CN104239908A - Intelligent ridership automatic statistical method based on self-adaptive threshold value - Google Patents
Intelligent ridership automatic statistical method based on self-adaptive threshold value Download PDFInfo
- Publication number
- CN104239908A CN104239908A CN201410363764.7A CN201410363764A CN104239908A CN 104239908 A CN104239908 A CN 104239908A CN 201410363764 A CN201410363764 A CN 201410363764A CN 104239908 A CN104239908 A CN 104239908A
- Authority
- CN
- China
- Prior art keywords
- ridership
- detection block
- pixel
- passenger
- foreground
- 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
- 238000007619 statistical method Methods 0.000 title abstract description 7
- 238000000034 method Methods 0.000 claims abstract description 55
- 230000006399 behavior Effects 0.000 claims abstract description 11
- 238000001514 detection method Methods 0.000 claims description 70
- 230000003044 adaptive effect Effects 0.000 claims description 22
- 238000004422 calculation algorithm Methods 0.000 claims description 10
- 239000000284 extract Substances 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 5
- 230000008859 change Effects 0.000 claims description 4
- 230000007306 turnover Effects 0.000 claims description 2
- 238000012544 monitoring process Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 4
- 230000033001 locomotion Effects 0.000 description 4
- PCTMTFRHKVHKIS-BMFZQQSSSA-N (1s,3r,4e,6e,8e,10e,12e,14e,16e,18s,19r,20r,21s,25r,27r,30r,31r,33s,35r,37s,38r)-3-[(2r,3s,4s,5s,6r)-4-amino-3,5-dihydroxy-6-methyloxan-2-yl]oxy-19,25,27,30,31,33,35,37-octahydroxy-18,20,21-trimethyl-23-oxo-22,39-dioxabicyclo[33.3.1]nonatriaconta-4,6,8,10 Chemical compound C1C=C2C[C@@H](OS(O)(=O)=O)CC[C@]2(C)[C@@H]2[C@@H]1[C@@H]1CC[C@H]([C@H](C)CCCC(C)C)[C@@]1(C)CC2.O[C@H]1[C@@H](N)[C@H](O)[C@@H](C)O[C@H]1O[C@H]1/C=C/C=C/C=C/C=C/C=C/C=C/C=C/[C@H](C)[C@@H](O)[C@@H](C)[C@H](C)OC(=O)C[C@H](O)C[C@H](O)CC[C@@H](O)[C@H](O)C[C@H](O)C[C@](O)(C[C@H](O)[C@H]2C(O)=O)O[C@H]2C1 PCTMTFRHKVHKIS-BMFZQQSSSA-N 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000037237 body shape Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000011897 real-time detection Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses an intelligent ridership automatic statistical method based on a self-adaptive threshold value. The method comprises the following steps that a video sequence of a detecting zone is collected in real time through monitoring equipment, and a foreground moving target is extracted from the video sequence obtained by collecting; according to a practical application scene and the distance between a camera and the detecting zone, the position and the size of a ridership detecting frame are set; based on video information and the ridership detecting frame, the self-adaptive threshold value is generated by unsupervised learning; a method based on the geometry principle is used for judging the behavior of passenger getting-on or getting-off on the ridership detecting frame; and according to the judging results and the self-adaptive threshold value, the ridership is subjected to judging and statistics. The method is simple and efficient, practicability and portability are high, and the method is suitable for intelligent automatic statistics of the passenger car ridership.
Description
Technical field
The present invention relates to the video intelligent such as Video processing, image procossing analysis technical field, particularly relate to a kind of intelligent ridership method for automatically counting based on adaptive threshold.
Background technology
Flow of the people programming count is an important function in intelligent video monitoring system, and it can be effectively applied to the public places such as market, bus, subway gateway.Intelligent bus is the inevitable pattern of following public transport development, has great significance to the intellectuality realizing public transport to the programming count of bus ridership.
