CN111144166A - Method, system and storage medium for establishing abnormal crowd information base - Google Patents
Method, system and storage medium for establishing abnormal crowd information base Download PDFInfo
- Publication number
- CN111144166A CN111144166A CN201811302295.2A CN201811302295A CN111144166A CN 111144166 A CN111144166 A CN 111144166A CN 201811302295 A CN201811302295 A CN 201811302295A CN 111144166 A CN111144166 A CN 111144166A
- Authority
- CN
- China
- Prior art keywords
- gait
- abnormal
- data
- characteristic data
- identity
- 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
- 230000002159 abnormal effect Effects 0.000 title claims abstract description 127
- 238000000034 method Methods 0.000 title claims abstract description 65
- 230000005021 gait Effects 0.000 claims abstract description 185
- 238000007781 pre-processing Methods 0.000 claims abstract description 82
- 206010017577 Gait disturbance Diseases 0.000 claims abstract description 13
- 239000013598 vector Substances 0.000 claims description 38
- 230000011218 segmentation Effects 0.000 claims description 27
- 230000004927 fusion Effects 0.000 claims description 7
- 238000001514 detection method Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 4
- 238000012544 monitoring process Methods 0.000 abstract description 9
- 238000010586 diagram Methods 0.000 description 33
- 238000012549 training Methods 0.000 description 21
- 230000009471 action Effects 0.000 description 9
- 230000006870 function Effects 0.000 description 9
- 230000036544 posture Effects 0.000 description 7
- 238000012545 processing Methods 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 5
- 238000001914 filtration Methods 0.000 description 5
- 230000033001 locomotion Effects 0.000 description 5
- 239000011159 matrix material Substances 0.000 description 5
- 238000005260 corrosion Methods 0.000 description 4
- 230000007797 corrosion Effects 0.000 description 4
- 210000002683 foot Anatomy 0.000 description 4
- 208000032538 Depersonalisation Diseases 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000007499 fusion processing Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 238000007373 indentation Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000003825 pressing Methods 0.000 description 2
- 230000000630 rising effect Effects 0.000 description 2
- 238000006748 scratching Methods 0.000 description 2
- 230000002393 scratching effect Effects 0.000 description 2
- 238000011410 subtraction method Methods 0.000 description 2
- 238000010408 sweeping Methods 0.000 description 2
- 210000003423 ankle Anatomy 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000003759 clinical diagnosis Methods 0.000 description 1
- 230000003111 delayed effect Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000037149 energy metabolism Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 210000003127 knee Anatomy 0.000 description 1
- 210000003141 lower extremity Anatomy 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000002156 mixing Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000003205 muscle Anatomy 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 210000003371 toe Anatomy 0.000 description 1
- 210000001364 upper extremity Anatomy 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
- G06V40/23—Recognition of whole body movements, e.g. for sport training
- G06V40/25—Recognition of walking or running movements, e.g. gait recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/41—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items
- G06V20/42—Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items of sport video content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
- G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Human Computer Interaction (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to a method, a system and a storage medium for establishing an abnormal crowd information base. The establishing method comprises the following steps: acquiring gait preprocessing data of walking of people in the video image; extracting identity characteristics of the gait preprocessing data to obtain identity characteristic data corresponding to the gait preprocessing data; respectively calculating similarity values of the identity characteristic data and each group of pre-stored abnormal characteristic data; and when any similarity value is larger than a preset threshold value, acquiring face information corresponding to the identity characteristic data, and storing the face information into an abnormal crowd information base. The embodiment of the invention acquires the gait preprocessing data of the person in the video image, compares the gait preprocessing data with the pre-stored abnormal gait preprocessing data, judges the gait preprocessing data similar to the abnormal gait preprocessing data in the video image, acquires the person information corresponding to the gait preprocessing data, and stores the face information so as to improve the monitoring efficiency and provide abnormal person information for security personnel.
Description
Technical Field
The invention relates to the technical field of biological identification, in particular to a method and a system for establishing an abnormal crowd information base and a storage medium.
Background
With the need for security level improvement in public places in various countries and the wide spread of video monitoring technologies, intelligent monitoring becomes a very active field in computer vision. In intelligent monitoring, the remote identification of human identity in a monitoring scene is a direction which is full of challenges and has a good application prospect, so that the system has scientific research and commercial values, and has theoretical and practical significance for deep research on the system.
Due to the increasing safety requirements, video surveillance is increasingly used in various public places, such as railway stations, airports, subways, buses, roads, markets, and the like. Although abnormal events or abnormal personnel can be monitored through remote identification and monitoring, the mode can only carry out comparison according to known personnel images, such as images of escaped personnel and images of recorded personnel, and areas where the abnormal personnel are located are identified and confirmed manually or automatically, but due to the fact that the information of the abnormal personnel is less, whether the abnormal personnel exist in video monitoring or not is confirmed manually or automatically, false alarm, delayed alarm and false alarm of abnormal emergency are easily caused.
Disclosure of Invention
In order to solve the problems in the prior art, at least one embodiment of the present invention provides a method, a system, and a storage medium for creating an abnormal crowd information base.
In a first aspect, an embodiment of the present invention provides a method for establishing an abnormal crowd information base, where the method includes:
acquiring gait preprocessing data of walking of people in the video image;
extracting identity characteristics of the gait preprocessing data to obtain identity characteristic data corresponding to the gait preprocessing data;
respectively calculating similarity values of the identity characteristic data and each group of pre-stored abnormal characteristic data;
and when any similarity value is larger than a preset threshold value, acquiring face information corresponding to the identity characteristic data, and storing the face information into the abnormal crowd information base.
Based on the above technical solutions, the embodiments of the present invention may be further improved as follows.
With reference to the first aspect, in a first embodiment of an aspect, the method for acquiring abnormal feature data includes:
inputting a plurality of abnormal video images containing abnormal crowd information, and acquiring abnormal gait preprocessing data of people walking in each abnormal video image;
performing identity recognition on each abnormal gait preprocessing data to obtain a plurality of groups of identity characteristic data to be confirmed;
respectively calculating the abnormal similarity value of each group of identity characteristic data to be confirmed and other identity characteristic data to be confirmed;
counting the number of abnormal similarity values of each group of identity characteristic data to be confirmed and other identity characteristic data to be confirmed, which are larger than a preset similarity value, as abnormal number;
and taking the identity characteristic data to be confirmed corresponding to the abnormal quantity larger than the preset quantity as abnormal characteristic data.
