WO2020135127A1 - 一种行人识别方法及装置 - Google Patents
一种行人识别方法及装置 Download PDFInfo
- Publication number
- WO2020135127A1 WO2020135127A1 PCT/CN2019/125667 CN2019125667W WO2020135127A1 WO 2020135127 A1 WO2020135127 A1 WO 2020135127A1 CN 2019125667 W CN2019125667 W CN 2019125667W WO 2020135127 A1 WO2020135127 A1 WO 2020135127A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- pedestrian
- feature
- node
- target
- similarity
- Prior art date
Links
- 238000000034 method Methods 0.000 title claims abstract description 67
- 230000001815 facial effect Effects 0.000 claims abstract description 66
- 238000003860 storage Methods 0.000 claims description 22
- 230000009471 action Effects 0.000 claims description 18
- 238000004590 computer program Methods 0.000 claims description 11
- 238000001914 filtration Methods 0.000 claims description 7
- 238000012216 screening Methods 0.000 claims description 3
- 238000004140 cleaning Methods 0.000 claims description 2
- 238000012545 processing Methods 0.000 description 25
- 238000005516 engineering process Methods 0.000 description 18
- 238000010586 diagram Methods 0.000 description 17
- 230000009286 beneficial effect Effects 0.000 description 9
- 238000004891 communication Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 7
- 230000008901 benefit Effects 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 4
- 230000005236 sound signal Effects 0.000 description 4
- 239000013598 vector Substances 0.000 description 4
- 230000001133 acceleration Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 239000000835 fiber Substances 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000036544 posture Effects 0.000 description 2
- 230000001902 propagating effect Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 1
- 241000282412 Homo Species 0.000 description 1
- 230000001364 causal effect Effects 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 229910052802 copper Inorganic materials 0.000 description 1
- 239000010949 copper Substances 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001052 transient effect Effects 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
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2413—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- 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
-
- 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
- G06V40/70—Multimodal biometrics, e.g. combining information from different biometric modalities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
Definitions
- the present disclosure relates to the field of computer vision technology, and in particular, to a pedestrian recognition method and device.
- Pedestrian recognition technology plays an important role in the field of security monitoring such as smart cities and public security, and is also an important topic in the field of computer vision.
- Pedestrian recognition is a challenging technology.
- Pedestrian recognition technologies in related technologies are often based on human characteristics such as the clothes of pedestrians and the attributes of people. Typical technologies may include pedestrian re-identification (Person ReID), for example.
- Person ReID pedestrian re-identification
- human body characteristics are often not unique, such as pedestrians changing clothes and so on.
- the present disclosure provides a pedestrian recognition method and device.
- a pedestrian recognition method including:
- the feature database includes a plurality of pedestrian feature nodes
- the pedestrian feature nodes include facial features, human body features corresponding to pedestrian images, and relationship features with other pedestrian feature nodes.
- the technical solutions provided by the embodiments of the present disclosure may include the following beneficial effects:
- the pedestrian recognition method provided by the embodiments of the present disclosure may search for the image of the target pedestrian from the feature database based on the joint retrieval of facial features and human features.
- the joint retrieval method based on facial features and human features can take advantage of the unique advantages of facial features, as well as the recognition advantages of human features in special situations such as obscured faces and blurred faces.
- the feature database may include relationship features between the pedestrian feature node and other pedestrian feature nodes. In this way, one of the pedestrian feature nodes may be used to search for a pedestrian feature node associated with the pedestrian feature node. Based on this, the calculation amount of pedestrian search can be greatly reduced, and the search efficiency can be improved.
- the relationship feature is set to be determined according to the following parameters: facial image quality value, human image quality value, human face feature, and human feature.
- the technical solutions provided by the embodiments of the present disclosure may include the following beneficial effects: the face image quality value and the human body image quality value are used as parameters for calculating the associated feature, which may improve the accuracy of the calculation result of the relationship feature .
- the relationship feature includes a similar node association relationship
- the similar node association relationship is set to be determined in the following manner:
- the technical solutions provided by the embodiments of the present disclosure may include the following beneficial effects: determining the association relationship of similar nodes based on the face image quality value, the human image quality value, the face characteristics, and the body characteristics, and according to the attributes between the face characteristics and the body characteristics Difference, set the priority of facial features higher than the priority of human features, and accurately determine the association relationship of similar nodes.
- the at least one target node of the image feature is obtained from a feature database, and pedestrian images corresponding to the at least one target node are used as the image of the target pedestrian ,include:
- the image feature as a target feature node, and determining at least one search path from the target feature node to the pedestrian feature node, where the search path is formed by connecting multiple pedestrian feature nodes having the similar node association relationship;
- Pedestrian images corresponding to the at least one target node are used as the target pedestrian images.
- the technical solutions provided by the embodiments of the present disclosure may include the following beneficial effects: the similarity between the target feature node and the pedestrian feature node is determined based on multiple search paths, and the determination method of the similarity may be optimized.
- the at least one target node of the image feature is obtained from a feature database, and pedestrian images corresponding to the at least one target node are used as the image of the target pedestrian ,include:
- a pedestrian image corresponding to each of the at least one target node is used as the target pedestrian image.
- the technical solution provided by the embodiments of the present disclosure may include the following beneficial effects: some nodes are removed from the at least one similar node in a manner of providing post-processing.
- the selecting at least one target node from the at least one similar node includes:
- the technical solutions provided by the embodiments of the present disclosure may include the following beneficial effects: filtering out similar nodes whose facial features deviate too much from the central value of the face clustering based on the cluster center value from the at least one similar node, and the remaining Similar nodes are used as target nodes.
- the method before the clearing the second set of similar nodes from the at least one similar node, the method further includes:
- At least one human feature node is selected from the at least one similar node, the human face feature in the human feature node has a zero value, and the human feature has a non-zero value;
- the technical solution provided by the embodiments of the present disclosure may include the following beneficial effects: further filtering out human bodies in similar nodes whose facial features are zero and human features are non-zero based on the clustering central value from the at least one similar node Nodes with features that deviate from the central value of human clustering.
- the method further includes:
- an action trajectory of the target pedestrian is acquired, and the action trajectory includes time information and/or location information.
- the technical solutions provided by the embodiments of the present disclosure may include the following beneficial effects: Based on the pedestrian's action trajectory, the daily activities of the target pedestrian may be obtained, which is of great value to the field of public security and psychological analysis
- the method further includes:
- the image features of the new pedestrian image are used as new pedestrian feature nodes and updated to the feature database.
- the feature database may be continuously updated so that the feature database maintains the latest information.
- a pedestrian recognition device including:
- An image feature acquisition module configured to acquire image features of a target pedestrian image, where the image features include facial features and human features;
- a target node obtaining module configured to obtain at least one target node of the image feature from a feature database, and use pedestrian images corresponding to the at least one target node as the image of the target pedestrian;
- the feature database includes a plurality of pedestrian feature nodes
- the pedestrian feature nodes include facial features, human body features corresponding to pedestrian images, and relationship features with other pedestrian feature nodes.
- the relationship feature is set to be determined according to the following parameters: facial image quality value, human image quality value, human face feature, and human feature.