The existing people flow rate statistical method based on computer vision technique mainly comprises following a few class at present:
(1) method of detection and tracking is takeed on based on the number of people or head.The method is effectively to detect the number of people in video or head shoulder, and follows the tracks of to it object reaching statistics flow of the people.Such as: application number is 201210208666.7, denomination of invention is " a kind of people flow rate statistical method based on Video Analysis Technology ", application people is the patented claim of Wuhan Fenghuo Zhongzhi Digital Technology Co., Ltd., carry out the detection of number of people characteristic area according to the detection and Identification of number of people characteristic sum body local feature, and adopt tracking technique to obtain pedestrian movement's track to judge direction and the flow of pedestrian; Application number is PCT/CN2010/070607, denomination of invention is " method and system of people flow rate statistical ", application people is the patented claim of Hangzhou Haikang Weishi Software Co., Ltd., then adopt each number of people of multiclass number of people detection of classifier in parallel, and respectively tracking formation number of people target trajectory is carried out to each number of people, finally carry out flow of the people counting according to this movement locus direction; Application number is 201210316862, denomination of invention is " the elevator people flow rate statistical method and system based on intelligent vision perception ", application people is the patented claim of University of Electronic Science and Technology, detect the target in realtime graphic according to the head shoulder model bank set up in advance, line trace of going forward side by side is to reach the object of people flow rate statistical.The validity feature that these class methods need to extract the number of people or head shoulder or carry out a large amount of positive and negative sample training to produce effective sorter, to realize the detection of the number of people or head shoulder accurately, but it easily produces higher false alarm rate, and need tracking technique to obtain target trajectory, this considerably increases the operand of algorithm.
(2) based on the method for human body segmentation.These class methods carry out human detection to video sequence, need the priori of human body, such as body shape, marginal information etc., with Statistics Bar flow of the people.Such as: application number is 201110423349, denomination of invention is " a kind of people flow rate statistical method based on many Gausses counter model ", applicant is the patented claim of Chongqing Mail and Telephones Unvi, the training video sequence image Sample Establishing many Gausses counter model utilizing band number to mark, then based on the pedestrian's number comprised in this model analysis Unknown Motion target area, thus people flow rate statistical is realized; Application number is 201110147358, denomination of invention is " pedestrian traffic statistical method based on heuristic information ", application people is the patented claim of Electronic University Of Science & Technology Of Hangzhou, the method based on gradient orientation histogram is then adopted to carry out pedestrian detection, and produce weight by the ratio relation of the point on some testing results and specific region, finally adopt the size and Orientation of sparse optical flow method determination motion vector, to reach the object of pedestrian's traffic statistics.These class methods are not only difficult to effectively solve occlusion issue, and comparatively large to the detection calculations amount of characteristics of human body, are difficult to realize real-time detection.
Summary of the invention
The object of the invention is to the shortcoming and defect overcoming prior art existence, a kind of quick and efficient intelligent ridership method for automatically counting based on adaptive threshold is provided, the method adopts the method for unsupervised learning generation adaptive threshold to carry out number judgement, and adopt the method based on geometry principle to carry out the judgement of passenger getting on/off, and in conjunction with video processing technique, reach accurate, in real time intelligent bus ridership is added up, last again by ridership statistics by wired or wireless communication apparatus Real-time Feedback on bus dispatching center and the bus platform electronical display terminal that do not arrive, in time for supvr and passenger provide real-time bus carrying information.
In order to realize above-mentioned purpose of the present invention, the invention provides a kind of intelligent ridership method for automatically counting based on adaptive threshold, the method comprises the following steps:
Step 1, by the video sequence of watch-dog Real-time Collection one surveyed area, and extracts foreground moving object to the video sequence collected;
Step 2, according to practical application scene and camera to the distance of surveyed area, arranges position and the size of ridership detection block;
Step 3, based on video information and described ridership detection block, produces adaptive threshold by unsupervised learning;
Step 4, adopts the method based on geometry principle described ridership detection block to be carried out to the judgement of passenger loading or behavior of getting off;
Step 5, according to result of determination and the described adaptive threshold of described step 4, carries out judging for the volume of the flow of passengers and adds up.