In combination with the first embodiment of the first aspect, in the second embodiment of the first aspect,
the calculating of the abnormal similarity value between each group of the identity characteristic data to be confirmed and other identity characteristic data to be confirmed specifically includes:
vectorizing all the identity characteristic data to be confirmed respectively to obtain a plurality of groups of identity characteristic data vectors to be confirmed;
respectively calculating cosine values of each group of identity characteristic data vectors to be confirmed and other identity characteristic data vectors to be confirmed as the abnormal similarity value;
the calculating the similarity value between the identity characteristic data and each pre-stored group of abnormal characteristic data respectively specifically includes:
vectorizing the identity characteristic data and all the abnormal characteristic data respectively to obtain identity characteristic data vectors and a plurality of groups of abnormal characteristic data vectors;
and respectively calculating cosine values of each group of abnormal characteristic data vectors and identity characteristic data vectors as the similarity values.
With reference to the first aspect, in a third embodiment of the first aspect, the obtaining of the face information corresponding to the identity feature data specifically includes:
acquiring the spatial coordinates of the face characteristic points corresponding to the identity characteristic data;
and constructing a corresponding human face mesh model according to the space coordinates of all the human face characteristic points to serve as the human face information.
With reference to the third embodiment of the first aspect, in a fourth embodiment of the first aspect, the obtaining the spatial coordinates of the face feature point corresponding to the identity feature data specifically includes:
acquiring a plurality of frame images in the video image;
respectively acquiring pixel coordinates of the face characteristic points corresponding to the identity characteristic data in each frame image;
and calculating the space coordinates of the face characteristic points according to the internal reference information and the external reference information of the camera for acquiring the video image and the pixel coordinates of the face characteristic points in each frame image.
With reference to the third embodiment of the first aspect, in a fifth embodiment of the first aspect, the constructing a corresponding face mesh model according to the spatial coordinates of all the face feature points specifically includes:
and triangulating all the human face characteristic points according to the space coordinates of the human face characteristic points to obtain topological relations of all the human face characteristic points and construct a corresponding human face mesh model.
With reference to the first aspect, in a sixth embodiment of the first aspect, the extracting the identity feature of the gait preprocessing data to obtain the identity feature data corresponding to the gait preprocessing data specifically includes:
inputting the gait preprocessing data into a recognition model;
and acquiring the identity characteristic data output after the identification model identifies the gait preprocessing data.
With reference to the first aspect or the first, second, third, fourth, fifth, or sixth embodiment of the first aspect, in a seventh embodiment of the first aspect, the acquiring gait preprocessing data of a person walking in a video image specifically includes:
acquiring continuous frame images in a video image;
detecting an image area containing human figures from the continuous frame images by using a detection algorithm;
extracting a human-shaped outline in the human-shaped image area to generate a human-shaped outline segmentation graph;
aligning the human shape center and the image center of each frame of the human shape contour segmentation image to generate a primary gait silhouette image;
scaling the human-shaped contour in each frame of primary gait silhouette image to a uniform resolution ratio to generate a gait silhouette image sequence;
respectively acquiring silhouette gait features of each frame of gait silhouette image in the gait silhouette image sequence to form silhouette gait preprocessing data;
calculating the correlation similarity of each frame of silhouette gait features in the silhouette gait preprocessing data;
and performing weighted fusion on the silhouette gait features according to the correlation similarity to obtain the gait preprocessing data.
In a second aspect, an embodiment of the present invention provides an abnormal crowd information base establishing system, where the abnormal crowd information base establishing system includes a processor and a memory; the processor is configured to execute an abnormal crowd information base establishment program stored in the memory, so as to implement the abnormal crowd information base establishment method according to any one of the first aspect.
In a third aspect, an embodiment of the present invention provides a storage medium, where the storage medium stores one or more programs, and the one or more programs are executable by one or more processors to implement the abnormal crowd information base establishing method according to any one of the first aspects.
Compared with the prior art, the technical scheme of the invention has the following advantages: the embodiment of the invention acquires the gait preprocessing data of the person in the video image, compares the gait preprocessing data with the pre-stored abnormal gait preprocessing data, judges the gait preprocessing data similar to the abnormal gait preprocessing data in the video image, acquires the person information corresponding to the gait preprocessing data, and stores the face information so as to improve the monitoring efficiency and provide abnormal person information for security personnel.
Drawings
Fig. 1 is a schematic flow chart of a method for establishing an abnormal crowd information base according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of a method for creating an abnormal crowd information base according to another embodiment of the present invention;
fig. 3 is a first flowchart of a method for establishing an abnormal crowd information base according to another embodiment of the present invention;
fig. 4 is a flowchart illustrating a method for establishing an abnormal crowd information base according to another embodiment of the present invention;
fig. 5 is a third schematic flowchart of a method for establishing an abnormal crowd information base according to another embodiment of the present invention;
fig. 6 is a fourth schematic flowchart of a method for establishing an abnormal crowd information base according to another embodiment of the present invention;
fig. 7 is a fifth flowchart illustrating a method for establishing an abnormal crowd information base according to another embodiment of the present invention;
fig. 8 is a flowchart illustrating a method for establishing an abnormal crowd information base according to yet another embodiment of the present invention;
fig. 9 is a schematic structural diagram of a system for establishing an abnormal crowd information base according to yet another embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
As shown in fig. 1, an abnormal crowd information base establishment method provided in an embodiment of the present invention includes:
and S11, acquiring gait preprocessing data of the walking of the person in the video image.
In this embodiment, the gait preprocessing data in the gait silhouette image obtained from each frame of image in the video image can be respectively obtained from the gait silhouette image obtained from the human body contour line.
As shown in fig. 2, acquiring gait preprocessing data of walking of a person in a video image comprises:
and S21, acquiring continuous frame images in the video images.
A single frame image is a still picture, and a frame is a single picture of the smallest unit in a motion picture, which is equivalent to each frame of a shot on a motion picture film. A single frame is a still picture, and consecutive frames form a moving picture, such as a television image. In this step, successive frame images in the video image are acquired.
S22, an image region including a human figure is detected from the continuous frame image by a detection algorithm.
For example, a moving object in an image may be detected by a background subtraction method, and a contour of the moving object may be detected to confirm a human-shaped image region, or another image detection method may be used to detect a continuous frame image to confirm a human-shaped image region in the continuous frame image.
And S23, extracting the human-shaped outline in the human-shaped image area to generate a human-shaped outline segmentation graph.
In this embodiment, the human-shaped contour in each human-shaped image region in each frame of image is extracted to obtain a continuous human-shaped contour segmentation map for the video image, the image is subjected to binary segmentation, the binary-segmented image is processed through an expansion filtering operator and a corrosion operator, noise in the image is filtered, a hole in the binary-segmented image is filled, and boundary tracking is performed on the processed image, so that the corresponding human-shaped contour can be obtained.
