CN103093273A - Video people counting method based on body weight recognition - Google Patents
Video people counting method based on body weight recognition Download PDFInfo
- Publication number
- CN103093273A CN103093273A CN2012105905152A CN201210590515A CN103093273A CN 103093273 A CN103093273 A CN 103093273A CN 2012105905152 A CN2012105905152 A CN 2012105905152A CN 201210590515 A CN201210590515 A CN 201210590515A CN 103093273 A CN103093273 A CN 103093273A
- Authority
- CN
- China
- Prior art keywords
- human body
- vector
- image
- body image
- reference vector
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Landscapes
- Image Analysis (AREA)
Abstract
The invention provides a video people counting method based on body weight recognition. The method comprises that a human body image in a video image is detected; the feature vector of the human body image is determined, the determined feature vector is matched with a plurality of reference vectors collected in advance in a data base; if matching is not successful, the corresponding reference vector is acquired according to the detected human body image, the human body image and the reference vector corresponding to the human body image are added into the data base, and meanwhile plus-one operation is carried out in a counter. According to the method, the human body image can be determined in the data base, the determined human body image is used as the detected human body image, and accordingly people flow rate in a certain time can be counted in a statistics mode.
Description
Technical field
The present invention relates to field of video monitoring, in particular to a kind of video demographic method based on body weight for humans identification.
Background technology
For the security protection of public place, usually adopt at present camera to realize the collection of image.
Due to present video identification technology, can only identify the human body image in video, can not confirm the corresponding individuality of human body image, thereby cause to distinguish everyone motion track, can not determine the corresponding identity of human body image in current video.Whether there is identical people owing to can not determine out, is difficult to determine stream of people's quantity of a period of time in the zone.
Summary of the invention
The present invention aims to provide a kind of video demographic method based on body weight for humans identification, the problem that must not confirm the individuality of human body image with solution.
In an embodiment of the present invention, provide a kind of video demographic method based on body weight for humans identification, having comprised:
Detect the human body image in video image;
Determine the proper vector of described human body image, a plurality of reference vector in the proper vector of determining and the database that gathers are in advance mated;
The match is successful if do not have, and the human body image according to described detection obtains corresponding reference vector, and described human body image and corresponding reference vector thereof are joined in described database, simultaneously counter added one.
By above-mentioned step, can determine human body image in database, with the human body image determined as the human body image that detects.Thereby can count the number flow in a period of time in video.
Description of drawings
Accompanying drawing described herein is used to provide a further understanding of the present invention, consists of the application's a part, and illustrative examples of the present invention and explanation thereof are used for explaining the present invention, do not consist of improper restriction of the present invention.In the accompanying drawings:
Fig. 1 shows the process flow diagram of embodiment;
Embodiment
Below with reference to the accompanying drawings and in conjunction with the embodiments, describe the present invention in detail.Referring to Fig. 1, the step of embodiment comprises:
S11: detect the human body image in video image;
S12: determine the proper vector of described human body image, a plurality of reference vector in the proper vector of determining and the database that gathers are in advance mated;
S13: the match is successful if do not have, and the human body image according to described detection obtains corresponding reference vector, and described human body image and corresponding reference vector thereof are joined in described database, simultaneously counter added one.
By above-mentioned step, can determine human body image in database, with the human body image determined as the human body image that detects.Thereby can count the number flow in a period of time in video.
Preferably, in embodiment, the step of human body image comprises: use the Gaussian Background modeling to detect the moving region in video.In the moving region that detects, use based on histograms of oriented gradients (HOG) with the object detecting method of the support vector machine (latent SVM) of implicit parameter, on different scale, the human body image in video is detected.
Preferably, in embodiment, determine that the process of proper vector comprises:
Be the HSV form with the image transitions that detects, and extract the color distribution histogram.
Conversion from the RGB color space to the hsv color space, computing formula is as follows:
v＝max
Max=max (r, g, b) wherein, min=min (r, g, b).Such as, be the pixel of (0.1,0.2,0.5) for the RGB color value, the value in the hsv color space is (225,0.8,0.5).
Calculate color histogram: for each pixel in image, its color is added up.For example, the v component is black less than threshold value 1, and the v component is white greater than threshold value 2 and s component less than threshold value 3, the v component between threshold value 1 and threshold value 2 and the v component be grey less than threshold value 3, other colors are colour.