Beneficial effect of the present invention is:
(1) by arranging ridership detection block, the scope of detection can be reduced, improving the efficiency of algorithm;
(2) only need to obtain foreground pixel number in detection block as handling object, and do not need to carry out the operations such as complicated identification, greatly reduce the operand of algorithm, improve the real-time of algorithm;
(3) unsupervised learning is carried out to the foreground pixel number in the detection block detected, and then produce adaptive threshold, be used for distinguishing once through the number of detection block, avoid using track algorithm to solve occlusion issue, reduce calculated amount further;
(4) only adopt the geometry principle between the foreground pixel number in detection block and detection block is analyzed, the effective decision method to passenger loading or event of getting off can be produced, improve speed and the efficiency of algorithm;
(5) by wireless senser, traffic statistics result is sent to platform electronical display terminal, adds the practicality of system.
The present invention is simple, stable performance, and speed is fast, and efficiency is high, portable strong, has stronger real-time, is applicable to the ridership statistics of intelligent bus passenger vehicle.
Accompanying drawing explanation
Fig. 1 is the process flow diagram of the intelligent ridership method for automatically counting that the present invention is based on adaptive threshold;
Fig. 2 according to an embodiment of the invention ridership detection block arranges schematic diagram;
Fig. 3 is passenger loading and the schematic diagram judged of getting off according to an embodiment of the invention;
Fig. 4 is according to the intelligent ridership method for automatically counting experiment simulation figure based on adaptive threshold in the present invention.
embodiment
For making the object, technical solutions and advantages of the present invention clearly understand, below in conjunction with specific embodiment, and with reference to accompanying drawing, the present invention is described in more detail.
The present invention proposes a kind of intelligent ridership method for automatically counting based on adaptive threshold, the method can be used for the place that the passengers such as public transport frequently come in and go out, for convenience's sake, next for bus, the present invention is further detailed.
Fig. 1 is the process flow diagram of the intelligent ridership method for automatically counting that the present invention is based on adaptive threshold.As shown in Figure 1, described method comprises the steps:
Step 1, by the video sequence of watch-dog Real-time Collection one surveyed area, and extracts foreground moving object to the video sequence collected;
In an embodiment of the present invention, utilize background subtraction combining form to process and foreground moving object is extracted to the video sequence collected, wherein, background subtraction and Morphological scale-space method are image processing techniques well known to those skilled in the art, and therefore not to repeat here.
In actual applications, the boarding area of bus can be chosen, the position that such as front area is added up as ridership, monitoring camera staticly can be arranged on the top of the inner front area of bus, and be tilted to down (need not completely vertically downward) and extract passenger flow information, video acquisition speed can be set to 25 frames/second.
Step 2, according to practical application scene and the camera distance to surveyed area, position and the size of ridership detection block are set, wherein, what the position of described ridership detection block was set in passenger's turnover must through region and the length of described ridership detection block is greater than the width that passenger passes in and out region;
Fig. 2 is that ridership detection block arranges schematic diagram according to an embodiment of the invention, in an embodiment of the present invention, while guaranteeing ridership statistical efficiency, reduce sensing range as much as possible, to improve detection speed, therefore, ridership detection block length and wide when arranging the following constraint condition of demand fulfillment:
I. the width W of detection block meets: 2W
h≤ W≤3W
h;
Ii. the length L of detection block meets: L >=BC.
Wherein, W
hfor the valuation of number of people diameter round in video frame images, BC is the width of surveyed area, and in Fig. 2, the rectangle ABCD of dash area represents boarding area, bus Qianmen, and BC is its width, and the square frame being positioned at middle part is set ridership detection block.
Step 3, based on video information and described ridership detection block, produces adaptive threshold by unsupervised learning;
Described step 3 is further comprising the steps:
Step 31, the non-zero foreground pixel value produced when having passenger to enter described detection block in N two field picture before statistics, obtains the individual foreground pixel value of m (m<N);
Step 32, adopts the clustering algorithms such as K-means foreground pixel value to be divided into K class, gets the average of K class cluster central value as described adaptive threshold.