Specifically, the method of S23 specifically includes: the background frame of the frame image is obtained based on the intermediate value method. And detecting a moving target in the frame image by using a background difference method according to the background frame, and performing binary segmentation on the frame image. Processing the frame image after binary segmentation by using a corrosion operator and an expansion filtering operator, and filling holes in the frame image according to connectivity analysis; and carrying out boundary tracking on the frame image to obtain a human-shaped contour, and generating a human-shaped contour segmentation graph.
And S24, aligning the human figure center and the image center of each human figure outline segmentation image to generate a primary gait silhouette image.
And aligning the human figure center and the image center of the human figure contour segmentation graph to ensure that each human figure contour segmentation graph is adjusted according to the walking video image of the human figure contour segmentation graph to obtain a primary gait silhouette image.
And S25, scaling the human-shaped contour in each frame of primary gait silhouette image to a uniform resolution ratio to generate a gait silhouette image sequence.
And adjusting the resolution of the primary gait silhouette images to enable the resolution of each primary gait silhouette image to be consistent, so as to obtain a gait silhouette image sequence.
And S26, respectively acquiring silhouette gait features of each frame of gait silhouette image in the gait silhouette image sequence to form silhouette gait preprocessing data.
Acquiring silhouette gait features of each frame of gait silhouette image, wherein the gait features refer to features of the force magnitude, direction and action point of the person during walking reflected in the footprints. Is the reflection of the walking habit of the person in the steps of falling feet, rising feet and supporting swing. Generally comprising: the mark can be selected from the group consisting of a bump mark, a tread mark, a push mark, a traveling mark, a sitting mark, a pressing mark, an indentation mark, a twisting mark, a lifting mark, a kicking mark, a digging mark, a scratching mark, a picking mark, an slit mark, a scratch mark, a sweeping mark, a scratch mark and the like.
And S27, calculating the relevance similarity of the silhouette gait features of each frame in the silhouette gait preprocessing data.
The correlation similarity between each silhouette gait feature and other frame silhouette gait features in the same gait sequence is calculated respectively, in this embodiment, the correlation similarity may be distance measurement of two gait features, such as euclidean distance of each frame silhouette gait feature, and the smaller the value of the euclidean distance, the larger the similarity of each frame silhouette gait feature.
And S28, performing weighted fusion on the silhouette gait features according to the correlation similarity to obtain gait preprocessing data.
As shown in fig. 3, the method for obtaining the corresponding gait preprocessing data by fusing the gait features of each silhouette according to the correlation similarity includes:
and S31, calculating the equal error rate of the corresponding silhouette gait characteristics used for the characteristic identification process according to each correlation similarity.
The credibility of different gait features in the fusion process is inconsistent, and the accuracy of feature identification can be generally expressed by Equal Error Rate (EER). The higher the EER value is, the worse the performance of the feature is, the higher the error rate in the step is, the lower the reliability of the feature in the fusion process is, in the step, the greater the correlation similarity is, the more similar the silhouette gait feature and the real gait feature is, the lower the equal error rate corresponding to the gait feature with the greater correlation similarity is, in the embodiment, the correlation similarity is calculated by the Euclidean distance between the silhouette gait feature and the real gait feature, that is, the lower the Euclidean distance is, the higher the correlation similarity is, and the lower the corresponding equal error rate is.
And S32, respectively calculating the weight values of the corresponding silhouette gait characteristics according to each equal error rate.
The method for respectively calculating the weight values of the corresponding silhouette gait features according to the equal error rates of the different silhouette gait features comprises the following steps:
calculating the weight value according to the following calculation formula:
wherein, wnWeight value of nth silhouette gait feature, enThe equal error rate of the nth silhouette gait feature is shown, and M is the total number of the silhouette gait features.
And S33, performing weighted fusion on all silhouette gait features according to corresponding weight values to obtain gait preprocessing data.
And performing weighted fusion on all silhouette gait features according to corresponding weight values, so that the weighting proportion of the silhouette gait features with smaller weight values in the fusion process is smaller, the error of the final gait preprocessing data is reduced, and the accuracy of the gait preprocessing data is improved.
And S12, extracting the identity characteristics of the gait preprocessing data to obtain the identity characteristic data corresponding to the gait preprocessing data.
In this embodiment, S12 specifically includes:
and inputting the generated gait preprocessing data into the recognition model, and carrying out identity recognition on the gait preprocessing data through the recognition model to obtain corresponding identity characteristic data. And carrying out identity recognition on the gait preprocessing data through the recognition model to obtain identity characteristic data corresponding to gait characteristics.
And S13, respectively calculating similarity values of the identity characteristic data and each group of pre-stored abnormal characteristic data.
In this embodiment, similarity values are respectively calculated for the recognized identity characteristic data and the pre-stored abnormal characteristic data to determine whether the recognized identity characteristic data matches with the pre-stored abnormal characteristic data, and whether the identity characteristic data is abnormal is determined, so that people in the video image are monitored, and when the identity characteristic data is abnormal, the monitoring is timely performed.
Calculating the similarity value of the identity characteristic data and the abnormal characteristic data comprises the following steps:
and vectorizing the identity characteristic data and all abnormal characteristic data respectively to obtain an identity characteristic data vector and a plurality of groups of abnormal characteristic data vectors.
In this embodiment, the identity feature data and the abnormal feature data are respectively digitized to form a corresponding abnormal feature data vector and an identity feature data vector, for example, data such as the strength, direction, and action point of a person walking in the identity feature are respectively digitized, the action point can be represented by pixel coordinates in a corresponding picture, each identity feature data includes walking features of the person in different postures, and other data can be used as parameters of the vectors.
And respectively calculating cosine values of each group of abnormal characteristic data vectors and identity characteristic data vectors as similarity values.
In this embodiment, the cosine distance, also called cosine similarity value, is a measure for measuring the difference between two individuals by using the cosine value of the included angle between two vectors in the vector space. Cosine similarity values are one method of calculating similarity values. The method firstly maps individual index data to vector space, and secondly measures the similarity between two individual vectors by measuring the cosine value of an included angle of an inner product space between the two individual vectors. The closer the included angle of the two individual vectors is to 0 degree, namely the larger the cosine value of the included angle is, the higher the similarity value of the two individuals is; on the contrary, the closer the included angle of the two individuals is to 180 degrees, the smaller the cosine value of the included angle is, and the lower the similarity value is. Of course, in the present embodiment, the euclidean distance or the hamming distance equidistance measure can also be adopted as the similarity value.