For colour, evenly be divided into 6 kinds of colors according to h component from 0 to 360, namely [0,60), [60,120), [120,180), [180,240), [240,300), [300,360).
Color to each pixel is added up, and calculates every kind of color proportion in human body image, stores into successively in array x, uses as the Characteristic of Image vector.
For example, in an image, 10 pixels are arranged.Wherein black color dots and white point respectively have 3, other 4 points belong to color [60,120), this image characteristic of correspondence vector is (0.3,0.3,0,0,0.4,0,0,0,0) so.
Preferably, in embodiment, the reference vector in described database is determined by following steps:
Gather in advance everyone several human body images in video image;
Adopt the K-means clustering algorithm to described several human body image computings of same person, with a plurality of proper vector computings one to one of several human body images, obtain a proper vector of everyone correspondence as reference vector.
When using the K-means training, the color histogram of everyone volume image that obtains in testing process is carried out cluster as proper vector, obtain the cluster centre of proper vector, and the sample that comprises of each cluster centre.
The K mean algorithm need to be inputted a parameter k, and several proper vectors.Calculate by the K mean algorithm and these proper vectors can be divided into k class and the sample that comprises in each class.Like this, just the sample of input can be divided into the k class, each class represents a human body image.
The characteristic of correspondence vector that cluster centre is obtained each class stores in database.
Above-mentioned matching process comprises:
Each proper vector corresponding to each image of computing respectively with described database in the distance of reference vector of everyone volume image;
To a plurality of distance-taxis that each proper vector obtains, determine two minimums apart from d1 and d2; Wherein, d1＜d2;
If described 1.5d1＜d2 determines that this proper vector and the reference vector that is used for the described d1 of computing are complementary.
Determine the human body image corresponding with the nearest reference vector of each described proper vector, and the summation of the number of times that mated of the reference vector of everyone volume image of statistics correspondence;
Find out the human body image of the unique and the highest value of the number of times summation that is determined, as the described human body image that the match is successful.
Wherein, be used for calculating the reference vector of minimum Euclidean distance as the highest reference vector of distance.The formula of Euclidean distance is as follows:
Wherein d is that proper vector arrives the distance between the reference vector of cluster centre, x is the Characteristic of Image vector, the cluster centre characteristic of correspondence vector that X obtains for training, it is reference vector, the i position of the reference vector of xi and Xi difference presentation video and the reference vector of cluster centre, N is the dimension of proper vector or reference vector.
For example: if one have 5 human body image samples, each sample is the corresponding a plurality of reference vector of human body image.
The human body image that detects is 5 width, totally 5 proper vectors; Database comprises 5 human body image samples, and each sample comprises 6 reference vector, has 30 reference vector, the corresponding reference vector of everyone volume image.Each proper vector that calculating detects and the distance of 30 reference vector obtain 5 groups of data.
Every group of data comprise 30 distances, find two minimum distances, d1 and d2, and satisfy 1.5d1＜d2, think to match reference vector.
Add up the number of times that each reference vector of everyone volume image is mated.For example: detect certain proper vector and be (1,0,0,0,0,0,0,0,0), two nearest reference vector are respectively (0.8,0,0,0,0,0,0,0,0.2) and (0.5,0.5,0,0,0,0,0,0,0) with it.Can calculate d1 ≈ 0.283, d2 ≈ 0.707, and 1.5d1＜d2.Determine that this proper vector and the reference vector that is used for the described d1 of computing are complementary.The reference vector that is used for the described d1 of computing is the human body image of sample 1, and the human body image of sample 1 is the successful human body image of identification.
Human body image is identified as respectively the situation in following each sample; As: sample 1, sample 1, sample 1, sample 2, sample 3, statistic histogram is (3,1,1), and sample 1 is high and the most unique sample, and the human body image that is detected finally is identified as the corresponding human body image of sample 1 again.