For bus, because each passenger got on the bus from Qianmen mostly is two passengers most, therefore number of clusters K can be taken as 2 in the clustering algorithms such as K-means.Along with the increase of N, the situation that different passenger gets on the bus by different way is more and more comprehensive, and data capacity m is also increasing, and the threshold value obtained by clustering algorithm also just more and more adapts to the judgement of patronage.When passenger enter the non-zero foreground pixel value produced in detection block be greater than this threshold value time, then judge that the patronage of this time getting on the bus is as 2 people, otherwise be 1 people.
Step 4, adopts the method based on geometry principle described ridership detection block to be carried out to the judgement of passenger loading or behavior of getting off;
Consider the traffic-operating period of actual bus, when crowded, also may there is the behavior of passenger getting off car in passenger car front door, so in order to accurate count bus ridership situation, needs all to judge passenger getting on/off behavior.
Described step 4 is further comprising the steps:
Step 41, is divided into multiple subregion by described ridership detection block;
Fig. 3 is passenger loading according to an embodiment of the invention and judgement schematic diagram of getting off, as shown in Figure 3, in an embodiment of the present invention, line segment EH and line segment FG can be used rectangle ABCD to be divided into three little rectangles, wherein, rectangle ABCD be before arrange ridership detection block.
Step 42, calculates the foreground target elemental area that in described subregion, passenger produces;
Suppose that in Fig. 3, oval representative produces foreground target by passenger, then in Fig. 3, black part is expressed as the foreground pixel area that foreground target enters into rectangle AEHD and rectangle FBCG generation, respectively called after S1, S2 or S3, S4, as shown in Figure 3 A and Figure 3 B.
Step 43, judges the behavior of getting on the bus or get off of passenger in described ridership detection block according to the change of the foreground target elemental area of passenger's generation in same subregion.
In an embodiment of the present invention, can according to two sub regions being arranged in described ridership detection block upper end and bottom, the change of the foreground target elemental area that passenger produces judges getting on the bus of passenger or behavior of getting off, namely, suppose that passenger is when entering the state shown in Fig. 3 B by the state shown in Fig. 3 A, then judge getting on the bus of passenger or behavior of getting off by following formula by the process of ridership detection block:
Step 5, according to result of determination and the described adaptive threshold of described step 4, carries out judging for the volume of the flow of passengers and adds up.
Described step 5 is further comprising the steps:
Step 51, the value of parameter is initialized as 0, described parameter at least comprises: parameter f lag=false, parameter up=true, the minimum pixel value low_pixel of prospect in ridership detection block, foreground pixel value last_pixel in the max pixel value high_pixel of prospect in ridership detection block, the foreground pixel value current_Fgpixel in video present frame detection block and video former frame detection block;
Step 52, judges that whether current image frame is the first frame of video sequence, if so, then makes low_pixel=high_pixel=current_Fgpixel, otherwise, if current_Fgpixel-last_Fgpixel>=0, then make up=true, if current_Fgpixel-low_pixel>Thresh, flag=false, up=true tri-conditions are all satisfied, wherein, Thresh represents an empirical value, generally gets 1/10th of high_pixel, now be judged as that passenger enters ridership detection block, make flag=true, in calculation procedure 4, foreground target enters the foreground pixel area in ridership detection block top subregion and bottom subregion simultaneously, such as foreground pixel area S1 and S2, as flag=true, the moment upgrades the value of high_pixel, makes it get maximal value in both high_pixel, current_Fgpixel, if high_pixel-current_Fgpixel>Thresh, flag=true two conditions meet simultaneously, now be judged as that passenger walks out ridership detection block, then make flag=false, up=false, in calculation procedure 4, foreground target enters the foreground pixel area in ridership detection block top subregion and bottom subregion simultaneously, such as foreground pixel area S3 and S4, then according to the foreground pixel area S1 obtained, S2, S3 and S4 the judgement of passenger getting on/off event in integrating step 4, show that this prospect belongs to the event of getting on the bus through ridership detection block or gets off event,
Step 53, compares the adaptive threshold that high_pixel and described step 3 obtain, if high_pixel value is comparatively large, then adds 2 to the flowmeter numerical value of the above-mentioned event of getting on the bus that determines or event of getting off; Otherwise its flowmeter numerical value adds 1, so namely statistics obtains the volume of the flow of passengers.