And S14, when any similarity value is larger than a preset threshold value, acquiring the face information corresponding to the identity characteristic data, and storing the face information into an abnormal crowd information base.
In this embodiment, when the similarity value between the identity characteristic data and any abnormal characteristic data is greater than a preset threshold value, face information corresponding to the identity characteristic data in the video image is acquired, the face information is entered into an abnormal crowd information base, and when an abnormal condition occurs in an area corresponding to the video image, the face information corresponding to each abnormal identity characteristic data is quickly positioned, so that quick screening is facilitated, and the processing efficiency of an abnormal event is improved.
As shown in fig. 4, an embodiment of the present invention further provides a method for establishing an abnormal crowd information base, and compared with the establishing method shown in fig. 1, the difference is that the method for acquiring abnormal feature data includes:
and S41, inputting a plurality of abnormal video images containing abnormal crowd information, and acquiring abnormal gait preprocessing data of people walking in each abnormal video image.
In this embodiment, the abnormal video image containing the information of the abnormal crowd may be a video image manually screened and input system by the user, for example, a thief is confirmed to be someone, the video image when the thief takes a case is taken as the abnormal video image, the thief is only one of the abnormal crowd, and the video images corresponding to each situation can be screened according to the abnormal situation. The method for acquiring the gait preprocessing data of the person walking in the abnormal video image can be performed according to the method for acquiring the gait preprocessing data in the embodiment.
And S42, performing identity recognition on each abnormal gait preprocessing data to obtain a plurality of groups of identity characteristic data to be confirmed.
And inputting the generated abnormal gait preprocessing data into an identification model, and carrying out identity identification on the abnormal gait preprocessing data through the identification model to obtain corresponding identity characteristic data. And carrying out identity recognition on the abnormal gait preprocessing data through the recognition model to obtain identity characteristic data corresponding to gait characteristics.
And S43, respectively calculating the abnormal similarity value of each group of identity characteristic data to be confirmed and other identity characteristic data to be confirmed.
And vectorizing all the identity characteristic data to be confirmed respectively to obtain a plurality of groups of identity characteristic data vectors to be confirmed.
The identity characteristic data to be confirmed are respectively digitized to form corresponding identity characteristic data vectors to be confirmed, for example, data such as the force magnitude, the direction and the action point of a person walking in the identity characteristic are respectively digitized, the action point digitization can be represented by pixel point coordinates in a corresponding picture, each identity characteristic data comprises the walking characteristic of the person in different postures, and other data can also be used as parameters of the vectors.
And respectively calculating cosine values of each group of identity characteristic data vectors to be confirmed and other identity characteristic data vectors to be confirmed as abnormal similarity values.
In this embodiment, the cosine distance, also called cosine similarity value, is a measure for measuring the difference between two individuals by using the cosine value of the included angle between two vectors in the vector space. Cosine similarity values are one method of calculating similarity values. The method firstly maps individual index data to vector space, and secondly measures the similarity between two individual vectors by measuring the cosine value of an included angle of an inner product space between the two individual vectors. The closer the included angle of the two individual vectors is to 0 degree, namely the larger the cosine value of the included angle is, the higher the similarity value of the two individuals is; on the contrary, the closer the included angle of the two individuals is to 180 degrees, the smaller the cosine value of the included angle is, and the lower the similarity value is. Of course, in the present embodiment, the euclidean distance or the hamming distance equidistance measure can also be adopted as the similarity value.
And S44, counting the number of the abnormal similarity values of each group of the identity characteristic data to be confirmed and other identity characteristic data to be confirmed, which are larger than the preset similarity values, as the abnormal number.
In this embodiment, when the abnormal similarity between the identity feature data and other identity feature data is greater than the preset similarity value, the two identity feature data are similar to each other, and the number of similarity between each identity feature data and other identity feature data is counted, that is, the abnormal number.
And S45, taking the identity characteristic data to be confirmed corresponding to the abnormal quantity larger than the preset quantity as abnormal characteristic data.
If the abnormal number is larger than the preset number, the identity characteristic data extracted from the same batch of abnormal video images is similar to other identity characteristic data, the identity characteristic data is used as abnormal characteristic data, the abnormal number of each identity characteristic data and other identity characteristic data is respectively counted, namely whether each identity characteristic data can be used as the abnormal characteristic data is respectively confirmed, and the diversity of the pre-stored abnormal characteristic data is improved.
As shown in fig. 5, an embodiment of the present invention further provides a method for establishing an abnormal crowd information base, and compared with the establishing method shown in fig. 1, the difference is that the obtaining of the face information corresponding to the identity feature data specifically includes:
and S51, acquiring the space coordinates of the face characteristic points corresponding to the identity characteristic data.
Acquiring the spatial coordinates of the face characteristic points corresponding to the identity characteristic data in the video image, wherein the coordinates of the image displayed in the video image comprise: the spatial coordinates in this embodiment may be camera coordinates or world coordinates, and since the pixel coordinates are of the image itself, the pixel coordinates can only represent plane coordinates, and face information with less interference cannot be obtained according to the pixel coordinates.
As shown in fig. 6, obtaining the spatial coordinates of the face feature point corresponding to the identity feature data includes:
and S61, acquiring a plurality of frame images in the video image.
In this embodiment, a plurality of frame images in a video image are acquired, and the frame images may be continuous frame images or frame images that can clearly display a face contour, so as to improve the efficiency of acquiring face information.
And S62, respectively acquiring the pixel coordinates of the face characteristic points corresponding to the identity characteristic data in each frame image.
And S63, calculating the space coordinates of the face characteristic points according to the internal reference information and the external reference information of the camera for acquiring the video image and the pixel coordinates of the face characteristic points in each frame image.
In the embodiment, the spatial coordinates of the face characteristic points are calculated according to the parameter information of the camera for shooting the video image and the pixel coordinates of the face characteristic points in each frame image, and the intrinsic matrix and the basic matrix of the multi-view camera can be obtained; constructing a projection matrix of the independent cameras according to the internal reference information, the external reference information, the essential matrix and the basic matrix of each independent camera; and obtaining the space coordinates of the human face characteristic points according to the projection evidence and the corresponding pixel coordinates.
And S52, constructing a corresponding face mesh model according to the space coordinates of all the face characteristic points to serve as face information.
In this embodiment, all the face feature points may be triangulated according to the spatial coordinates of the face feature points, so as to obtain the topological relation of all the face feature points and construct a corresponding face mesh model.
As shown in fig. 7, an embodiment of the present invention further provides a method for establishing an abnormal population information base, and compared with the establishing method shown in fig. 1, the method is different in that identity feature extraction is performed on gait preprocessing data to obtain identity feature data corresponding to the gait preprocessing data, and specifically includes:
the training method of the recognition model comprises the following steps:
and S71, acquiring first gait preprocessing data of the walking of the person in any video image.