- the relationship feature includes a similar node association relationship
- the similar node association relationship is set to be determined in the following manner:
- the target node acquisition module includes:
- a path determination submodule configured to use the image feature as a target feature node, and determine at least one search path from the target feature node to the pedestrian feature node, where the search path is composed of multiple related relationships of the similar nodes Pedestrian feature nodes are connected;
- a path score determination submodule configured to determine a minimum value in the similarity between two adjacent pedestrian feature nodes in the search path, and use the minimum value as the path score of the search path;
- a node similarity determination submodule configured to determine a maximum value among path scores of the at least one search path, and use the maximum value as the similarity between the target feature node and the pedestrian feature node;
- a target node determination submodule configured to use at least one pedestrian feature node whose similarity with the target feature node is greater than or equal to the preset face similarity threshold or the preset human similarity threshold as the target feature node At least one target node, and use pedestrian images corresponding to the at least one target node as the image of the target pedestrian.
- the target node acquisition module includes:
- a similar node search submodule configured to search for at least one similar node of the image feature from the feature database based on the relationship features of the plurality of pedestrian feature nodes;
- a target node selection sub-module for selecting at least one target node from the at least one similar node
- the pedestrian image acquisition submodule is configured to use pedestrian images corresponding to the at least one target node as the target pedestrian image.
- the target node selection submodule includes:
- a face center value determining unit configured to determine a face clustering center value of face features in the at least one similar node
- a node filtering unit configured to filter at least one human face human feature node from the at least one similar node, and the human face features and human body features in the human face human feature nodes are non-zero values;
- a node dividing unit used to determine the face similarity between the face feature and the face clustering center value in the at least one face human feature node, and the face similarity is greater than or equal to the preset similarity
- Nodes with a degree threshold are divided into a first set of similar nodes, and nodes with a face similarity less than the preset similarity threshold are divided into a second set of similar nodes;
- the node removal unit is configured to remove the second set of similar nodes from the at least one similar node, and use the pedestrian images corresponding to the at least one similar node after removal as the target pedestrian images.
- the target node selection sub-module further includes:
- a human body center value determining unit configured to determine a first human body clustering center value of human body features in the first similarity node set, and a second human body clustering center value of human body features in the second similarity node set;
- a human body node screening unit configured to screen out at least one human body feature node from the at least one similar node, the human face feature in the human body feature node has a zero value, and the human body feature has a non-zero value;
- the similarity determination unit is configured to determine the first human body similarity between the human body feature and the first human body clustering center value in the at least one human body feature node, and the second human body clustering center value respectively The second human similarity;
- a node adding unit is used to add a human body feature node corresponding to the second human body similarity when the second human body similarity is greater than the first human body similarity.
- the device further includes:
- a pedestrian trajectory acquisition module is used to acquire the action trajectory of the target pedestrian based on the image of the target pedestrian, the action trajectory including time information and/or location information.
- the device further includes:
- a new data acquisition module used to extract image features of the new pedestrian image in the case of acquiring a new pedestrian image
- the data updating module is used to update the image features of the new pedestrian image as new pedestrian feature nodes to the feature database.
- an electronic device including:
- Memory for storing processor executable instructions
- the processor is configured to perform the above pedestrian recognition method.
- a non-transitory computer-readable storage medium which, when instructions in the storage medium are executed by a processor, enables the processor to execute the aforementioned pedestrian recognition method.
- a computer program includes computer readable code, and when the computer readable code runs in an electronic device, the processor in the electronic device executes In order to realize the above pedestrian recognition method.
- Fig. 1 is a flowchart of a method for pedestrian recognition according to an exemplary embodiment.
- Fig. 2 is a scene diagram shown according to an exemplary embodiment.
- Fig. 3 is a block diagram of a device according to an exemplary embodiment.
- Fig. 4 is a block diagram of a device according to an exemplary embodiment.
- Fig. 5 is a block diagram of a device according to an exemplary embodiment.
- Pedestrian recognition technology of related technologies is often based on face recognition technology or human body recognition technology.
- Pedestrian recognition technology based on face recognition technology often recognizes target pedestrians through the facial features of pedestrians.
- the captured facial images of pedestrians often have obstructions, side angles, too far away, etc. Therefore, the way of identifying target pedestrians through facial features often also has a low recall rate And accuracy.
- the pedestrian recognition method provided by the present disclosure may construct a feature database based on facial features and human features based on the joint retrieval of human faces and human bodies. Based on the facial features and human features of the target pedestrian, the facial features and human features similar to the facial features and human features of the target pedestrian can be searched from the feature database, and the similar facial features The pedestrian image corresponding to the human body feature is used as the target pedestrian image.
- FIG. 1 is a method flowchart of an embodiment of a pedestrian recognition method provided by the present disclosure.
- the present disclosure provides method operation steps as shown in the following embodiments or drawings, more or less operation steps may be included in the method based on conventional or without creative labor. Among the steps that do not logically need a causal relationship, the execution order of these steps is not limited to the execution order provided by the embodiments of the present disclosure.
- An embodiment of the present disclosure provides a pedestrian recognition method, which can be applied to any image processing apparatus, for example, the method can be applied to a terminal device or a server, or can also be applied to other processing devices, where the terminal device Can include user equipment (User Equipment, UE), mobile devices, user terminals, terminals, cellular phones, cordless phones, personal digital processing (Personal Digital Assistant, PDA), handheld devices, computing devices, in-vehicle devices, wearable devices, etc.
- the pedestrian recognition method may be implemented by the processor calling computer-readable instructions stored in the memory.
- FIG. 1 an embodiment of the pedestrian recognition method provided by the present disclosure is shown in FIG. 1, and the method may include:
- S101 Acquire image features of a target pedestrian image, where the image features include facial features and human features.
- S103 Acquire at least one target node of the image feature from the feature database, and use a pedestrian image corresponding to the at least one target node as the target pedestrian image;
- the feature database includes a plurality of pedestrian feature nodes
- the pedestrian feature nodes include facial features, human body features corresponding to pedestrian images, and relationship features with other pedestrian feature nodes.
- a target pedestrian image used as a search basis may be obtained.
- the target pedestrian image may include, for example, Zhang San’s ID photo, life photo, and street Take photos, portraits, etc.
- the target pedestrian image may include a face image, a human body image, or a human face image. Based on this, image features can be obtained from the target pedestrian image, and the image features can include facial features and human features.
- facial features and human body features can be expressed using feature vectors.
- the facial feature vectors can include multiple components such as Euclidean distance, curvature, and angle between key points of the human face.
- the human feature can be It includes various components such as proportions, postures, and clothing characteristics of human body parts. The disclosure does not limit the extraction method of face features and human features.
- At least one target node of the image feature may be acquired from a preset feature database based on the image feature.
- the feature database may include multiple pedestrian feature nodes, and the pedestrian feature nodes include facial features, human features, and relationship features with other pedestrian feature nodes corresponding to pedestrian images.
- the pedestrian feature nodes have a one-to-one correspondence with pedestrian images. For example, if the feature database can include 1 million pedestrian feature nodes, the 1 million pedestrian feature nodes correspond to 100 Ten thousand pedestrian images. Then, the purpose of the embodiments of the present disclosure is to search out the target pedestrian image from the one million pedestrian images.
- the pedestrian image may include a human face image, a human body image, a human face image, and based on this, the human face characteristics and human body characteristics of the pedestrian image may be extracted, and the human face characteristics and human body characteristics may be set In the pedestrian feature node corresponding to the pedestrian image.
- the relationship feature with other pedestrian feature nodes may be set to be determined according to the face feature and the human feature.