In addition, in order to realize exact matching, the human body image that identifies and the image of sample are extracted the ORB unique point, use the hamming distance that unique point is mated, and use RANSAC algorithm eliminating error coupling.Determine whether that according to final matching result the match is successful.
obviously, those skilled in the art should be understood that, above-mentioned each module of the present invention or each step can realize with general calculation element, they can concentrate on single calculation element, perhaps be distributed on the network that a plurality of calculation elements form, alternatively, they can be realized with the executable program code of calculation element, thereby, they can be stored in memory storage and be carried out by calculation element, perhaps they are made into respectively each integrated circuit modules, perhaps a plurality of modules in them or step being made into the single integrated circuit module realizes.Like this, the present invention is not restricted to any specific hardware and software combination.
The above is only the preferred embodiments of the present invention, is not limited to the present invention, and for a person skilled in the art, the present invention can have various modifications and variations.Within the spirit and principles in the present invention all, any modification of doing, be equal to replacement, improvement etc., within all should being included in protection scope of the present invention.
Claims (8)
1. the video demographic method based on body weight for humans identification, is characterized in that, comprising:
Detect the human body image in video image;
Determine the proper vector of described human body image, a plurality of reference vector in the proper vector of determining and the database that gathers are in advance mated;
The match is successful if do not have, and the human body image according to described detection obtains corresponding reference vector, and described human body image and corresponding reference vector thereof are joined in described database, simultaneously counter added one.
2. method according to claim 1, is characterized in that, the process of described definite proper vector comprises:
Described human body image is converted to the HSV form;
Add up the interior versicolor pixel quantity of image of described HSV form;
Determine a proper vector corresponding with this image according to described versicolor pixel quantity.
3. method according to claim 2, is characterized in that, described reference vector is determined by following steps:
Gather in advance everyone several human body images in video image;
Adopt the K-means clustering algorithm to the proper vector of described several human body image computings, obtain a proper vector of everyone correspondence as reference vector.
4. method according to claim 3, is characterized in that, described matching process comprises:
The described definite proper vector of computing is the distance of a reference vector corresponding with everyone volume image in described database respectively;
To a plurality of distance-taxis that each proper vector obtains, determine two minimums apart from d1 and d2; Wherein, d1＜d2;
If described 1.5d1＜d2 determines that this proper vector and the reference vector that is used for the described d1 of computing are complementary.
5. method according to claim 4, is characterized in that,
Determine the human body image corresponding with the nearest reference vector of each described proper vector, and the summation of the number of times that mated of the reference vector of everyone volume image of statistics correspondence;
Find out the human body image of the unique and the highest value of the number of times summation that is determined, as the described human body image that the match is successful.
6. method according to claim 5, is characterized in that, also comprises: adopt the described distance of following Euclidean distance formula operation;
Wherein d is the distance of proper vector and reference vector, and x is the Characteristic of Image vector, the reference vector that X obtains for training, and the figure place of i representation feature vector or reference vector, N is the dimension of proper vector or reference vector.
7. method according to claim 6, is characterized in that, also comprises:
The match is successful if do not have, and the proper vector with described detected human body image joins described database as new reference vector.
8. method according to claim 1, is characterized in that, also comprises:
Current frame image and before video image in, adopt minimum with color receptacle frame residence stating this human body image that detects.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210590515.2A CN103093273B (en) | 2012-12-30 | 2012-12-30 | Based on the video demographic method of body weight for humans identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210590515.2A CN103093273B (en) | 2012-12-30 | 2012-12-30 | Based on the video demographic method of body weight for humans identification |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103093273A true CN103093273A (en) | 2013-05-08 |
| CN103093273B CN103093273B (en) | 2016-05-11 |
Family
ID=48205819