In this embodiment, the first gait preprocessing data may be obtained by user input, or obtained by processing a video image by using another trained generative model, or obtained by scanning according to the walking characteristics of a person in the video image; the method can also be used for acquiring first-step preprocessing data from a video image through a gait feature extraction technology in the prior art. The first gait preprocessing data refers to the posture and behavior characteristics of the human body when walking, and the human body moves along a certain direction through a series of continuous activities of the hip, the knee, the ankle and the toes. Gait involves factors such as behavioral habits, occupation, education, age and sex, and is also affected by various diseases. Control of walking is complex, including central commands, body balance and coordinated control, involving coordinated movements of the joints and muscles of the lower extremities, as well as associated with the posture of the upper extremities and the trunk. Misadjustment of any link may affect gait, and abnormalities may be compensated or masked. Normal gait has stability, periodicity and rhythmicity, directionality, coordination, and individual variability, however, these gait characteristics will change significantly when a person is ill. Gait analysis is an inspection method for studying walking rules, and aims to disclose key links and influencing factors of gait abnormalities through biomechanical and kinematic means so as to guide rehabilitation assessment and treatment and contribute to clinical diagnosis, curative effect assessment, mechanism research and the like. In gait analysis, whether gait is normal or not is often described by some special parameters, which generally include the following categories: gait cycle, kinematic parameters, kinetic parameters, electromyographic activity parameters, energy metabolism parameters and the like.
And S72, acquiring second gait preprocessing data of the walking of the person in any video image.
In this embodiment, second gait preprocessing data of the video image, such as gait silhouette images obtained according to a human body contour line, are obtained, and the second gait preprocessing data in the gait silhouette images obtained from each frame of image in the video image are respectively obtained.
In this step, the method for acquiring the second-step preprocessing data includes:
successive frame images in the video image are acquired.
A single frame image is a still picture, and a frame is a single picture of the smallest unit in a motion picture, which is equivalent to each frame of a shot on a motion picture film. A single frame is a still picture, and consecutive frames form a moving picture, such as a television image. In this step, successive frame images in the video image are acquired.
An image region including a human figure is detected from the continuous frame images by a detection algorithm.
For example, a moving object in an image may be detected by a background subtraction method, and a contour of the moving object may be detected to confirm a human-shaped image region, or another image detection method may be used to detect a continuous frame image to confirm a human-shaped image region in the continuous frame image.
And extracting the human-shaped outline in the human-shaped image area to generate a human-shaped outline segmentation graph.
In this embodiment, the human-shaped contour in each human-shaped image region in each frame of image is extracted to obtain a continuous human-shaped contour segmentation map for the video image, the image is subjected to binary segmentation, the binary-segmented image is processed through an expansion filtering operator and a corrosion operator, noise in the image is filtered, a hole in the binary-segmented image is filled, and boundary tracking is performed on the processed image, so that the corresponding human-shaped contour can be obtained.
Specifically, the method for extracting the human-shaped profile in the human-shaped image region and generating the human-shaped profile segmentation graph specifically comprises the following steps: the background frame of the frame image is obtained based on the intermediate value method. And detecting a moving target in the frame image by using a background difference method according to the background frame, and performing binary segmentation on the frame image. Processing the frame image after binary segmentation by using a corrosion operator and an expansion filtering operator, and filling holes in the frame image according to connectivity analysis; and carrying out boundary tracking on the frame image to obtain a human-shaped contour, and generating a human-shaped contour segmentation graph.
In this embodiment, a human-shaped contour in a human-shaped image region may also be extracted through a semantic analysis algorithm to generate a human-shaped contour segmentation map, specifically, each pixel point in the picture is subjected to secondary classification through a neural network, and then adjusted by some post-processing methods, such as edge smoothing, threshold filtering, and the like, to finally generate a segmentation image.
And aligning the human figure center and the image center of each frame of the human figure contour segmentation image to generate a primary gait silhouette image.
And aligning the human figure center and the image center of the human figure contour segmentation graph to ensure that each human figure contour segmentation graph is adjusted according to the walking video image of the human figure contour segmentation graph to obtain a primary gait silhouette image.
And (4) scaling the human-shaped contour in each frame of primary gait silhouette image to a uniform resolution ratio to generate a gait silhouette image sequence.
And adjusting the resolution of the primary gait silhouette images to enable the resolution of each primary gait silhouette image to be consistent, so as to obtain a gait silhouette image sequence.
And respectively acquiring silhouette gait features of each frame of gait silhouette image in the gait silhouette image sequence to form silhouette gait preprocessing data.
Acquiring silhouette gait features of each frame of gait silhouette image, wherein the gait features refer to features of the force magnitude, direction and action point of the person during walking reflected in the footprints. Is the reflection of the walking habit of the person in the steps of falling feet, rising feet and supporting swing. Generally comprising: the mark can be selected from the group consisting of a bump mark, a tread mark, a push mark, a traveling mark, a sitting mark, a pressing mark, an indentation mark, a twisting mark, a lifting mark, a kicking mark, a digging mark, a scratching mark, a picking mark, an slit mark, a scratch mark, a sweeping mark, a scratch mark and the like.
And calculating the relevance similarity value of each frame of silhouette gait features in the silhouette gait preprocessing data.
The correlation similarity value between each silhouette gait feature and other frame silhouette gait features in the same gait sequence is calculated respectively, in this embodiment, the correlation similarity value may be distance measurement of two gait features, such as euclidean distance of each frame silhouette gait feature, and the smaller the value of the euclidean distance, the larger the similarity of each frame silhouette gait feature.
And performing weighted fusion on the silhouette gait features according to the correlation similarity value to obtain second-step state preprocessing data.
Through the steps, the finally obtained second-step state preprocessing data better conform to the first-step state preprocessing data, and the accuracy of gait recognition through the second-step state energy diagram is improved.
And S73, inputting the second-step state preprocessing data and the first-step state preprocessing data into the recognition model for identity recognition and data recognition respectively, and performing parameter training iteration on the recognition model according to the identity recognition result and the data recognition result to obtain the recognition model.
As shown in fig. 8, in this embodiment, S73 specifically includes:
s81, generating a second-step energy map according to the second-step preprocessing data, and generating a first-step energy map according to the first-step preprocessing data;
and S82, mixing the second step state energy diagram and the first step state energy diagram to obtain a plurality of identification gait energy diagrams of different action postures, and inputting the identification gait energy diagrams into an identification model for identity identification and data identification.
