A TOF camera-based tourist category online auditing method
A technology for cameras and tourists, applied in the field of image processing and pattern recognition, can solve the problems of face recognition that cannot effectively extract face features, be easily affected by noise, and unstable height, etc., and achieve low cost, less equipment, and reduced impact Effect
Active Publication Date: 2019-04-05
DALIAN MARITIME UNIVERSITY
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] 1. When measuring the height through the ranging sensor, it is easily affected by the non-full-body image of the user observed by the camera for ranging, resulting in unstable measured height
[0005] 2. When measuring the height through the depth camera, the height information is extracted from a picture, which is accidental and susceptible to noise
[0007] 1. The face images used in face recognition are color images or grayscale images, which are greatly affected by light
In the case of insufficient light or overexposure, it is impossible to effectively extract face features and complete face 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
[0042] Such as figure 1 As shown, the present invention provides a kind of tourist category online review method based on TOF camera, comprising:
[0043] Step S1: Use the TOF camera to obtain the in-depth video of the ticket purchased by tourists and the in-depth video of the ticket used by tourists;
[0044] Step S2: Separating the foreground and background of the acquired in-depth videos of the tickets purchased by tourists and the tickets used by tourists, so as to obtain the final moving object video;
[0045] Step S21: average the first n frames of the depth video as the fixed background Ground, and then subtract each frame of the depth video from the fixed background Ground to obtain the moving object video A. Among them, the parameter n is determined according to the actual situation;
[0046] Step S22: Process the depth video using a Gaussian mixture model to obtain a moving object video B;
[0047] Step S23: Perform weighted fusion of the moving object video A and...
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 provides a TOF (Time of Flight) camera-based tourist category online auditing method, which comprises the following steps of: acquiring a depth video of ticket purchase and ticket use ofa tourist by utilizing a TOF camera to obtain a final moving object video; Determining the center of the moving object; Tracking the track of a moving object in the moving video; Performing feature extraction on the track of the moving object, and screening out and storing the head track of the tourist according to the extracted features; Screening out segments with higher reliability of each track from the stored tracks according to the extracted head possibility characteristics of the tourists, carrying out feature integration, and calculating average head image characteristics of the tourists. The invention mainly relates to two technologies, one technology is to measure the height of a tourist, and the tourist category is audited through the measured height of the tourist; Another technology is head recognition, and whether the tourist category is manually audited in the tourist ticket auditing stage is judged according to the head recognition result.
Description
technical field [0001] The present invention relates to the technical fields of image processing and pattern recognition, in particular, to an online review method for tourist categories based on a TOF camera. Background technique [0002] At present, the methods of height measurement are roughly divided into two categories, one is to measure the height through the range sensor, and the other is to measure the height through the depth camera. The method of measuring height through the ranging sensor is to use the ranging sensor to obtain the distance from the person to the camera when the camera observes the whole body image of the person, and then calculate the height based on other parameters. The method of measuring the height through the depth camera is to use the characteristics of the depth camera to measure the height. First, the depth camera is placed on the top of the roof for top-down shooting to obtain the depth image of the person. Then judge the human body tar...
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 Applications(China)
IPC IPC(8): G06K9/00G06K9/62G06T7/277G06T7/254G06F16/903G07B11/00G06Q50/14
CPCG06Q50/14G06T7/254G06T7/277G07B11/00G06T2207/10016G06T2207/20076G06T2207/30196G06T2207/20224G06V40/172G06F18/22
Inventor 王新年刘春华齐国清
Owner DALIAN MARITIME UNIVERSITY