It should be noted that, in embodiments of the present invention, for the definition of passenger getting on/off event in step 4, can according to actual conditions accurate definition direction for another direction of the event of getting on the bus be the event of getting off.
Fig. 4 is the application example figure of the intelligent ridership method for automatically counting that the present invention is based on adaptive threshold, left figure in Fig. 4 be detection block schematic diagram is set, as shown in black box, and to define up be the event of getting on the bus, descending is the event of getting off, middle figure in Fig. 4 is detection block foreground detection result figure, and the right figure in Fig. 4 is the result figure of pedestrian count.
Draw according to Multi simulation running experimental result, pedestrian's flow method for automatically counting that the present invention proposes can automatic accurate geo-statistic ridership.
Above-described specific embodiment; object of the present invention, technical scheme and beneficial effect are further described; be understood that; the foregoing is only specific embodiments of the invention; be not limited to the present invention; within the spirit and principles in the present invention all, any amendment made, equivalent replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (8)
1., based on an intelligent ridership method for automatically counting for adaptive threshold, it is characterized in that, the method comprises the following steps:
Step 1, by the video sequence of watch-dog Real-time Collection one surveyed area, and extracts foreground moving object to the video sequence collected;
Step 2, according to practical application scene and camera to the distance of surveyed area, arranges position and the size of ridership detection block;
Step 3, based on video information and described ridership detection block, produces adaptive threshold by unsupervised learning;
Step 4, adopts the method based on geometry principle described ridership detection block to be carried out to the judgement of passenger loading or behavior of getting off;
Step 5, according to result of determination and the described adaptive threshold of described step 4, carries out judging for the volume of the flow of passengers and adds up.
2. method according to claim 1, is characterized in that, in described step 1, utilizes background subtraction combining form to process and extracts foreground moving object to the video sequence collected.
3. method according to claim 1, is characterized in that, in described step 2, what the position of described ridership detection block was set in passenger's turnover must through region and the length of described ridership detection block is greater than the width that passenger passes in and out region.
4. method according to claim 1, is characterized in that, in described step 2, and the length of described ridership detection block and widely meet following constraint condition:
I. the width W of detection block meets: 2W
h≤ W≤3W
h;
Ii. the length L of detection block meets: L >=BC;
Wherein, W
hfor the valuation of number of people diameter round in video frame images, BC is the width of surveyed area.
5. method according to claim 1, is characterized in that, described step 3 is further comprising the steps:
Step 31, the non-zero foreground pixel value produced when having passenger to enter described ridership detection block in N two field picture before statistics, obtains m foreground pixel value, wherein, m<N;
Step 32, adopts clustering algorithm that foreground pixel value is divided into K class, gets the average of K class cluster central value as described adaptive threshold.
6. method according to claim 1, is characterized in that, described step 4 is further comprising the steps:
Step 41, is divided into multiple subregion by described ridership detection block;
Step 42, calculates the foreground target elemental area that in described subregion, passenger produces;
Step 43, judges the behavior of getting on the bus or get off of passenger in described ridership detection block according to the change of the foreground target elemental area of passenger's generation in same subregion.
7. method according to claim 6, it is characterized in that, in described step 43, according to two sub regions being arranged in described ridership detection block upper end and bottom, the change of the foreground target elemental area that passenger produces judges getting on the bus of passenger or behavior of getting off.