In the step, the second step state energy diagram and the first step state energy diagram are respectively split to obtain a plurality of identification gait energy diagrams of different action postures in each gait energy diagram, and all the identification gait energy diagrams are input into an identification training model to respectively carry out identity identification and data identification.
For example, the second-step energy diagram and the first-step energy diagram are expressed as 1: 1 to obtain a plurality of gait energy recognition graphs with different action postures.
And S83, respectively obtaining the identification probability distribution of each identification gait energy graph as an identification result.
And obtaining the recognition probability of each recognition gait energy image corresponding to different people, wherein the person with the highest recognition probability is the recognition result of the recognition gait energy image, if the recognition gait energy image which is finally larger than the preset threshold value can accurately recognize the identity, the parameters of the recognition training model are accurately trained, the model parameters of the recognition training model can not be adjusted, otherwise, the parameters of the recognition training model need to be adjusted.
And S84, confirming whether the identification of each identification gait energy image belongs to the second step energy image or the first step energy image by the identification model is accurate or not, and taking the identification result as a data identification result.
And identifying the attribution of each identified gait energy image, determining whether the identification training model can accurately identify the second-step energy image or the first-step energy image in the gait energy image, if the identification training model can be accurately distinguished, adjusting the parameters of the identification training model to regenerate the second-step preprocessed data, otherwise, not adjusting the identification model.
And S85, calculating the identification loss according to the identification result of each identification gait energy graph.
Based on the above embodiment, the identification is performed by identifying the gait energy maps, and the identification loss of all the identification gait energy maps is calculated according to the identification result, for example, the accuracy of identity recognition can be calculated as the loss of identity recognition, and the greater the loss of identity recognition, the more the recognition training model needs to adjust the parameters to perform identity recognition again, for example, when the accuracy of identity recognition is greater than or equal to 75 percent, the identity recognition of the person in the video can be accurately recognized by performing identity recognition through the recognition training model by using the second-step energy diagram, when the identity recognition accuracy is lower than 75 percent, the parameters for identifying and generating the training model need to be adjusted, and the generation of the second-step state energy diagram, the data identification and the identity identification are carried out again, so that the lower the identity identification accuracy is, the larger the parameter adjustment range for identifying and generating the training model is.
For example, the identification loss is calculated by the following calculation method:
lIfor identification loss, n represents the number of identification gait energy patterns,
identifying the identity loss of the ith gait energy image, c represents the number of comparison identities, exp is an exponential function with a natural constant as the base, xi[j]Identification probability, x, for identifying the identity of the gait energy profile as the jth comparison identityi[yi]Identification as the y-th for identifying the gait energy profileiIdentity recognition probability of individual contrasted identities, yiThe number of the corresponding real identity of the video image is obtained.
And S86, calculating the data true and false judgment loss according to the data identification result of each identification gait energy graph.
And judging whether each recognition gait energy image is a first step energy image or a second step energy image, calculating true and false discrimination loss according to the recognition result, and confirming whether the recognition training model can accurately distinguish whether the recognition gait energy image is the second step energy image or the first step energy image according to the true and false discrimination loss.
For example, the data true and false discrimination loss is calculated by the following calculation formula:
lD＝-(mn×logkn+(1-mn)×log(1-kn))；
lDfor judging loss of data true and false, when the nth gait energy recognition image is the second step state energy image, mnIs 1, when the nth identification gait energy diagram is the first step state energy diagram, mnIs 0;
knfor the nth identified gait energy map, the confidence coefficient of the second step energy map is as knWhen the gait energy is larger than the preset threshold value, the gait energy graph is identified as a second step state energy graph, and when k is larger than the preset threshold valuenWhen the value is less than or equal to the preset threshold value, the identification stepThe state energy diagram is a first step state energy diagram.
And S87, judging whether the identity recognition loss and the data true and false judgment loss both meet preset conditions.
For example, comparing the identification loss with a first preset threshold range, comparing the data true and false judgment loss with a second preset threshold range, and judging whether the identification loss meets the first preset threshold range; and judging whether the data true and false judging loss meets a second preset threshold range.
If yes, outputting the identification model; if not, updating the preset parameters of the recognition model by a loss back propagation method, and carrying out S81-S87.
If the accuracy of the identification result is greater than the preset threshold value, and the accuracy of the data identification result is less than the preset threshold value, it can be determined that the identification training model cannot accurately identify the second-step energy map and the first-step energy map, and the identity of the person corresponding to the video can be accurately identified through the second-step energy map, at this time, the parameters of the identification training model are trained, and corresponding parameters can be output to obtain the identification model, otherwise, the preset parameters of the identification training model need to be updated, the parameters in the identification model can be updated through a stochastic gradient descent algorithm, or the parameters in the identification model can be updated through a loss back propagation method, and S81 is performed again.
In this embodiment, it may also be determined whether the second-step energy map is qualified by calculating the mean square error loss of the second-step energy map and the first-step energy map to determine the second-step energy map.
In this step, the mean square error loss of the second-step energy diagram and the first-step energy diagram is calculated, the mean square error is the average of the sum of squared distances of each data from the true value, the deviation degree of the second-step energy diagram from the first-step energy diagram can be obtained by calculating the mean square error loss of the second-step energy diagram and the first-step energy diagram, if the deviation degree of the second-step energy diagram from the first-step energy diagram is too large, it can be determined that the second-step energy diagram obtained by generating the training model is not qualified, therefore, if the mean square error loss is too large, the parameters for generating the training model need to be adjusted, and a new second-step energy diagram is generated again.
For example, the mean square error loss is calculated by:
lgfor mean square error loss, t is the number of pixels in the second-step state energy diagram or the number of pixels in the first-step state energy diagram, pxiIs the gray value, py, of the 0-mean normalization of the ith pixel point in the second-step energy diagramiAnd normalizing the gray value of the 0 mean value of the ith pixel point in the first step state energy diagram.
In a specific embodiment, the embodiment of the present invention provides a method for creating an abnormal crowd information base, which is different from the creating method shown in fig. 1 in that,
and optimizing gait information identification:
s1: and sequentially inputting the gait silhouette image sequences (multi-frame images) p1, p2, … and pn into a basic feature extraction part for generating the network to respectively obtain feature sequences f1, f2, … and fn.
And S2, inputting the characteristics F1, F2, … and fn of the multi-frame input image into the encoder network part of the generation network, and carrying out characteristic weighting fusion to obtain the characteristic F of the whole gait silhouette image sequence.