- the relationship feature includes a similar node association relationship, and the similar node association relationship includes two pedestrian feature nodes having a high degree of similarity, that is, the two pedestrian feature nodes are likely to be feature nodes of the same pedestrian .
- Another pedestrian feature node can be searched through one of the pedestrian feature nodes.
- the face features of the two pedestrian feature nodes are non-zero values and the similarity between the face features of the two pedestrian feature nodes is greater than or equal to the preset face similarity threshold To determine that the two pedestrian feature nodes are related to similar nodes.
- the body features of the two pedestrian feature nodes are non-zero values and the similarity between the body features of the two pedestrian feature nodes is greater than or equal to the preset body similarity threshold, it is determined
- the two pedestrian feature nodes are similar node association relationships.
- the similarity between the facial features or the human features can be calculated using a feature vector.
- the similarity can be a cosine value between two feature vectors. The disclosure does not limit the calculation method of the similarity between two features.
- the relationship feature is set to be determined according to the following parameters: face image quality value, human image quality value, human face feature, and human feature.
- face image quality value can be calculated based on the parameters of the human face 3-dimensional posture, the degree of blurring of the picture, the exposure quality, etc.
- human body image quality value can be calculated according to the parameters such as the degree of occlusion, the degree of crowding, the integrity of the subject Calculated.
- the pedestrian feature node may further include a face image quality value and a human body image quality value.
- the image features of the target pedestrian image may also include a face image quality value and a human body image quality value.
- the similarity between the face features of the two pedestrian feature nodes may be calculated first. This is due to the uniqueness and accuracy of facial features, so the priority of facial features can be set higher than the priority of human features.
- the similarity between the facial features of the two pedestrian feature nodes may be determined when the smaller facial image quality value of the two pedestrian feature nodes is greater than or equal to the preset facial image quality threshold. That is to say, when the face features in the two pedestrian feature nodes are non-zero values, and the face image quality values in the two pedestrian feature nodes are greater than or equal to the preset face image quality threshold, it is determined that the Similarity between face features of two pedestrian feature nodes. If it is calculated that the similarity between the face features is greater than or equal to a preset face similarity threshold, it is determined that the two pedestrian feature nodes are similar node association relationships.
- the smaller face image quality value of the two pedestrian feature nodes is less than a preset face image quality threshold, it may be determined whether the human features of the two pedestrian feature nodes are non-zero values.
- the calculation may be performed The similarity between human features of two pedestrian feature nodes. In a case where the similarity between the human body features is greater than or equal to a preset human body similarity threshold, it may be determined that the two pedestrian feature nodes are similar node association relationships.
- the preset face image quality threshold for the setting of the preset face image quality threshold, the preset human body image quality threshold, the preset face similarity threshold, and the preset human body similarity threshold, reference may be made to an empirical value, It can also be obtained based on sample data statistics, which is not limited in this disclosure.
- a network-type relationship graph may be formed between the multiple pedestrian feature nodes. Through one of the pedestrian feature nodes, a pedestrian feature node with a similar node association relationship can be searched from the feature database.
- the expression manner of the feature database may include a network structure such as a heterogeneous graph.
- the The image feature is used as a target feature node, and at least one search path that reaches the target feature node from the target feature node is determined, and the search path is formed by connecting a plurality of pedestrian feature nodes having the association relationship of the similar nodes.
- a minimum value in the similarity between two adjacent pedestrian feature nodes in the search path may be determined, and the minimum value may be used as the path score of the search path.
- a maximum value among the path scores of the at least one search path may be determined, and the maximum value is used as the similarity between the target feature node and the pedestrian feature node.
- the target feature node is set to node A
- nodes B-H are pedestrian feature nodes in the feature database.
- node C and node D in path 1 have similar node associations between node D and node B
- node E in path 3 There are similar node associations with node F, node F and node G, node G and node H, and node H and node B.
- the direct similarity between node A and node B is 0.5.
- node B will not be determined as node A Similar nodes.
- both node A and node B are characteristics of the target pedestrian, but node A may correspond to the front image of the target pedestrian wearing black clothes, and node B may correspond to the side image of the target pedestrian wearing yellow clothes, then, The direct similarity between node A and node B may be relatively low. However, through other related nodes to reach B, you can find the close relationship between node A and node B. For example, in path 1, node C is the frontal image of the target pedestrian's face, and node D is the frontal image of the target pedestrian wearing that yellow dress.
- the path score of each path may be calculated separately, and the path score may include the minimum value of the similarity between two adjacent pedestrian feature nodes in the path.
- the path score of path 1 is 0.6
- the path score of path 2 is 0.5
- the path score of path 3 is 0.8.
- the largest path score of the three paths is 0.8
- node A and node B can be determined
- the similarity between them is 0.8, which is greater than 0.7. Therefore, node A and node B are target nodes of target feature node A.
- the feature database can be searched in the same manner as the method in the above embodiment, at least one target node corresponding to the target feature node is searched, and pedestrian images corresponding to the at least one target node as the target pedestrian Image.
- the process of acquiring at least one target node of the image feature from a feature database, and using pedestrian images corresponding to the at least one target node as the image of the target pedestrian in Based on the relationship features of the plurality of pedestrian feature nodes, after searching for at least one similar node of the image feature from the feature database, filtering out those facial features from the at least one similar node that is too far away from the face cluster Similar nodes with similar center values, and take the remaining similar nodes as target nodes.
- the method of acquiring the similar node reference may be made to the method of searching for the target node B of the node A in the foregoing example.
- the face clustering center value of the face features in the at least one similar node can be determined. Then, at least one human face human feature node is selected from the at least one similar node, and the human face features and human body features in the human face human feature nodes are non-zero values. Then, a node whose face feature deviates too far from the center value of the face clustering may be filtered from the at least one face human feature node.
- the face similarity between the face feature in the at least one face human feature node and the face clustering center value may be calculated separately, and the face similarity is greater than or equal to a preset similarity threshold
- the nodes of are divided into a first set of similar nodes, and the nodes whose face similarity is less than the preset similarity threshold are divided into a second set of similar nodes.
- the similar nodes in the second similar node set have a high possibility that they are not nodes corresponding to the target pedestrian. Therefore, the second set of similar nodes may be cleared from the at least one similar node, and the pedestrian images corresponding to the at least one similar node after clearing may be used as the target pedestrian images.
- the at least one similar node may be further filtered to filter out human features in similar nodes whose facial features are zero-valued and human features are non-zero-valued, deviating from the clustering center of the human body Value node.
- the first human clustering center value of human body features in the first similarity node set and the second human clustering center value of human body features in the second similarity node set may be calculated.
- at least one human feature node may be selected from the at least one similar node, and the human face feature in the human feature node has a zero value and the human feature has a non-zero value.
- the second similar node set is the node set to be filtered out. If the second human body similarity is greater than the first human body similarity, it indicates that the human body characteristic also deviates from the human body characteristic of the target pedestrian. Therefore, the human body feature nodes corresponding to the second human body similarity greater than the first human body similarity may be added to the second similarity node set. Thereafter, the second set of similar nodes may be cleared from the at least one similar node.
- multiple target pedestrian images are often used for feature search.
- feature search can be performed on the multiple target pedestrian images, respectively, and at least one target node is obtained.
- at least one target node obtained separately may be merged, and a pedestrian image corresponding to the at least one target node after the merger may be used as the image of the target pedestrian.
- the action trajectory of the target pedestrian may be acquired based on the image of the target pedestrian, the action trajectory including time information and/or location information .