8. method according to claim 1, is characterized in that, described step 5 is further comprising the steps:
Step 51, the value of parameter is initialized as 0, described parameter at least comprises: parameter f lag=false, parameter up=true, the minimum pixel value low_pixel of prospect in ridership detection block, foreground pixel value last_pixel in the max pixel value high_pixel of prospect in ridership detection block, the foreground pixel value current_Fgpixel in video present frame detection block and video former frame detection block;
Step 52, judges that whether current image frame is the first frame of video sequence, if so, then makes low_pixel=high_pixel=current_Fgpixel;
Otherwise, if current_Fgpixel-last_Fgpixel>=0, then make up=true; If current_Fgpixel-low_pixel>Thresh, flag=false, up=true tri-conditions are all satisfied, wherein, Thresh represents empirical value, now judge that passenger enters ridership detection block, make flag=true, calculating foreground target enters the foreground pixel area in ridership detection block top subregion and bottom subregion simultaneously; As flag=true, upgrade the value of high_pixel, make it get maximal value in both high_pixel, current_Fgpixel; If high_pixel-current_Fgpixel>Thresh, flag=true two conditions meet simultaneously, now judge that passenger walks out ridership detection block, then make flag=false, up=false, calculating foreground target enters the foreground pixel area in ridership detection block top subregion and bottom subregion again, then according to the foreground pixel area that obtains in conjunction with the result of determination of described step 4, judge that this prospect belongs to the event of getting on the bus through ridership detection block or gets off event;
Step 53, compares the adaptive threshold that high_pixel and described step 3 obtain, if high_pixel value is comparatively large, then adds 2 to the flowmeter numerical value of the above-mentioned event of getting on the bus that determines or event of getting off; Otherwise its flowmeter numerical value adds 1, namely statistics obtains the volume of the flow of passengers.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410363764.7A CN104239908A (en) | 2014-07-28 | 2014-07-28 | Intelligent ridership automatic statistical method based on self-adaptive threshold value |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410363764.7A CN104239908A (en) | 2014-07-28 | 2014-07-28 | Intelligent ridership automatic statistical method based on self-adaptive threshold value |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104239908A true CN104239908A (en) | 2014-12-24 |
Family
ID=52227931
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410363764.7A Pending CN104239908A (en) | 2014-07-28 | 2014-07-28 | Intelligent ridership automatic statistical method based on self-adaptive threshold value |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104239908A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105551266A (en) * | 2015-12-08 | 2016-05-04 | 合肥寰景信息技术有限公司 | Method of calculating pedestrian flow threshold of traffic signal controller |
| CN112333431A (en) * | 2020-10-30 | 2021-02-05 | 深圳市商汤科技有限公司 | Scene monitoring method and device, electronic equipment and storage medium |
| CN113870604A (en) * | 2021-09-29 | 2021-12-31 | 湖南省交通规划勘察设计院有限公司 | Method and system for realizing reasonable allocation and coordination of traffic hub passenger flow based on mobile phone signaling |
| CN116563287A (en) * | 2023-07-10 | 2023-08-08 | 长沙海信智能系统研究院有限公司 | Passenger flow volume detection method of bus and electronic equipment |
| WO2023159371A1 (en) * | 2022-02-23 | 2023-08-31 | 京东方科技集团股份有限公司 | Traffic statistical method and apparatus |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060227862A1 (en) * | 2005-04-06 | 2006-10-12 | March Networks Corporation | Method and system for counting moving objects in a digital video stream |
| CN101231755A (en) * | 2007-01-25 | 2008-07-30 | 上海遥薇实业有限公司 | Moving target tracking and quantity statistics method |
| CN101383005A (en) * | 2007-09-06 | 2009-03-11 | 上海遥薇实业有限公司 | Method for separating passenger target image and background by auxiliary regular veins |
| US7787656B2 (en) * | 2007-03-01 | 2010-08-31 | Huper Laboratories Co., Ltd. | Method for counting people passing through a gate |
| CN102622578A (en) * | 2012-02-06 | 2012-08-01 | 中山大学 | Passenger counting system and passenger counting method |
| US8295545B2 (en) * | 2008-11-17 | 2012-10-23 | International Business Machines Corporation | System and method for model based people counting |
