A human body identification method based on serial depth images
A depth image and identity recognition technology, applied in the field of human identity recognition based on sequence depth images, can solve the problems of poor robustness and limited accuracy in application scenarios, so as to improve the recognition rate and improve the effect of human identity recognition. The effect of human identification
Active Publication Date: 2019-01-11
HUAZHONG UNIV OF SCI & TECH
View PDF7 Cites 3 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0010] In view of the above defects or improvement needs of the prior art, the present invention provides a human body identification method based on sequence depth images, thereby solving the technical problems of poor robustness and limited accuracy in the application scenarios of the prior art
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0052] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not constitute a conflict with each other.
[0053] Such as figure 1 As shown, a human body identification method based on sequence depth images, including:
[0054] (1) collecting sequence depth images of the human body, the sequence depth images comprising the gait motion of the human body;
[0055] (2) The use of convolutional neural network and recursive neural network to perform human body joint point regression based on each frame ...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a human body identification method based on serial depth images. The method comprises the following steps: acquiring a sequence depth image of a human body; returning a human body joint node to obtain a coordinate position of the human body joint node by using a convolution neural network and a recurrence neural network based on the sequence depth image; Obtaining the humanbody posture feature vector by calculating the coordinate position of the human body joint, and using the static feature classifier for identification, and obtaining the human body identity recognition score of the static feature; extracting the human motion behavior feature from the serial depth images, using the dynamic feature classifier to recognize the human body, and obtaining the human body identification score of the dynamic feature; performing weighting calculation on the human identification scores of the static feature and the dynamic feature to get the human identification score,and then obtaining the human identification results. The invention has strong robustness and the accuracy is not affected by the application scene.
Description
technical field [0001] The invention belongs to the cross technical field of digital image processing and machine learning, and more specifically relates to a human body identification method based on sequence depth images. Background technique [0002] With the rapid development of information technology, the digitization of personally identifiable information is becoming more and more common. In the fields of security, finance, criminal investigation, and elderly care, the demand for human identification technology is becoming more and more urgent. Due to the shortcomings of not easy to carry, easy to lose, easy to damage, and low security, traditional identification technology is gradually replaced by identity authentication technology based on biometrics. The research on voiceprint, fingerprint, iris recognition and other technologies has become more and more mature, and has greatly improved in terms of security, confidentiality, and portability. However, most of these...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More IPC IPC(8): G06K9/00G06K9/62G06K9/66G06N3/04
CPCG06V40/25G06V30/194G06N3/045G06F18/241G06F18/24147
Inventor 肖阳张博深曹治国毛靖朱子豪王焱乘
Owner HUAZHONG UNIV OF SCI & TECH