- the action trajectory of the target pedestrian includes, for example, 10:30, October 1, 2018: Guanqian Street, Suzhou ⁇ 11:03, October 1, 2018: Guanqian Street, Suzhou ⁇ 10, 2018 12:50 on January 1st: XX parking lot in Suzhou ⁇ ... ⁇ 21:37 on October 1, 2018: XX community in Suzhou city. Based on the above action trajectory, the daily activities of the target pedestrian can be obtained, which is of great value in the field of public security and psychological analysis.
- the feature database may be updated.
- the image frames in the surveillance video may be extracted.
- feature extraction can be performed on the image frame to extract image features of the image frame, and the image features include facial features and human features.
- the image features in the image frame are used as new pedestrian feature nodes and updated to the feature database.
- the pedestrian recognition methods provided by the various embodiments of the present disclosure can search for the image of the target pedestrian from the feature database based on the joint retrieval of facial features and human features.
- the joint retrieval method based on facial features and human features can take advantage of the unique advantages of facial features, as well as the recognition advantages of human features in special situations such as obscured faces and blurred faces.
- the feature database may include relationship features between the pedestrian feature node and other pedestrian feature nodes. In this way, one of the pedestrian feature nodes may be used to search for a pedestrian feature node associated with the pedestrian feature node. Based on this, the calculation amount of pedestrian search can be greatly reduced, and the search efficiency can be improved.
- FIG. 3 shows a block diagram of a pedestrian recognition device according to an embodiment of the present disclosure. As shown in FIG. 3, the device 300 includes:
- the image feature acquisition module 301 is used to acquire image features of a target pedestrian image, where the image features include facial features and human features;
- a target node obtaining module 303 configured to obtain at least one target node of the image feature from a feature database, and use pedestrian images corresponding to the at least one target node as the image of the target pedestrian;
- the feature database includes a plurality of pedestrian feature nodes
- the pedestrian feature nodes include facial features, human body features corresponding to pedestrian images, and relationship features with other pedestrian feature nodes.
- the relationship feature is set to be determined according to the following parameters: facial image quality value, human image quality value, human face feature, and human feature.
- the relationship feature includes a similar node association relationship
- the similar node association relationship is set to be determined in the following manner:
- the target node acquisition module includes:
- a path determination submodule configured to use the image feature as a target feature node, and determine at least one search path from the target feature node to the pedestrian feature node, where the search path is composed of multiple related relationships of the similar nodes Pedestrian feature nodes are connected;
- a path score determination submodule configured to determine a minimum value in the similarity between two adjacent pedestrian feature nodes in the search path, and use the minimum value as the path score of the search path;
- a node similarity determination submodule configured to determine a maximum value among path scores of the at least one search path, and use the maximum value as the similarity between the target feature node and the pedestrian feature node;
- a target node determination submodule configured to use at least one pedestrian feature node whose similarity with the target feature node is greater than or equal to the preset face similarity threshold or the preset human similarity threshold as the target feature node At least one target node, and use pedestrian images corresponding to the at least one target node as the image of the target pedestrian.
- the target node acquisition module includes:
- a similar node search submodule configured to search for at least one similar node of the image feature from the feature database based on the relationship features of the plurality of pedestrian feature nodes;
- a target node selection sub-module for selecting at least one target node from the at least one similar node
- the pedestrian image acquisition submodule is configured to use pedestrian images corresponding to the at least one target node as the target pedestrian image.
- the target node selection submodule includes:
- a face center value determining unit configured to determine a face clustering center value of face features in the at least one similar node
- a node filtering unit configured to filter at least one human face human feature node from the at least one similar node, and the human face features and human body features in the human face human feature nodes are non-zero values;
- a node dividing unit used to determine the face similarity between the face feature and the face clustering center value in the at least one face human feature node, and the face similarity is greater than or equal to the preset similarity
- Nodes with a degree threshold are divided into a first set of similar nodes, and nodes with a face similarity less than the preset similarity threshold are divided into a second set of similar nodes;
- the node removal unit is configured to remove the second set of similar nodes from the at least one similar node, and use the pedestrian images corresponding to the at least one similar node after removal as the target pedestrian images.
- the target node selection sub-module further includes:
- a human body center value determining unit configured to determine a first human body clustering center value of human body features in the first similarity node set, and a second human body clustering center value of human body features in the second similarity node set;
- a human body node screening unit configured to screen out at least one human body feature node from the at least one similar node, the human face feature in the human body feature node has a zero value, and the human body feature has a non-zero value;
- the similarity determination unit is configured to determine the first human body similarity between the human body feature and the first human body clustering center value in the at least one human body feature node, and the second human body clustering center value respectively The second human similarity;
- a node adding unit is used to add a human body feature node corresponding to the second human body similarity when the second human body similarity is greater than the first human body similarity.
- the device further includes:
- a pedestrian trajectory acquisition module is used to acquire the action trajectory of the target pedestrian based on the image of the target pedestrian, the action trajectory including time information and/or location information.
- the device further includes:
- a new data acquisition module used to extract image features of the new pedestrian image in the case of acquiring a new pedestrian image
- the data updating module is used to update the image features of the new pedestrian image as new pedestrian feature nodes to the feature database.
- An embodiment of the present disclosure also provides an electronic device, including: a processor; a memory for storing processor-executable instructions; wherein the processor is configured as the method described in each of the foregoing embodiments.
- the electronic device may be provided as a terminal, server, or other form of device.
- Fig. 4 is a block diagram of an electronic device 800 according to an exemplary embodiment.
- the electronic device 800 may be a terminal such as a mobile phone, a computer, a digital broadcasting terminal, a messaging device, a game console, a tablet device, a medical device, a fitness device, and a personal digital assistant.
- the electronic device 800 may include one or more of the following components: a processing component 802, a memory 804, a power supply component 806, a multimedia component 808, an audio component 810, an input/output (I/O) interface 812, and a sensor component 814 , ⁇ 816.
- the processing component 802 generally controls the overall operations of the electronic device 800, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations.
- the processing component 802 may include one or more processors 820 to execute instructions to complete all or part of the steps in the above method.
- the processing component 802 may include one or more modules to facilitate interaction between the processing component 802 and other components.
- the processing component 802 may include a multimedia module to facilitate interaction between the multimedia component 808 and the processing component 802.
- the memory 804 is configured to store various types of data to support operation at the electronic device 800. Examples of these data include instructions for any application or method for operating on the electronic device 800, contact data, phone book data, messages, pictures, videos, etc.
- the memory 804 may be implemented by any type of volatile or nonvolatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read only memory (EEPROM), erasable and removable Programmable read only memory (EPROM), programmable read only memory (PROM), read only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.
- SRAM static random access memory
- EEPROM electrically erasable programmable read only memory
- EPROM erasable and removable Programmable read only memory
- PROM programmable read only memory
- ROM read only memory
- magnetic memory flash memory
- flash memory magnetic disk or optical disk.
- the power supply component 806 provides power to various components of the electronic device 800.
- the power component 806 may include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for the electronic device 800.
- the multimedia component 808 includes a screen that provides an output interface between the electronic device 800 and the user.
- the screen may include a liquid crystal display (LCD) and a touch panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from the user.
- the touch panel includes one or more touch sensors to sense touch, swipe, and gestures on the touch panel. The touch sensor may not only sense the boundary of the touch or sliding action, but also detect the duration and pressure related to the touch or sliding operation.
