Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A vehicle detection method based on multiple subimages and image saliency analysis

A vehicle detection and remarkable technology, applied in the field of vehicle detection, can solve the problems of a large number of training costs, high false alarms, low contrast, etc., to achieve good detection results, high real-time performance, and the effect of suppressing false alarms

Active Publication Date: 2022-02-25
ZONGMU TECH SHANGHAI CO LTD
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The current moving vehicle detection method based on visual sensors is often difficult to detect the target vehicle when dealing with large backlight situations, because at this time, the information such as the shadow of the vehicle bottom or the taillights of the vehicle has a low contrast with the surrounding environment. The means of processing are often no longer applicable; for the detection means of sliding window, it requires a lot of training cost and is accompanied by a high risk of false alarm

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
  • A vehicle detection method based on multiple subimages and image saliency analysis
  • A vehicle detection method based on multiple subimages and image saliency analysis

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0061] Such as figure 1 As shown, the present invention uses the sampled image Y channel information to detect vehicle targets. Firstly, preprocessing is carried out based on the saliency analysis based on image layering, and the candidate area containing the target vehicle is obtained after screening; then, the boundary correction is performed on the candidate target area containing the target vehicle; after that, the corrected area containing the target vehicle is The candidate area is sent to the classifier for accurate judgment; after that, the final target vehicle area is obtained after processing according to the multi-frame joint mechanism and the image de-overlapping mechanism.

[0062] A vehicle detection method based on multiple subimages and image saliency analysis, comprising the following steps:

[0063] S1, saliency preprocessing based on the fusion of multiple subimages;

[0064] S2, performing boundary correction on the candidate target area containing the ta...

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 present invention proposes a vehicle detection method based on multiple sub-images and image saliency analysis, including the following steps: S1, saliency preprocessing based on the fusion of multiple sub-images; S2, performing candidate target areas containing target vehicles Boundary correction; S3, accurate judgment of the corrected target candidate area; S4, multi-frame joint and de-coincidence; S5, output the coordinates of the target window area, and complete the vehicle detection. The invention has low time complexity and high real-time performance, and can adapt to many different scenarios such as rainy day or nighttime.

Description

technical field [0001] The invention relates to the field of vehicle detection, in particular to a vehicle detection method based on multiple subimages and image saliency analysis. Background technique [0002] Forward Collision Warning system (Forward Collision Warning), FCW can monitor the vehicle in front at all times through the radar system, judge the distance, orientation and relative speed between the vehicle and the vehicle in front, and warn the driver when there is a potential collision risk. The FCW system itself does not take any braking action to avoid a collision or control the vehicle. [0003] As an important part of FCW, moving vehicle detection based on visual sensors has become one of the focuses of many peer researches. The current moving vehicle detection method based on visual sensors is often difficult to detect the target vehicle when dealing with large backlight situations, because at this time, the information such as the shadow of the vehicle bott...

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): G06V10/26G06V10/25G06T3/00G06T5/40G06K9/62
CPCG06T3/0093G06T5/40G06T2207/30236G06V20/584G06V2201/08G06F18/25
Inventor 吴子章王凡唐锐
Owner ZONGMU TECH SHANGHAI CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products