Unlock instant, AI-driven research and patent intelligence for your innovation.

Taxi monitoring abnormal image signal detection method based on static area feature matching

An abnormal image and signal detection technology, applied in the field of image processing, can solve problems such as image transmission failure, image abnormality, image deflection, etc.

Inactive Publication Date: 2019-05-14
CHANGAN UNIV
View PDF1 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, during the operation of the taxi, the on-board camera will be interfered, resulting in the inability to collect image data or the abnormality of the collected images. These abnormalities include image transmission failures, incomplete image frames, and severe image deflection. Carry out screening, detect abnormal images in time, and remind the driver or taxi management personnel to repair the on-board camera in time to ensure that normal image data can be obtained

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Taxi monitoring abnormal image signal detection method based on static area feature matching
  • Taxi monitoring abnormal image signal detection method based on static area feature matching
  • Taxi monitoring abnormal image signal detection method based on static area feature matching

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0128] The present invention will be further described in detail below in conjunction with the accompanying drawings. The concrete implementation steps of the method that present embodiment provides are as follows:

[0129] Step S0: selection of reference image.

[0130] The normal image signal refers to an image that is normally transmitted, undeflected, and includes the complete front row (copilot and driver) area, roof area and front windshield area. Select a normal image in the taxi video surveillance image database as a reference image, and the reference image is marked as JM (such as figure 1 shown), its image size is M×N, where M and N are the total rows and columns of the image frame, respectively. In this embodiment, JM is an RGB color image frame, M=288, N=352.

[0131] Go to step S1.

[0132] Step S1: Preprocessing the reference image to obtain a filtered reference image.

[0133] Perform preprocessing on the reference image JM selected in step S0, including tw...

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

No PUM Login to View More

Abstract

The invention discloses a method for detecting an abnormal image signal of a taxi monitoring based on feature matching in a static area: Step 1: selecting a reference image; Step 2: preprocessing the reference image to obtain a filtered reference image; select. Step 4: Calculate the area and average gray level of the static area of ​​the reference image. Step 5: Collect the image frames to be checked in real time. Step 6: Preprocessing of frames to be checked. Step 7: Calculate the average gray level of the static area of ​​the frame to be checked. Step 8: Multi-source feature extraction for non-frame static regions. Step 9: Judgment of abnormal image signal based on the abnormal degree of non-frame static area. Step 10: Abnormal image signal determination considering the correlation coefficient of the frame region. Using the present invention to detect taxi monitoring images, the average processing time for each image is 0.273s, and meanwhile, the accuracy rate of detecting taxi monitoring images reaches 95.47%.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to an extended application of a taxi video monitoring system, in particular to an automatic detection method for abnormal image signals of the taxi video monitoring system. Background technique [0002] With the rapid development of machine vision technology, many cities in China have installed cameras in the taxi co-pilot position to monitor the operation of taxis in real time. By observing the video image data collected by the camera, the whole process of taxi operation can be supervised and managed. . However, during the operation of the taxi, the on-board camera will be interfered, resulting in the inability to collect image data or the abnormality of the collected images. These abnormalities include image transmission failures, incomplete image frames, and severe image deflection. Carry out screening, detect abnormal images in time, and remind the driver o...

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
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/00
CPCG06F2218/02G06F2218/08G06F2218/12
Inventor 肖梅颜建强马登辉王杏张雷
Owner CHANGAN UNIV