- the multimedia component 808 includes a front camera and/or a rear camera. When the electronic device 800 is in an operation mode, such as a shooting mode or a video mode, the front camera and/or the rear camera may receive external multimedia data. Each front camera and rear camera can be a fixed optical lens system or have focal length and optical zoom capabilities.
- the audio component 810 is configured to output and/or input audio signals.
- the audio component 810 includes a microphone (MIC).
- the microphone is configured to receive an external audio signal.
- the received audio signal may be further stored in the memory 804 or transmitted via the communication component 816.
- the audio component 810 further includes a speaker for outputting audio signals.
- the I/O interface 812 provides an interface between the processing component 802 and a peripheral interface module.
- the peripheral interface module may be a keyboard, a click wheel, or a button. These buttons may include, but are not limited to: home button, volume button, start button, and lock button.
- the sensor component 814 includes one or more sensors for providing the electronic device 800 with status assessment in various aspects.
- the sensor component 814 can detect the on/off state of the electronic device 800, and the relative positioning of the components, for example, the component is the display and keypad of the electronic device 800, and the sensor component 814 can also detect the electronic device 800 or the electronic device 800.
- the position of the component changes, the presence or absence of user contact with the electronic device 800, the orientation or acceleration/deceleration of the electronic device 800, and the temperature change of the electronic device 800.
- the sensor assembly 814 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact.
- the sensor component 814 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications.
- the sensor component 814 may further include an acceleration sensor, a gyro sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.
- the communication component 816 is configured to facilitate wired or wireless communication between the electronic device 800 and other devices.
- the electronic device 800 can access a wireless network based on a communication standard, such as WiFi, 2G, or 3G, or a combination thereof.
- the communication component 816 receives a broadcast signal or broadcast related information from an external broadcast management system via a broadcast channel.
- the communication component 816 also includes a near field communication (NFC) module to facilitate short-range communication.
- the NFC module can be implemented based on radio frequency identification (RFID) technology, infrared data association (IrDA) technology, ultra-wideband (UWB) technology, Bluetooth (BT) technology, and other technologies.
- RFID radio frequency identification
- IrDA infrared data association
- UWB ultra-wideband
- Bluetooth Bluetooth
- the electronic device 800 may be used by one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field Programming gate array (FPGA), controller, microcontroller, microprocessor or other electronic components are used to implement the above method.
- ASICs application specific integrated circuits
- DSPs digital signal processors
- DSPDs digital signal processing devices
- PLDs programmable logic devices
- FPGA field Programming gate array
- controller microcontroller, microprocessor or other electronic components are used to implement the above method.
- a non-volatile computer-readable storage medium is also provided, for example, a memory 804 including computer program instructions, which can be executed by the processor 820 of the electronic device 800 to complete the above method.
- Fig. 5 is a block diagram of an electronic device 1900 according to an exemplary embodiment.
- the electronic device 1900 may be provided as a server.
- the electronic device 1900 includes a processing component 1922, which further includes one or more processors, and memory resources represented by the memory 1932, for storing instructions executable by the processing component 1922, such as application programs.
- the application programs stored in the memory 1932 may include one or more modules each corresponding to a set of instructions.
- the processing component 1922 is configured to execute instructions to perform the above method.
- the electronic device 1900 may also include a power component 1926 configured to perform power management of the electronic device 1900, a wired or wireless network interface 1950 configured to connect the electronic device 1900 to the network, and an input output (I/O) interface 1958 .
- the electronic device 1900 can operate an operating system based on the memory 1932, such as Windows ServerTM, Mac OS XTM, UnixTM, LinuxTM, FreeBSDTM or the like.
- a non-volatile computer-readable storage medium is also provided, for example, a memory 1932 including computer program instructions, which can be executed by the processing component 1922 of the electronic device 1900 to complete the above method.
- the present disclosure may be a system, method, and/or computer program product.
- the computer program product may include a computer-readable storage medium loaded with computer-readable program instructions for causing the processor to implement various aspects of the present disclosure.
- the computer-readable storage medium may be a tangible device that can hold and store instructions used by the instruction execution device.
- the computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing.
- Computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read only memory (ROM), and erasable programmable read only memory (EPROM (Or flash memory), static random access memory (SRAM), portable compact disk read-only memory (CD-ROM), digital versatile disk (DVD), memory stick, floppy disk, mechanical encoding device, such as a computer on which instructions are stored
- RAM random access memory
- ROM read only memory
- EPROM erasable programmable read only memory
- SRAM static random access memory
- CD-ROM compact disk read-only memory
- DVD digital versatile disk
- memory stick floppy disk
- mechanical encoding device such as a computer on which instructions are stored
- the convex structure in the hole card or the groove and any suitable combination of the above.
- the computer-readable storage medium used here is not to be interpreted as a transient signal itself, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (for example, optical pulses through fiber optic cables), or through wires The transmitted electrical signal.
- the computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to various computing/processing devices, or downloaded to an external computer or external storage device through a network, such as the Internet, a local area network, a wide area network, and/or a wireless network.
- the network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers, and/or edge servers.
- the network adapter card or network interface in each computing/processing device receives computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing/processing device .
- the computer program instructions for performing the operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or in one or more programming languages Source code or object code written in any combination.
- the programming languages include object-oriented programming languages such as Smalltalk, C++, etc., and conventional procedural programming languages such as "C" language or similar programming languages.
- Computer readable program instructions can be executed entirely on the user's computer, partly on the user's computer, as an independent software package, partly on the user's computer and partly on a remote computer, or completely on the remote computer or server carried out.
- the remote computer may be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (eg, using an Internet service provider to pass the Internet connection).
- electronic circuits such as programmable logic circuits, field programmable gate arrays (FPGAs), or programmable logic arrays (PLA), are personalized by utilizing the state information of computer-readable program instructions.
- Computer-readable program instructions are executed to implement various aspects of the present disclosure.
- These computer-readable program instructions can be provided to the processor of a general-purpose computer, special-purpose computer, or other programmable data processing device, thereby producing a machine that causes these instructions to be executed by the processor of a computer or other programmable data processing device A device that implements the functions/actions specified in one or more blocks in the flowchart and/or block diagram is generated.
- the computer-readable program instructions may also be stored in a computer-readable storage medium. These instructions cause the computer, programmable data processing apparatus, and/or other devices to work in a specific manner. Therefore, the computer-readable medium storing the instructions includes An article of manufacture that includes instructions to implement various aspects of the functions/acts specified in one or more blocks in the flowchart and/or block diagram.
- the computer-readable program instructions can also be loaded onto a computer, other programmable data processing apparatus, or other equipment, so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other equipment to produce a computer-implemented process , So that the instructions executed on the computer, other programmable data processing device, or other equipment implement the functions/acts specified in one or more blocks in the flowchart and/or block diagram.
- each block in the flowchart or block diagram may represent a part of a module, program segment, or instruction that contains one or more Executable instructions.
- the functions marked in the blocks may also occur in an order different from that marked in the drawings. For example, two consecutive blocks can actually be executed substantially in parallel, and sometimes they can also be executed in reverse order, depending on the functions involved.
- each block in the block diagrams and/or flowcharts, and combinations of blocks in the block diagrams and/or flowcharts can be implemented with a dedicated hardware-based system that performs specified functions or actions Or, it can be realized by a combination of dedicated hardware and computer instructions.
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Quality & Reliability (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Databases & Information Systems (AREA)
- Image Analysis (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
- Collating Specific Patterns (AREA)
Abstract
Description
Claims (21)
- 一种行人识别方法,其特征在于,包括:获取目标行人图像的图像特征,所述图像特征包括人脸特征和人体特征;从特征数据库中获取所述图像特征的至少一个目标节点,并将所述至少一个目标节点分别对应的行人图像作为所述目标行人的图像;其中,所述特征数据库中包括多个行人特征节点,所述行人特征节点中包括行人图像对应的人脸特征、人体特征以及与其他行人特征节点之间的关系特征。
- 根据权利要求1所述的行人识别方法,其特征在于,所述关系特征被设置为根据下述参数确定:人脸图像质量值、人体图像质量值、人脸特征、人体特征。
- 根据权利要求2所述的行人识别方法,其特征在于,所述关系特征包括相似节点关联关系,所述相似节点关联关系被设置为按照下述方式确定:在两个行人特征节点中较小的人脸图像质量值大于等于预设人脸图像质量阈值的情况下,确定所述两个行人特征节点的人脸特征之间的相似度;在所述人脸特征之间的相似度大于等于预设人脸相似度阈值的情况下,确定所述两个行人特征节点为相似节点关联关系;在所述两个行人特征节点中较小的人脸图像质量值小于预设人脸图像质量阈值,且所述两个行人特征节点中较小的人体图像质量值大于等于人体图像质量阈值的情况下,确定所述两个行人特征节点的人体特征之间的相似度;在所述人体特征之间的相似度大于等于预设人体相似度阈值的情况下,确定所述两个行人特征节点为相似节点关联关系。
- 根据权利要求3所述的行人识别方法,其特征在于,所述从特征数据库中获取所述图像特征的至少一个目标节点,并将所述至少一个目标节点分别对应的行人图像作为所述目标行人的图像,包括:将所述图像特征作为目标特征节点,确定所述目标特征节点到达所述行人特征节点的至少一条搜索路径,所述搜索路径由具有所述相似节点关联关系的多个行人特征节点连接而成;确定所述搜索路径中相邻两个行人特征节点之间的相似度中的最小值,并将所述最小值作为所述搜索路径的路径分值;确定所述至少一条搜索路径的路径分值中的最大值,并将所述最大值作为所述目标特征节点与所述行人特征节点的相似度;将与所述目标特征节点的相似度大于等于所述预设人脸相似度阈值或者所述预设人体相似度阈值的至少一个行人特征节点作为所述目标特征节点的至少一个目标节点,并将所述至少一个目标节点分别对应的行人图像作为所述目标行人的图像。
- 根据权利要求1-3中任一项所述的行人识别方法,其特征在于,所述从特征数据库中获取所述图像特征的至少一个目标节点,并将所述至少一个目标节点分别对应的行人图像作为所述目标行人的图像,包括:基于所述多个行人特征节点的关系特征,从所述特征数据库中搜索出所述图像特征的至少一个相似节点;从所述至少一个相似节点中选择出至少一个目标节点;将所述至少一个目标节点分别对应的行人图像作为所述目标行人的图像。
- 根据权利要求5所述的行人识别方法,其特征在于,所述从所述至少一个相似节点中选择出至少一个目标节点,包括:确定所述至少一个相似节点中人脸特征的人脸聚类中心值;从所述至少一个相似节点中筛选出至少一个人脸人体特征节点,所述人脸人体特征节点中的人脸特征和人体特征为非零值;分别确定所述至少一个人脸人体特征节点中人脸特征与所述人脸聚类中心值之间的人脸相似度,将所述人脸相似度大于等于预设相似度阈值的节点划分至第一相似节点集合,将所述人脸相似度小于所述预设相似度阈值的节点划分至第二相似节点集合;从所述至少一个相似节点中清除所述第二相似节点集合,并将清除后的所述至少一个相似节点分别对应的行人图像作为所述目标行人的图像。
- 根据权利要求6所述的行人识别方法,其特征在于,在所述从所述至少一个相似节点中清除所述第二相似节点集合之前,所述方法还包括:确定所述第一相似节点集合中人体特征的第一人体聚类中心值、所述第二相似节点集合中人体特征的第二人体聚类中心值;从所述至少一个相似节点中筛选出至少一个人体特征节点,所述人体特征节点中的人脸特征为零值、人体特征为非零值;分别确定所述至少一个人体特征节点中人体特征与所述第一人体聚类中心值之间的第一人体相似度、与所述第二人体聚类中心值之间的第二人体相似度;将所述第二人体相似度大于所述第一人体相似度时所对应的人体特征节点添加至所述第二相似节点集合中。
- 根据权利要求1-7中任一项所述的行人识别方法,其特征在于,所述方法还包括:基于所述目标行人的图像,获取所述目标行人的行动轨迹,所述行动轨迹包括时间信息和/或位置信息。
- 根据权利要求1-8中任一项所述的行人识别方法,其特征在于,所述方法还包括:在获取到新行人图像的情况下,提取所述新行人图像的图像特征;将所述新行人图像的图像特征作为新的行人特征节点,更新至所述特征数据库中。
- 一种行人识别装置,其特征在于,包括:图像特征获取模块,用于获取目标行人图像的图像特征,所述图像特征包括人脸特征和人体特征;目标节点获取模块,用于从特征数据库中获取所述图像特征的至少一个目标节点,并将所述至少一个目标节点分别对应的行人图像作为所述目标行人的图像;其中,所述特征数据库中包括多个行人特征节点,所述行人特征节点中包括行人图像对应的人脸特征、人体特征以及与其他行人特征节点之间的关系特征。
- 根据权利要求10所述的行人识别装置,其特征在于,所述关系特征被设置为根据下述参数确定:人脸图像质量值、人体图像质量值、人脸特征、人体特征。
- 根据权利要求11所述的行人识别装置,其特征在于,所述关系特征包括相似节点关联关系,所述相似节点关联关系被设置为按照下述方式确定:在两个行人特征节点中较小的人脸图像质量值大于等于预设人脸图像质量阈值的情况下,确定所述两个行人特征节点的人脸特征之间的相似度;在所述人脸特征之间的相似度大于等于预设人脸相似度阈值的情况下,确定所述两个 行人特征节点为相似节点关联关系;在所述两个行人特征节点中较小的人脸图像质量值小于预设人脸图像质量阈值,且所述两个行人特征节点中较小的人体图像质量值大于等于人体图像质量阈值的情况下,确定所述两个行人特征节点的人体特征之间的相似度;在所述人体特征之间的相似度大于等于预设人体相似度阈值的情况下,确定所述两个行人特征节点为相似节点关联关系。
- 根据权利要求12所述的行人识别装置,其特征在于,所述目标节点获取模块包括:路径确定子模块,用于将所述图像特征作为目标特征节点,确定所述目标特征节点到达所述行人特征节点的至少一条搜索路径,所述搜索路径由具有所述相似节点关联关系的多个行人特征节点连接而成;路径分值确定子模块,用于确定所述搜索路径中相邻两个行人特征节点之间的相似度中的最小值,并将所述最小值作为所述搜索路径的路径分值;节点相似度确定子模块,用于确定所述至少一条搜索路径的路径分值中的最大值,并将所述最大值作为所述目标特征节点与所述行人特征节点的相似度;目标节点确定子模块,用于将与所述目标特征节点的相似度大于等于所述预设人脸相似度阈值或者所述预设人体相似度阈值的至少一个行人特征节点作为所述目标特征节点的至少一个目标节点,并将所述至少一个目标节点分别对应的行人图像作为所述目标行人的图像。
- 根据权利要求10-12中任一项所述的行人识别装置,其特征在于,所述目标节点获取模块包括:相似节点搜索子模块,用于基于所述多个行人特征节点的关系特征,从所述特征数据库中搜索出所述图像特征的至少一个相似节点;目标节点选取子模块,用于从所述至少一个相似节点中选择出至少一个目标节点;行人图像获取子模块,用于将所述至少一个目标节点分别对应的行人图像作为所述目标行人的图像。
- 根据权利要求14所述的行人识别装置,其特征在于,所述目标节点选取子模块包括:人脸中心值确定单元,用于确定所述至少一个相似节点中人脸特征的人脸聚类中心值;节点筛选单元,用于从所述至少一个相似节点中筛选出至少一个人脸人体特征节点,所述人脸人体特征节点中的人脸特征和人体特征为非零值;节点划分单元,用于分别确定所述至少一个人脸人体特征节点中人脸特征与所述人脸聚类中心值之间的人脸相似度,将所述人脸相似度大于等于预设相似度阈值的节点划分至第一相似节点集合,将所述人脸相似度小于所述预设相似度阈值的节点划分至第二相似节点集合;节点清除单元,用于从所述至少一个相似节点中清除所述第二相似节点集合,并将清除后的所述至少一个相似节点分别对应的行人图像作为所述目标行人的图像。
- 根据权利要求15所述的行人识别装置,其特征在于,所述目标节点选取子模块还包括:人体中心值确定单元,用于确定所述第一相似节点集合中人体特征的第一人体聚类中 心值、所述第二相似节点集合中人体特征的第二人体聚类中心值;人体节点筛选单元,用于从所述至少一个相似节点中筛选出至少一个人体特征节点,所述人体特征节点中的人脸特征为零值、人体特征为非零值;相似度确定单元,用于分别确定所述至少一个人体特征节点中人体特征与所述第一人体聚类中心值之间的第一人体相似度、与所述第二人体聚类中心值之间的第二人体相似度;节点添加单元,用于将所述第二人体相似度大于所述第一人体相似度时所对应的人体特征节点添加至所述第二相似节点集合中。
