
x(x, y
n) be the horizontal direction distance between moving target, D
y(x, y
n) be the vertical direction distance between moving target, a, b, c are weighted values.F (x, y
n) value is more little, and more coupling of two targets be described, selection makes F (x, y
n) the minimum target y of value
nBe the optimum matching target.
Repetitive cycling execution in step 1 is finished bus passenger flow automatic counting to step 5.
Claims (6)
1. the bus passenger flow automatic counting method based on two-way parallactic space-time diagram is characterized in that this method of counting comprises the steps:
(1), obtain left and right two synchronization video image sequences, with parallel synchronous left and right video camera the direction vertical with the passenger moving direction and keep the in counting line of a determining deviation and the out counting line on form left and right each capable gray scale spacetime diagram of 2 width of cloth;
(2), calculate the parallax of the moving target in counting line and the out counting line, form the capable parallax spacetime diagram of 2 width of cloth moving targets on the double-counting line respectively by above line gray scale spacetime diagram;
(3), to the moving target in the above line parallax spacetime diagram extract, mark;
(4), above-mentioned target is cut apart and merged;
(5), moving target is carried out optimum matching, obtain the judgement of passenger flow direction of motion and finish automatic counting.
2. the bus passenger flow automatic counting method based on two-way parallactic space-time diagram according to claim 1, it is characterized in that, above-mentioned steps (2) generates row parallax spacetime diagram, and left and right capable gray scale spacetime diagram is handled by row parallax spacetime diagram generation module by microprocessor, and its concrete steps are as follows:
(2-1), adopt 3 every trade frame difference methods to detect possible moving target candidate point on the counting line, 3 row are meant current line and last 2 row, 3 row images gray scale difference absolute value sum between any two is poor as the current line frame, the threshold value of judging the motion candidate target is OBJ_TH, if the frame difference of current line pixel is greater than OBJ_TH, think that then this pixel is the moving region candidate point, otherwise think background dot;
(2-2), calculate parallax when the pre-treatment row, if pixel is the target candidate point, then calculate the parallax of this pixel, handle otherwise its parallax is used as 0, the parallax of pixel is done greyscale transformation, obtain the capable parallax of parallax gray scale in 0～255 scope at last;
(2-3), the capable parallax data that obtains on every frame count line is launched successively by time shaft, and get nearest fixed line number and form capable parallax spacetime diagram, in counting line and out counting line are repeated above-mentioned steps (2-1)～(2-3), obtain the capable parallax spacetime diagram of 2 width of cloth in counting line and the out counting line respectively.
3. the bus passenger flow automatic counting method based on two-way parallactic space-time diagram according to claim 2, it is characterized in that, above-mentioned steps (3) is to extraction, the mark of the moving target in the above line parallax spacetime diagram, above-mentioned left and right capable parallax spacetime diagram is handled by the extraction and the serial mark module of moving target by microprocessor, and its concrete steps are as follows:
(3-1), adopt 3 * 11 morphology smoothing operator that the parallax of current line is carried out smoothing processing, 3 row parallaxes are current line parallax and each delegation's parallax of front and back, so row parallax spacetime diagram postpones a frame in time than capable gray scale spacetime diagram;
(3-2), judge that according to the parallax of moving target whether current line is to have real moving target, if the pixel parallax value, is then thought the moving target point greater than PARA_MIN, otherwise just thinks background dot; Occur when detecting, then upgrade the information of this target area, and judge whether each target connected region finishes, if the information that a new chained list node is stored this fresh target zone is then opened up in the fresh target zone when the pre-treatment row has target;
(3-3), detecting the target connected region finishes, calculate the width of its boundary rectangle, if width is during greater than OBJ_WIDTH_min, think that then this connected region is a target, with the information stores of this target in the RECT_TAG structural array, and the number of target connected domain appears in target-marking connected domain and record count line, if width is less than OBJ_WIDTH_min, think that then this connected region is a decoy, this object block is done discard processing, capable parallax in counting line and out counting line repeats above-mentioned steps (3-1)～(3-3), realizes that moving target extracts and the serial mark.
