A Computer Vision-Based Recognition Method for Express Violent Sorting
A technology of computer vision and recognition method, which is applied in the direction of computer parts, calculation, character and pattern recognition, etc. It can solve the problems of difficulty in action recognition and difficult to meet the needs of express violent sorting and recognition, and achieve good generalization performance, It is conducive to large-scale deployment and solves the effect of blurring the outline
Active Publication Date: 2020-09-22
NANJING UNIV OF POSTS & TELECOMM
View PDF3 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0007] Although human behavior recognition based on deep learning has made some progress, however, human behavior recognition based on 2D video still faces many challenges, including the difference of inter-class and intra-class data and scene changes. The person itself is a complex non-rigid object. Human action recognition is affected by individual differences in human appearance, posture, movement, clothing, perspective changes and camera movements, lighting changes, occlusions and complex backgrounds, while 2D videos only get 3D A projection of space, which causes great difficulties for the underlying action recognition, and it is difficult to meet the needs of courier violence sorting and recognition in actual complex scenes
[0008] In summary, the existing human behavior recognition methods based on computer vision are difficult to meet the needs of express violent sorting and recognition
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
[0042] The invention will be described in further detail below in conjunction with the accompanying drawings.
[0043] Such as figure 1 As shown, the present invention provides a computer vision-based express delivery violence sorting recognition method, the method includes the following steps:
[0044] Step 1: Depth camera-based pose estimation: Pixels in the depth image record the calibrated depth of the scene, not the value of scene intensity or color. Depth cameras operate at lower light levels than traditional intensity sensors and are affected by color and texture variations Small advantage, and solves the problem of ambiguous outlines of poses. Depth image technology has developed greatly in the past few years. With the release of Kinect, it has finally become a low-cost product. The schematic diagram of the depth camera Kinect is as follows figure 2 shown. The present invention adopts the literature "Shotton J, Sharp T, Kipman A, et al. Real-time humanpose recognit...
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 computer vision-based express delivery violence sorting and recognition method, which includes the following steps: pose estimation based on a depth camera: transforming the problem of human body pose estimation into a problem of classifying depth image pixels captured by a depth camera , by using the method of random forest to obtain the estimation of human body posture; the relative spatiotemporal feature extraction of human body three-dimensional posture: extract the relative spatial position between the geometric elements of points, lines and surfaces formed by the joints in the three-dimensional posture and the measure of its change as the characteristic representation of posture ; Violent sorting recognition based on recurrent neural network: Through the long-short-term memory model LSTM, the time-continuous temporal-spatial relative features of the posture extracted from the three-dimensional posture of the human body are modeled and trained, so as to realize the recognition of express violent sorting behavior.
Description
technical field [0001] The invention belongs to the technical field of computer vision and pattern recognition, and relates to a computer vision-based express violent sorting and recognition method. Background technique [0002] With the increasing demand for express delivery services in new service industries such as e-commerce and online shopping, my country's express delivery industry has shown a trend of rapid development. Express delivery has become a livelihood service that connects hundreds of millions of merchants and the general public. It plays an increasingly important role in promoting consumption upgrading. Compared with previous years, the service quality and sorting efficiency of my country's express delivery industry are constantly improving, but industry problems such as "violent sorting" are still emerging one after another. Open Bing or Baidu search, and there are hundreds of thousands of web pages related to violent sorting. The chaos of "violent sorting"...
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 Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00G06K9/62
CPCG06V40/23G06F18/29
Inventor 陈松乐孙知信胡冰
Owner NANJING UNIV OF POSTS & TELECOMM