| CN103021059A (en) * | 2012-12-12 | 2013-04-03 | 天津大学 | Video-monitoring-based public transport passenger flow counting method |
-
2014
- 2014-07-28 CN CN201410363764.7A patent/CN104239908A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060227862A1 (en) * | 2005-04-06 | 2006-10-12 | March Networks Corporation | Method and system for counting moving objects in a digital video stream |
| CN101231755A (en) * | 2007-01-25 | 2008-07-30 | 上海遥薇实业有限公司 | Moving target tracking and quantity statistics method |
| US7787656B2 (en) * | 2007-03-01 | 2010-08-31 | Huper Laboratories Co., Ltd. | Method for counting people passing through a gate |
| CN101383005A (en) * | 2007-09-06 | 2009-03-11 | 上海遥薇实业有限公司 | Method for separating passenger target image and background by auxiliary regular veins |
| US8295545B2 (en) * | 2008-11-17 | 2012-10-23 | International Business Machines Corporation | System and method for model based people counting |
| CN102622578A (en) * | 2012-02-06 | 2012-08-01 | 中山大学 | Passenger counting system and passenger counting method |
| CN103021059A (en) * | 2012-12-12 | 2013-04-03 | 天津大学 | Video-monitoring-based public transport passenger flow counting method |
Non-Patent Citations (1)
| Title |
|---|
| 郭荣庆等: "公交车人流量检测系统设计", 《长安大学学报（自然科学版）》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105551266A (en) * | 2015-12-08 | 2016-05-04 | 合肥寰景信息技术有限公司 | Method of calculating pedestrian flow threshold of traffic signal controller |
| CN112333431A (en) * | 2020-10-30 | 2021-02-05 | 深圳市商汤科技有限公司 | Scene monitoring method and device, electronic equipment and storage medium |
| CN113870604A (en) * | 2021-09-29 | 2021-12-31 | 湖南省交通规划勘察设计院有限公司 | Method and system for realizing reasonable allocation and coordination of traffic hub passenger flow based on mobile phone signaling |
| WO2023159371A1 (en) * | 2022-02-23 | 2023-08-31 | 京东方科技集团股份有限公司 | Traffic statistical method and apparatus |
| CN116563287A (en) * | 2023-07-10 | 2023-08-08 | 长沙海信智能系统研究院有限公司 | Passenger flow volume detection method of bus and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104933710B (en) | Based on the shop stream of people track intelligent analysis method under monitor video | |
| CN107491720A (en) | A kind of model recognizing method based on modified convolutional neural networks | |
| Li et al. | Abandoned objects detection using double illumination invariant foreground masks | |
| CN110188807A (en) | Tunnel pedestrian target detection method based on cascade super-resolution network and improvement Faster R-CNN | |
| CN104239908A (en) | Intelligent ridership automatic statistical method based on self-adaptive threshold value | |
| CN101727570B (en) | Tracking method, track detection processing unit and monitor system | |
| JP2007128513A (en) | Scene analysis | |
| CN103310194A (en) | Method for detecting head and shoulders of pedestrian in video based on overhead pixel gradient direction | |
| CN104715244A (en) | Multi-viewing-angle face detection method based on skin color segmentation and machine learning | |
| CN105138982A (en) | Crowd abnormity detection and evaluation method based on multi-characteristic cluster and classification | |
| CN108230364A (en) | A kind of foreground object motion state analysis method based on neural network | |
| CN103400113B (en) | Freeway tunnel pedestrian detection method based on image procossing | |
| CN102737386A (en) | Moving target anti-fusion shielding tracking algorithm | |
| CN108229256A (en) | A kind of road construction detection method and device | |
| CN107483894A (en) | Judge to realize the high ferro station video monitoring system of passenger transportation management based on scene | |
| Zhang et al. | Vision-based vehicle detecting and counting for traffic flow analysis | |
| CN109918971A (en) | Number detection method and device in monitor video | |
| CN104616006A (en) | Surveillance video oriented bearded face detection method | |
| CN110569819A (en) | Bus passenger re-identification method | |
| CN111062319A (en) | Driver call detection method based on active infrared image | |
| Liu et al. | A technology for automatically counting bus passenger based on YOLOv2 and MIL algorithm | |
| CN109816003A (en) | A kind of intelligent vehicle front Multi-Target Classification Method based on improvement HOG-LBP feature | |
| CN104077788B (en) | Moving object detection method fusing color and texture information for performing block background modeling | |
| CN111027482B (en) | Behavior analysis method and device based on motion vector segmentation analysis | |
| CN107240111B (en) | Edge communication segmentation passenger flow statistical method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20141224 |