Depth image human body detection method and system based on sparse coding features
A sparse coding and depth image technology, applied in the field of image processing, can solve the problems of human body false detection and missed detection in depth image recognition, and achieve the effect of fast calculation speed and improved performance.
Active Publication Date: 2020-07-14
SICHUAN CHANGHONG ELECTRIC CO LTD
View PDF10 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] The present invention aims to solve the existing problems of false detection and missed detection in human body recognition based on depth image, and proposes a method and system for human body detection in depth image based on sparse coding features
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
[0042] In the embodiment of the present invention, the depth image human body detection method based on sparse coding features, such as figure 1 shown, including the following steps:
[0043] Step S1. Obtain multiple depth images, mark the human body in the depth images, and obtain a training set consisting of target images containing human body images and background images not containing human body images;
[0044] Specifically, the marking the human body in the depth image may specifically include: linearly converting the depth value of the depth image into a grayscale image, and marking the human body image with a rectangular frame.
[0045] Step S2. Sampling small image blocks from the human body image and generating a dictionary, and calculating the sparse coding features of each depth image according to the dictionary;
[0046] Wherein, the sampling of small image blocks from human body images specifically includes: scaling all marked human body images to a first preset...
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 relates to the technical field of image processing. The invention aims to solve the problems of false detection and missing detection of human body identification based on a depth imagein the prior art. The invention provides a depth image human body detection method and system based on sparse coding features, and the method comprises the following steps: obtaining a plurality of depth images, marking a human body in the depth images, and obtaining a training set composed of a target image containing a human body image and a background image not containing the human body image;sampling image small blocks from the human body image and generating a dictionary, and calculating sparse coding characteristics of each depth image according to the dictionary; training according tothe sparse coding features and a training set to obtain a classification model; and calculating sparse coding features of a depth image to be detected, and inputting the sparse coding features into the classification model to obtain whether the depth image to be detected contains a human body and the position of the human body. High-accuracy detection can be carried out by only needing a small number of labeled samples, and the method and system have robustness of partially shielding a human body and is high in operation speed.
Description
technical field [0001] The invention relates to the technical field of image processing, in particular to a method and system for detecting a human body in a depth image. Background technique [0002] An important task in the field of computer vision is to detect human bodies, which can be used in the fields of people flow statistics, abnormal crowd monitoring, human body tracking, etc. There are also corresponding international competitions, such as the famous kitti 2D ObjectDetection (Pedestrian) competition; Human body detection is a rising trend in recent years, because depth images can overcome the shortcomings of traditional optical images that are susceptible to light and background interference, and easy to leak private information, and can be deployed in hospital wards and family residential environments. The current methods of human body detection based on depth images are mainly deep learning and some traditional methods directly based on features. However, when t...
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): G06K9/00G06K9/46G06K9/62
CPCG06V40/10G06V20/53G06V10/40G06V10/513G06F18/214
Inventor 胡亮
Owner SICHUAN CHANGHONG ELECTRIC CO LTD