4. the bus passenger flow automatic counting method based on two-way parallactic space-time diagram according to claim 3, it is characterized in that, above-mentioned steps (4) is cut apart and is merged above-mentioned moving target, above-mentioned moving target is cut apart resume module through microprocessor by the merging of moving target, and its concrete steps are as follows:
(4-1), when the number of target-marking has been not 0 on the counting line, detect the parallax grey level histogram and the area of each target area in the RECT_TAG array, judge according to the area of target area whether needs are cut apart in this target area, if its area is during greater than OBJ_AREA_TH0, execution in step (4-2), otherwise, execution in step (4-3);
(4-2), according to the parallax grey level histogram of this target area, certain ratio of parallax gray-scale value dynamic range as segmentation threshold, is labeled as background to the target area that is lower than this threshold value, cut apart the back to the circumscribed rectangular region execution in step (4-3) of this target;
(4-3), detect on the counting line number of target-marking, if greater than 1, judge and whether satisfy the condition that target merges in twos between target in the target-marking, if satisfy, merge target, and the information and the target number of target area in the renewal structural array, two target needs that satisfy following condition merge:
(1) two target is interrupted on time shaft and is no more than 3 frames;
(2) two targets have intersection in the horizontal direction, and the width that requires the intersection region is greater than 50% of the less target width of width in two targets;
The difference of the parallax mean value of (3) two target areas is less than OBJ_GRAY_DIFmax,
To the moving target repeated execution of steps (4-1)～(4-3) in counting line in the right view and the out counting line, realize cutting apart and merging of target in counting line and the out counting line respectively.
5. the bus passenger flow automatic counting method based on two-way parallactic space-time diagram according to claim 4, it is characterized in that, the coupling of above-mentioned steps (5), moving target, direction are judged and counting, above-mentioned moving target after cutting apart, merging is handled by the coupling and the counting module of moving target by microprocessor processes, and its concrete steps are as follows:
(5-1), detecting on the in counting line, whether the number g_iObjCountIn of target-marking is 0, if be not 0, detect the frame number frame_pass of each target process, if frame_pass is greater than FRAME_END, execution in step (5-2), if frame_pass is greater than FRAME_START, and less than FRAME_END, execution in step (5-3);
(5-2), above-mentioned target do not obtain mating target in the matching range of out counting line, this target area information is deleted from the object construction array of in counting line;
(5-3), on the out counting line in the object appearing, the optimum matching target of target to be matched on search and the in counting line, if obtain the optimum matching target, barycenter position relation on time shaft according to two coupling targets, judge the target travel direction, if on the in counting line barycenter of target on the time shaft prior to the out counting line on the barycenter of target, then this target is for getting on the bus, otherwise, then for getting off, the renewal counter of getting on or off the bus is deleted the information of two coupling targets respectively from the structural array of in counting line and out counting line.
6. bus passenger flow automatic counting system based on two-way parallactic space-time diagram, be applied to the bus passenger flow automatic counting method based on two-way parallactic space-time diagram according to claim 1, it comprises a parallel synchronous left side that is contained in the bus door top, right video camera, microprocessor, microprocessor comprises capable gray scale spacetime diagram generation module, row parallax spacetime diagram generation module, the extraction of moving target and serial mark module, cutting apart and the merging module of moving target, moving target coupling and direction are judged and counting module a left side, right video camera links to each other with microprocessor respectively; Above-mentioned microprocessor is connected to the infrared LED lamp.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2009100525973A CN101567097B (en) | 2009-06-05 | 2009-06-05 | Bus passenger flow automatic counting method based on two-way parallactic space-time diagram and system thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2009100525973A CN101567097B (en) | 2009-06-05 | 2009-06-05 | Bus passenger flow automatic counting method based on two-way parallactic space-time diagram and system thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101567097A CN101567097A (en) | 2009-10-28 |