S3, inputting the characteristics F of the whole gait silhouette image sequence into the decoding network part of the generation network to generate a frame of gait energy image GEI with the same resolution as the input silhouette imagef。
S4 GEIfAnd true GEI in the training data setrAccording to the following steps: the proportional mix of 1 is then input to the recognition network. Wherein the true GEIrIs a GEI generated by selecting those sums from a set of training datafData belonging to the same target and having a walking angle of 54 degrees and being close-fitting to the body.
S5: identifying GEI of network pair inputfAnd GEIrIdentification is carried out while judging which data in input data belong toIn generating the data, which data belongs to the real data.
S6: calculating loss of identity recognition based on the result of identity recognition and the result of discrimination of true and false data_ILoss of sum true and false discriminationD. Based on total loss LD＝α×loss_I+β×loss_DAnd updating the parameters of the judgment network by using a random gradient descent algorithm.
S7, calculating GEI of each group of same identity objectsfAnd GEIrLoss of mean square error (loss)gBased on the total loss LG＝λ×lossg+μ×lossDAnd updating the parameters of the generated network by using a random gradient descent algorithm.
S8, repeating S1-S7 until reaching the model overall convergence condition, namely that the judgment network can hardly distinguish the GEI any morefAnd GEIrWhile correctly recognizing GEIfAnd GEIrThe identity of the corresponding target, so as to obtain the well-learned generative confrontation model M.
As shown in fig. 9, an embodiment of the present invention provides an abnormal crowd information base establishing system, where the abnormal crowd information base establishing system includes a processor and a memory; the processor is used for executing the abnormal crowd information base establishing program stored in the memory so as to realize any one of the abnormal crowd information base establishing methods.
The storage medium for recording the program code of the software program that can realize the functions of the above-described embodiments is provided to the system or apparatus in the above-described embodiments, and the program code stored in the storage medium is read and executed by the computer (or CPU or MPU) of the system or apparatus.
In this case, the program code itself read out from the storage medium performs the functions of the above-described embodiments, and the storage medium storing the program code constitutes an embodiment of the present invention.
As a storage medium for supplying the program code, for example, a flexible disk, hard disk, optical disk, magneto-optical disk, CD-ROM, CD-R, magnetic tape, nonvolatile memory card, ROM, and the like can be used.
The functions of the above-described embodiments may be realized not only by executing the readout program code by the computer, but also by some or all of actual processing operations executed by an OS (operating system) running on the computer according to instructions of the program code.
Further, the embodiments of the present invention also include a case where after the program code read out from the storage medium is written into a function expansion card inserted into the computer or into a memory provided in a function expansion unit connected to the computer, a CPU or the like included in the function expansion card or the function expansion unit performs a part of or the whole of the processing in accordance with the command of the program code, thereby realizing the functions of the above-described embodiments.
The embodiment of the invention provides a storage medium, wherein one or more programs are stored in the storage medium, and the one or more programs can be executed by one or more processors to realize the abnormal crowd information base establishing method.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. An abnormal crowd information base establishing method is characterized by comprising the following steps:
acquiring gait preprocessing data of walking of people in the video image;
extracting identity characteristics of the gait preprocessing data to obtain identity characteristic data corresponding to the gait preprocessing data;
respectively calculating similarity values of the identity characteristic data and each group of pre-stored abnormal characteristic data;
and when any similarity value is larger than a preset threshold value, acquiring face information corresponding to the identity characteristic data, and storing the face information into the abnormal crowd information base.
2. The method for establishing the abnormal crowd information base according to claim 1, wherein the method for acquiring the abnormal feature data comprises the following steps:
inputting a plurality of abnormal video images containing abnormal crowd information, and acquiring abnormal gait preprocessing data of people walking in each abnormal video image;
performing identity recognition on each abnormal gait preprocessing data to obtain a plurality of groups of identity characteristic data to be confirmed;
respectively calculating the abnormal similarity value of each group of identity characteristic data to be confirmed and other identity characteristic data to be confirmed;
counting the number of abnormal similarity values of each group of identity characteristic data to be confirmed and other identity characteristic data to be confirmed, which are larger than a preset similarity value, as abnormal number;
and taking the identity characteristic data to be confirmed corresponding to the abnormal quantity larger than the preset quantity as abnormal characteristic data.
3. The abnormal crowd information base creation method according to claim 2,
the calculating of the abnormal similarity value between each group of the identity characteristic data to be confirmed and other identity characteristic data to be confirmed specifically includes:
vectorizing all the identity characteristic data to be confirmed respectively to obtain a plurality of groups of identity characteristic data vectors to be confirmed;
respectively calculating cosine values of each group of identity characteristic data vectors to be confirmed and other identity characteristic data vectors to be confirmed as the abnormal similarity value;
the calculating the similarity value between the identity characteristic data and each pre-stored group of abnormal characteristic data respectively specifically includes:
vectorizing the identity characteristic data and all the abnormal characteristic data respectively to obtain identity characteristic data vectors and a plurality of groups of abnormal characteristic data vectors;
and respectively calculating cosine values of each group of abnormal characteristic data vectors and identity characteristic data vectors as the similarity values.
4. The method for establishing the abnormal crowd information base according to claim 1, wherein the obtaining of the face information corresponding to the identity feature data specifically comprises:
acquiring the spatial coordinates of the face characteristic points corresponding to the identity characteristic data;
and constructing a corresponding human face mesh model according to the space coordinates of all the human face characteristic points to serve as the human face information.
5. The method for establishing the abnormal crowd information base according to claim 4, wherein the obtaining of the spatial coordinates of the face feature points corresponding to the identity feature data specifically comprises:
acquiring a plurality of frame images in the video image;
respectively acquiring pixel coordinates of the face characteristic points corresponding to the identity characteristic data in each frame image;
and calculating the space coordinates of the face characteristic points according to the internal reference information and the external reference information of the camera for acquiring the video image and the pixel coordinates of the face characteristic points in each frame image.
6. The method for establishing the abnormal crowd information base according to claim 4, wherein the constructing a corresponding face mesh model according to the spatial coordinates of all the face feature points specifically comprises:
and triangulating all the human face characteristic points according to the space coordinates of the human face characteristic points to obtain topological relations of all the human face characteristic points and construct a corresponding human face mesh model.
7. The method for establishing the abnormal population information base according to claim 1, wherein the step of performing identity feature extraction on the gait preprocessing data to obtain identity feature data corresponding to the gait preprocessing data specifically comprises:
inputting the gait preprocessing data into a recognition model;
and acquiring the identity characteristic data output after the identification model identifies the gait preprocessing data.