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210590515.2A Expired - Fee Related CN103093273B (en) | 2012-12-30 | 2012-12-30 | Based on the video demographic method of body weight for humans identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103093273B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109492610A (en) * | 2018-11-27 | 2019-03-19 | 广东工业大学 | A kind of pedestrian recognition methods, device and readable storage medium storing program for executing again |
| WO2019100346A1 (en) * | 2017-11-24 | 2019-05-31 | 深圳达闼科技控股有限公司 | Substance detection processing method, device and detection apparatus |
| CN113723539A (en) * | 2021-09-02 | 2021-11-30 | 北京云蝶智学科技有限公司 | Test question information acquisition method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1866270A (en) * | 2004-05-17 | 2006-11-22 | 香港中文大学 | Face recognition method based on video frequency |
| CN101311947A (en) * | 2008-06-12 | 2008-11-26 | 浙江大学 | Real time intelligent control method based on natural video frequency |
| CN101325690A (en) * | 2007-06-12 | 2008-12-17 | 上海正电科技发展有限公司 | Method and system for detecting human flow analysis and crowd accumulation process of monitoring video flow |
| CN101853377A (en) * | 2010-05-13 | 2010-10-06 | 复旦大学 | Method for identifying content of digital video |
-
2012
- 2012-12-30 CN CN201210590515.2A patent/CN103093273B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1866270A (en) * | 2004-05-17 | 2006-11-22 | 香港中文大学 | Face recognition method based on video frequency |
| CN101325690A (en) * | 2007-06-12 | 2008-12-17 | 上海正电科技发展有限公司 | Method and system for detecting human flow analysis and crowd accumulation process of monitoring video flow |
| CN101311947A (en) * | 2008-06-12 | 2008-11-26 | 浙江大学 | Real time intelligent control method based on natural video frequency |
| CN101853377A (en) * | 2010-05-13 | 2010-10-06 | 复旦大学 | Method for identifying content of digital video |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019100346A1 (en) * | 2017-11-24 | 2019-05-31 | 深圳达闼科技控股有限公司 | Substance detection processing method, device and detection apparatus |
| CN109492610A (en) * | 2018-11-27 | 2019-03-19 | 广东工业大学 | A kind of pedestrian recognition methods, device and readable storage medium storing program for executing again |
| CN109492610B (en) * | 2018-11-27 | 2022-05-10 | 广东工业大学 | Pedestrian re-identification method and device and readable storage medium |
| CN113723539A (en) * | 2021-09-02 | 2021-11-30 | 北京云蝶智学科技有限公司 | Test question information acquisition method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103093273B (en) | 2016-05-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Topkaya et al. | Counting people by clustering person detector outputs | |
| Bedagkar-Gala et al. | Part-based spatio-temporal model for multi-person re-identification | |
| CN103093274B (en) | Method based on the people counting of video | |
| US9489570B2 (en) | Method and system for emotion and behavior recognition | |
| US20170185826A1 (en) | Method and system for automatically recognizing facial expressions via algorithmic periocular localization | |
| CN102799893B (en) | Method for processing monitoring video in examination room | |
| Bedagkar-Gala et al. | Multiple person re-identification using part based spatio-temporal color appearance model | |
| Vrigkas et al. | Matching mixtures of curves for human action recognition | |
| Avgerinakis et al. | Recognition of activities of daily living for smart home environments | |
| Narayan et al. | Action and interaction recognition in first-person videos | |
| CN103065126B (en) | Re-identification method of different scenes on human body images | |
| CN103049749B (en) | The recognition methods again of human body under grid blocks | |
| CN105122270A (en) | Method and system for counting people using depth sensor | |
| Liong et al. | Regularized local metric learning for person re-identification | |
| Ma et al. | Counting people crossing a line using integer programming and local features | |
| Cheng et al. | Person re-identification by articulated appearance matching | |
| Thi et al. | Human action recognition and localization in video using structured learning of local space-time features | |
| CN109614933A (en) | A kind of motion segmentation method based on certainty fitting | |
| CN109902550A (en) | The recognition methods of pedestrian's attribute and device | |
| CN110827265A (en) | Image anomaly detection method based on deep learning | |
| CN104899559B (en) | A kind of rapid pedestrian detection method based on video monitoring | |
| CN103049747A (en) | Method for re-identifying human body images by utilization skin color | |
| CN103093273A (en) | Video people counting method based on body weight recognition | |
| Zhang et al. | Anomaly detection and localization in crowded scenes by motion-field shape description and similarity-based statistical learning | |
| CN103077376B (en) | Method for distinguishing is known again based on the human body image in video image |
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 | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20180625 Address after: 100096 Haidian District, Beijing, west 2 new apartment building, three floor commercial room 337. Patentee after: Letter frame technology (Beijing) Co., Ltd. Address before: 100085 A-6, 28, Beijing, Haidian District, Shanghai. Patentee before: Xinzheng Electronic Technology (Beijing) Co., Ltd. |
|
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20160511 Termination date: 20191230 |