- 根据权利要求10-16中任一项所述的行人识别装置,其特征在于,所述装置还包括:行人轨迹获取模块,用于基于所述目标行人的图像,获取所述目标行人的行动轨迹,所述行动轨迹包括时间信息和/或位置信息。
- 根据权利要求10-17中任一项所述的行人识别装置,其特征在于,所述装置还包括:新数据获取模块,用于在获取到新行人图像的情况下,提取所述新行人图像的图像特征;数据更新模块,用于将所述新行人图像的图像特征作为新的行人特征节点,更新至所述特征数据库中。
- 一种电子设备,其特征在于,包括:处理器;用于存储处理器可执行指令的存储器;其中,所述处理器被配置为执行权利要求1-9任意一项所述的行人识别方法。
- 一种非临时性计算机可读存储介质,当所述存储介质中的指令由处理器执行时,使得处理器能够执行权利要求1-9任意一项所述的行人识别方法。
- 一种计算机程序,其特征在于,所述计算机程序包括计算机可读代码,当所述计算机可读代码在电子设备中运行时,所述电子设备中的处理器执行用于实现权利要求1至9中的任意一项所述的方法。
Priority Applications (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR1020217008615A KR20210047917A (ko) | 2018-12-29 | 2019-12-16 | 보행자 인식 방법 및 장치 |
JP2021500852A JP7171884B2 (ja) | 2018-12-29 | 2019-12-16 | 歩行者認識方法及び装置 |
SG11202011791SA SG11202011791SA (en) | 2018-12-29 | 2019-12-16 | Pedestrian recognition method and device |
US17/113,949 US20210089799A1 (en) | 2018-12-29 | 2020-12-07 | Pedestrian Recognition Method and Apparatus and Storage Medium |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811637119.4 | 2018-12-29 | ||
CN201811637119.4A CN109753920B (zh) | 2018-12-29 | 2018-12-29 | 一种行人识别方法及装置 |
Related Child Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US17/113,949 Continuation US20210089799A1 (en) | 2018-12-29 | 2020-12-07 | Pedestrian Recognition Method and Apparatus and Storage Medium |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2020135127A1 true WO2020135127A1 (zh) | 2020-07-02 |
Family
ID=66404303
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/CN2019/125667 WO2020135127A1 (zh) | 2018-12-29 | 2019-12-16 | 一种行人识别方法及装置 |
Country Status (7)
Country | Link |
---|---|
US (1) | US20210089799A1 (zh) |
JP (1) | JP7171884B2 (zh) |
KR (1) | KR20210047917A (zh) |
CN (1) | CN109753920B (zh) |
SG (1) | SG11202011791SA (zh) |
TW (1) | TW202029055A (zh) |
WO (1) | WO2020135127A1 (zh) |
Families Citing this family (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109753920B (zh) * | 2018-12-29 | 2021-09-17 | 深圳市商汤科技有限公司 | 一种行人识别方法及装置 |
CN112149447A (zh) * | 2019-06-26 | 2020-12-29 | 杭州海康威视数字技术股份有限公司 | 一种人员识别方法、装置及电子设备 |
CN111783507A (zh) * | 2019-07-24 | 2020-10-16 | 北京京东尚科信息技术有限公司 | 目标搜索方法、装置及计算机可读存储介质 |
CN110390300A (zh) * | 2019-07-24 | 2019-10-29 | 北京洛必德科技有限公司 | 一种用于机器人的目标跟随方法和装置 |
CN110502651B (zh) * | 2019-08-15 | 2022-08-02 | 深圳市商汤科技有限公司 | 图像处理方法及装置、电子设备和存储介质 |
CN110503022A (zh) * | 2019-08-19 | 2019-11-26 | 北京积加科技有限公司 | 一种身份识别方法、装置及*** |
CN111753611A (zh) * | 2019-08-30 | 2020-10-09 | 北京市商汤科技开发有限公司 | 图像检测方法及装置和***、电子设备和存储介质 |
CN110826463B (zh) * | 2019-10-31 | 2021-08-24 | 深圳市商汤科技有限公司 | 人脸识别方法及装置、电子设备和存储介质 |
CN112784636A (zh) * | 2019-11-07 | 2021-05-11 | 佳能株式会社 | 人脸图像分类方法、人脸图像分类装置和存储介质 |
CN110942003A (zh) * | 2019-11-20 | 2020-03-31 | 中国建设银行股份有限公司 | 人员轨迹搜索方法及*** |
CN111680638B (zh) * | 2020-06-11 | 2020-12-29 | 深圳北斗应用技术研究院有限公司 | 一种乘客路径识别方法和基于该方法的客流清分方法 |
CN112541384B (zh) * | 2020-07-30 | 2023-04-28 | 深圳市商汤科技有限公司 | 可疑对象查找方法及装置、电子设备及存储介质 |
CN111967356A (zh) * | 2020-08-04 | 2020-11-20 | 杰创智能科技股份有限公司 | 图像中行人检测方法、装置、电子设备和存储介质 |
CN112132103A (zh) * | 2020-09-30 | 2020-12-25 | 新华智云科技有限公司 | 一种视频人脸检测识别方法和*** |
CN112270257A (zh) * | 2020-10-27 | 2021-01-26 | 深圳英飞拓科技股份有限公司 | 一种运动轨迹确定方法、装置及计算机可读存储介质 |
CN112307938B (zh) * | 2020-10-28 | 2022-11-11 | 深圳市商汤科技有限公司 | 数据聚类方法及其装置、电子设备、存储介质 |
TWI816072B (zh) * | 2020-12-10 | 2023-09-21 | 晶睿通訊股份有限公司 | 物件識別方法及其監控系統 |
CN112699810B (zh) * | 2020-12-31 | 2024-04-09 | 中国电子科技集团公司信息科学研究院 | 一种提升室内监控***人物识别精度的方法及装置 |
CN113657434A (zh) * | 2021-07-02 | 2021-11-16 | 浙江大华技术股份有限公司 | 人脸人体关联方法、***以及计算机可读存储介质 |
CN114973327B (zh) * | 2022-06-06 | 2024-07-12 | 清华大学 | 提取行人身体特征的遮挡行人重识别方法、***及设备 |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140185875A1 (en) * | 2012-12-27 | 2014-07-03 | Canon Kabushiki Kaisha | Object area tracking apparatus, control method, and program of the same |
CN107292240A (zh) * | 2017-05-24 | 2017-10-24 | 深圳市深网视界科技有限公司 | 一种基于人脸与人体识别的找人方法及*** |