| CN101567097B true CN101567097B (en) | 2011-05-04 |
Family
ID=41283241
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2009100525973A Expired - Fee Related CN101567097B (en) | 2009-06-05 | 2009-06-05 | Bus passenger flow automatic counting method based on two-way parallactic space-time diagram and system thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101567097B (en) |
Families Citing this family (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102369550B (en) * | 2009-03-31 | 2014-01-01 | 松下电器产业株式会社 | Stereo image processor and stereo image processing method |
| GB2476500B (en) * | 2009-12-24 | 2012-06-20 | Infrared Integrated Syst Ltd | Activity mapping system |
| CN101777188B (en) * | 2010-03-12 | 2012-06-13 | 华中科技大学 | Real-time bus passenger flow volume statistical method |
| EP2602761A4 (en) * | 2010-08-03 | 2017-11-01 | Panasonic Intellectual Property Management Co., Ltd. | Object detection device, object detection method, and program |
| CN102651086B (en) * | 2011-02-28 | 2015-07-29 | 北京海兰德维通信技术有限公司 | A kind of counting assembly, method and infrared detection system |
| CN102184587A (en) * | 2011-06-01 | 2011-09-14 | 洞头县亿纬自动化设备厂 | Light curtain type passenger flow counter |
| CN103310213B (en) * | 2012-03-07 | 2016-05-25 | 株式会社理光 | Vehicle checking method and device |
| CN103595916A (en) * | 2013-11-11 | 2014-02-19 | 南京邮电大学 | Double-camera target tracking system and implementation method thereof |
| CN104408746B (en) * | 2014-11-21 | 2017-07-14 | 安徽清新互联信息科技有限公司 | A kind of passenger flow statistical system based on depth information |
| CN104392522B (en) * | 2014-11-21 | 2016-08-24 | 安徽清新互联信息科技有限公司 | A kind of passenger flow statistical system based on pseudo-depth information |
| CN105893962A (en) * | 2016-03-31 | 2016-08-24 | 成都信息工程大学 | Method for counting passenger flow at airport security check counter |
-
2009
- 2009-06-05 CN CN2009100525973A patent/CN101567097B/en not_active Expired - Fee Related
Also Published As
| Publication number | Publication date |
|---|---|
| CN101567097A (en) | 2009-10-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101567097B (en) | Bus passenger flow automatic counting method based on two-way parallactic space-time diagram and system thereof | |
| CN107766821B (en) | Method and system for detecting and tracking full-time vehicle in video based on Kalman filtering and deep learning | |
| CN109147331B (en) | Road congestion state detection method based on computer vision | |
| Zhu et al. | VISATRAM: A real-time vision system for automatic traffic monitoring | |
| CN104751634B (en) | The integrated application method of freeway tunnel driving image acquisition information | |
| Lai et al. | Image-based vehicle tracking and classification on the highway | |
| CN110765922A (en) | AGV is with two mesh vision object detection barrier systems | |
| CN104902258A (en) | Multi-scene pedestrian volume counting method and system based on stereoscopic vision and binocular camera | |
| CN103150559B (en) | Head recognition and tracking method based on Kinect three-dimensional depth image | |
| CN104517095B (en) | A kind of number of people dividing method based on depth image | |
| CN102324183B (en) | Method for detecting and shooting vehicle based on composite virtual coil | |
| CN111360780A (en) | Garbage picking robot based on visual semantic SLAM | |
| CN103150903B (en) | Video vehicle detection method for adaptive learning | |
| CN102496281B (en) | Vehicle red-light violation detection method based on combination of tracking and virtual loop | |
| CN106127137A (en) | A kind of target detection recognizer based on 3D trajectory analysis | |
| CN102722982A (en) | Background and inter-frame difference algorithm-based traffic flow and motion state detection method | |
| CN103021059A (en) | Video-monitoring-based public transport passenger flow counting method | |
| CN101976504B (en) | Multi-vehicle video tracking method based on color space information | |
| CN105760846A (en) | Object detection and location method and system based on depth data | |
| CN110969131B (en) | Subway people flow counting method based on scene flow | |
| CN102073852A (en) | Multiple vehicle segmentation method based on optimum threshold values and random labeling method for multiple vehicles | |
| CN116824859B (en) | Intelligent traffic big data analysis system based on Internet of things | |
| CN106339657A (en) | Straw incineration monitoring method and device based on monitoring video | |
| CN103794050A (en) | Real-time transport vehicle detecting and tracking method | |
| CN103077387A (en) | Method for automatically detecting carriage of freight train in video |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| C17 | Cessation of patent right | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20110504 Termination date: 20140605 |