8. The method for establishing the abnormal crowd information base according to any one of claims 1 to 7, wherein the acquiring gait preprocessing data of the walking of the person in the video image specifically comprises:
acquiring continuous frame images in a video image;
detecting an image area containing human figures from the continuous frame images by using a detection algorithm;
extracting a human-shaped outline in the human-shaped image area to generate a human-shaped outline segmentation graph;
aligning the human shape center and the image center of each frame of the human shape contour segmentation image to generate a primary gait silhouette image;
scaling the human-shaped contour in each frame of primary gait silhouette image to a uniform resolution ratio to generate a gait silhouette image sequence;
respectively acquiring silhouette gait features of each frame of gait silhouette image in the gait silhouette image sequence to form silhouette gait preprocessing data;
calculating the correlation similarity of each frame of silhouette gait features in the silhouette gait preprocessing data;
and performing weighted fusion on the silhouette gait features according to the correlation similarity to obtain the gait preprocessing data.
9. The system for establishing the abnormal crowd information base is characterized by comprising a processor and a memory; the processor is used for executing an abnormal crowd information base establishing program stored in the memory so as to realize the abnormal crowd information base establishing method of any one of claims 1-8.
10. A storage medium storing one or more programs, wherein the one or more programs are executable by one or more processors to implement the abnormal crowd information base creation method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811302295.2A CN111144166A (en) | 2018-11-02 | 2018-11-02 | Method, system and storage medium for establishing abnormal crowd information base |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811302295.2A CN111144166A (en) | 2018-11-02 | 2018-11-02 | Method, system and storage medium for establishing abnormal crowd information base |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111144166A true CN111144166A (en) | 2020-05-12 |
Family
ID=70515432
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811302295.2A Pending CN111144166A (en) | 2018-11-02 | 2018-11-02 | Method, system and storage medium for establishing abnormal crowd information base |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111144166A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112022166A (en) * | 2020-08-08 | 2020-12-04 | 司法鉴定科学研究院 | Human body identity recognition method and system based on medical movement disorder feature recognition |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102799873A (en) * | 2012-07-23 | 2012-11-28 | 青岛科技大学 | Human body abnormal behavior recognition method |
| CN104077804A (en) * | 2014-06-09 | 2014-10-01 | 广州嘉崎智能科技有限公司 | Method for constructing three-dimensional human face model based on multi-frame video image |
| CN105827979A (en) * | 2016-04-29 | 2016-08-03 | 维沃移动通信有限公司 | Prompting photographing method and mobile terminal |
| CN107273866A (en) * | 2017-06-26 | 2017-10-20 | 国家电网公司 | A kind of human body abnormal behaviour recognition methods based on monitoring system |
| CN108244744A (en) * | 2016-12-29 | 2018-07-06 | ***通信有限公司研究院 | A kind of method of moving state identification, sole and footwear |
| CN108416276A (en) * | 2018-02-12 | 2018-08-17 | 浙江大学 | The abnormal gait detection method of side gait video based on people |
-
2018
- 2018-11-02 CN CN201811302295.2A patent/CN111144166A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102799873A (en) * | 2012-07-23 | 2012-11-28 | 青岛科技大学 | Human body abnormal behavior recognition method |
| CN104077804A (en) * | 2014-06-09 | 2014-10-01 | 广州嘉崎智能科技有限公司 | Method for constructing three-dimensional human face model based on multi-frame video image |
| CN105827979A (en) * | 2016-04-29 | 2016-08-03 | 维沃移动通信有限公司 | Prompting photographing method and mobile terminal |
| CN108244744A (en) * | 2016-12-29 | 2018-07-06 | ***通信有限公司研究院 | A kind of method of moving state identification, sole and footwear |
| CN107273866A (en) * | 2017-06-26 | 2017-10-20 | 国家电网公司 | A kind of human body abnormal behaviour recognition methods based on monitoring system |
| CN108416276A (en) * | 2018-02-12 | 2018-08-17 | 浙江大学 | The abnormal gait detection method of side gait video based on people |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112022166A (en) * | 2020-08-08 | 2020-12-04 | 司法鉴定科学研究院 | Human body identity recognition method and system based on medical movement disorder feature recognition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108710868B (en) | Human body key point detection system and method based on complex scene | |
| CN111488804B (en) | Labor insurance product wearing condition detection and identity identification method based on deep learning | |
| CN111144165B (en) | Gait information identification method, system and storage medium | |
| Salimi et al. | Visual-based trash detection and classification system for smart trash bin robot | |
| US10007850B2 (en) | System and method for event monitoring and detection | |
| CN109492581A (en) | A kind of human motion recognition method based on TP-STG frame | |
| CN104599287B (en) | Method for tracing object and device, object identifying method and device | |
| US9183431B2 (en) | Apparatus and method for providing activity recognition based application service | |
| CN111382679A (en) | Method, system and equipment for evaluating severity of gait dyskinesia of Parkinson's disease | |
| CN101807245A (en) | Artificial neural network-based multi-source gait feature extraction and identification method | |
| CN110633643A (en) | Abnormal behavior detection method and system for smart community | |
| CN108960047A (en) | Face De-weight method in video monitoring based on the secondary tree of depth | |
| JP5940862B2 (en) | Image processing device | |
| CN114269243A (en) | Fall risk evaluation system | |
| CN111144167A (en) | Gait information identification optimization method, system and storage medium | |
| CN112989889A (en) | Gait recognition method based on posture guidance | |
| KR102187831B1 (en) | Control method, device and program of congestion judgment system using cctv | |
| CN110532838A (en) | Object test equipment and method and storage medium | |
| CN117475502B (en) | Iris and face fusion recognition method and system based on mine | |
| Jinnovart et al. | Abnormal gait recognition in real-time using recurrent neural networks | |
| Jia et al. | Self-supervised person detection in 2D range data using a calibrated camera | |
| CN114792429A (en) | Multi-view-angle tumbling detection method and device and storage medium | |
| CN111144166A (en) | Method, system and storage medium for establishing abnormal crowd information base | |
| CN117037264A (en) | Prison personnel abnormal behavior identification method based on target and key point detection | |
| CN117541994A (en) | Abnormal behavior detection model and detection method in dense multi-person scene |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20210127 Address after: 315016 9-3, building 91, 16 Buzheng lane, Haishu District, Ningbo City, Zhejiang Province Applicant after: Yinhe shuidi Technology (Ningbo) Co.,Ltd. Address before: Room 501-1753, Development Zone office building, 8 Xingsheng South Road, Miyun District Economic Development Zone, Beijing Applicant before: Watrix Technology (Beijing) Co.,Ltd. |
|
| TA01 | Transfer of patent application right | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200512 |
|
| RJ01 | Rejection of invention patent application after publication |