CN108724178A (zh) * | 2018-04-13 | 2018-11-02 | 顺丰科技有限公司 | 特定人自主跟随方法及装置、机器人、设备和存储介质 |
CN108921008A (zh) * | 2018-05-14 | 2018-11-30 | 深圳市商汤科技有限公司 | 人像识别方法、装置及电子设备 |
CN109753920A (zh) * | 2018-12-29 | 2019-05-14 | 深圳市商汤科技有限公司 | 一种行人识别方法及装置 |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR101618735B1 (ko) | 2008-04-02 | 2016-05-09 | 구글 인코포레이티드 | 디지털 영상 컬렉션에 자동 얼굴 인식 기능을 통합하는 방법 및 장치 |
JP4775515B1 (ja) | 2011-03-14 | 2011-09-21 | オムロン株式会社 | 画像照合装置、画像処理システム、画像照合プログラム、コンピュータ読み取り可能な記録媒体、および画像照合方法 |
CN105718882B (zh) * | 2016-01-19 | 2018-12-18 | 上海交通大学 | 一种分辨率自适应特征提取与融合的行人重识别方法 |
CN109102531A (zh) * | 2018-08-21 | 2018-12-28 | 北京深瞐科技有限公司 | 一种目标轨迹追踪方法及装置 |
-
2018
- 2018-12-29 CN CN201811637119.4A patent/CN109753920B/zh active Active
-
2019
- 2019-12-16 WO PCT/CN2019/125667 patent/WO2020135127A1/zh active Application Filing
- 2019-12-16 SG SG11202011791SA patent/SG11202011791SA/en unknown
- 2019-12-16 KR KR1020217008615A patent/KR20210047917A/ko not_active Application Discontinuation
- 2019-12-16 JP JP2021500852A patent/JP7171884B2/ja active Active
- 2019-12-27 TW TW108148004A patent/TW202029055A/zh unknown
-
2020
- 2020-12-07 US US17/113,949 patent/US20210089799A1/en not_active Abandoned
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20140185875A1 (en) * | 2012-12-27 | 2014-07-03 | Canon Kabushiki Kaisha | Object area tracking apparatus, control method, and program of the same |
CN107292240A (zh) * | 2017-05-24 | 2017-10-24 | 深圳市深网视界科技有限公司 | 一种基于人脸与人体识别的找人方法及*** |
CN108724178A (zh) * | 2018-04-13 | 2018-11-02 | 顺丰科技有限公司 | 特定人自主跟随方法及装置、机器人、设备和存储介质 |
CN108921008A (zh) * | 2018-05-14 | 2018-11-30 | 深圳市商汤科技有限公司 | 人像识别方法、装置及电子设备 |
CN109753920A (zh) * | 2018-12-29 | 2019-05-14 | 深圳市商汤科技有限公司 | 一种行人识别方法及装置 |
Also Published As
Publication number | Publication date |
---|---|
US20210089799A1 (en) | 2021-03-25 |
KR20210047917A (ko) | 2021-04-30 |
TW202029055A (zh) | 2020-08-01 |
JP7171884B2 (ja) | 2022-11-15 |
CN109753920A (zh) | 2019-05-14 |
SG11202011791SA (en) | 2020-12-30 |
JP2021530791A (ja) | 2021-11-11 |
CN109753920B (zh) | 2021-09-17 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
WO2020135127A1 (zh) | 一种行人识别方法及装置 | |
WO2021196401A1 (zh) | 图像重建方法及装置、电子设备和存储介质 | |
TWI769635B (zh) | 網路訓練、行人重識別方法、電子設備及電腦可讀存儲介質 | |
WO2021093375A1 (zh) | 检测同行人的方法及装置、***、电子设备和存储介质 | |
CN109948494B (zh) | 图像处理方法及装置、电子设备和存储介质 | |
WO2021031609A1 (zh) | 活体检测方法及装置、电子设备和存储介质 | |
WO2021036382A1 (zh) | 图像处理方法及装置、电子设备和存储介质 | |
JP2022526381A (ja) | 画像処理方法及び装置、電子機器並びに記憶媒体 | |
CN111523346B (zh) | 图像识别方法及装置、电子设备和存储介质 | |
CN111553864A (zh) | 图像修复方法及装置、电子设备和存储介质 | |
CN109344703B (zh) | 对象检测方法及装置、电子设备和存储介质 | |
CN108171222B (zh) | 一种基于多流神经网络的实时视频分类方法及装置 | |
CN112906484A (zh) | 一种视频帧处理方法及装置、电子设备和存储介质 | |
CN110781842A (zh) | 图像处理方法及装置、电子设备和存储介质 | |
CN111062407B (zh) | 图像处理方法及装置、电子设备和存储介质 | |
CN110929545A (zh) | 人脸图像的整理方法及装置 | |
CN112330717A (zh) | 目标跟踪方法及装置、电子设备和存储介质 | |
CN113506324B (zh) | 图像处理方法及装置、电子设备和存储介质 | |
CN113506325B (zh) | 图像处理方法及装置、电子设备和存储介质 | |
WO2022198821A1 (zh) | 人脸和人体匹配的方法、装置、电子设备、存储介质及程序 | |
CN109325141B (zh) | 图像检索方法及装置、电子设备和存储介质 | |
CN113326938A (zh) | 网络训练、行人重识别方法及装置、电子设备和存储介质 | |
CN112330721A (zh) | 三维坐标的恢复方法及装置、电子设备和存储介质 | |
CN110929546B (zh) | 人脸比对方法及装置 | |
CN114020951A (zh) | 一种人脸质量增强模型的训练方法、图片搜索方法及装置 |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 19904510 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2021500852 Country of ref document: JP Kind code of ref document: A |
|
ENP | Entry into the national phase |
Ref document number: 20217008615 Country of ref document: KR Kind code of ref document: A |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
32PN | Ep: public notification in the ep bulletin as address of the adressee cannot be established |
Free format text: NOTING OF LOSS OF RIGHTS (EPO FORM 1205A DATED 04.10.2021) |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 19904510 Country of ref document: EP Kind code of ref document: A1 |