Method and device for detection of vehicle at night and method and device for tracking of vehicle at night

A vehicle detection and vehicle technology, applied in the field of image processing, can solve problems such as errors, achieve the effect of expanding the number of targets, reducing the missing tracking rate and wrong tracking rate, and improving the accuracy rate

Active Publication Date: 2013-06-12
DATANG MOBILE COMM EQUIP CO LTD
View PDF7 Cites 37 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

From this point of view, vehicle tracking and vehicle detection are inseparable. Vehicle tracking

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
  • Method and device for detection of vehicle at night and method and device for tracking of vehicle at night
  • Method and device for detection of vehicle at night and method and device for tracking of vehicle at night
  • Method and device for detection of vehicle at night and method and device for tracking of vehicle at night

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0086] In order to make the above objects, features and advantages of the present invention more comprehensible, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0087] refer to figure 1 , shows a flow chart of a nighttime vehicle detection method according to the present invention, and this embodiment may specifically include the following steps:

[0088] Step 100, calibrate the vehicle image to obtain the calibration ratio;

[0089] The purpose of calibrating the vehicle image is to obtain the scale between the actual vehicle in the three-dimensional real space and the two-dimensional vehicle image, that is, the above-mentioned calibration ratio. Obtaining the calibration ratio in this step 100 is usually completed in the first frame image, and the obtained calibration ratio is a prerequisite for realizing the steps of vehicle light extraction, vehicle light pairing and vehicle light gr...

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 provides a method and a device for detection of a vehicle at night. The method and the device for the detection of the vehicle at night are used for improving accuracy of the detection of the vehicle at night. Correspondingly, the invention further provides a method and a device for tracking of the vehicle at night. The method and the device for the tracking of the vehicle at night are used for improving the accuracy of the tracking of the vehicle at night. The method for the detection of the vehicle at night comprises the steps of calibrating an image of the vehicle and obtaining calibration rate, calculating the connection domain of the image of the vehicle, carrying out car light extraction on the connection domain by means of a taillight model and obtaining effective car lights; and pairing all the effective lights according to the calibration rate and obtaining car light pairs, grouping the car light pairs belonging to the same vehicle and using the taillight in the car light pair as a detection target and carrying out detection. According to the method for the detection of the vehicle at night, the extraction of the car light is innovatively improved, interference to the extraction of the car light of road reflection rays produced by street lights on both sides of a road and reflection rays of the road is reduced, and the accuracy of the detection of the vehicle at night is improved.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to a nighttime vehicle detection method, tracking method and device. Background technique [0002] Because the lighting conditions of the road at night are usually worse than that in the daytime, and the visibility of the vehicle body and the illumination of the road surface are often insufficient at night, most of the information of the vehicle target is invisible or not obvious, while the lights of the vehicle are generally prominent and clear, and are in harmony with the background and the vehicle. The brightness contrast of the body is sharp, so the vehicle target can be marked more accurately and conveniently, so the method of detecting the vehicle light is usually used to realize the vehicle detection at night. [0003] However, the environment at night is complex and diverse, and the halos produced by the lights themselves, the reflected light from the road surface, ...

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
IPC IPC(8): G08G1/01G06K9/54
Inventor 栗丽游亚平李谦王新生
Owner DATANG MOBILE COMM EQUIP CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap