Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Vehicle detection and tracking method and device

A vehicle detection and vehicle tracking technology, applied in character and pattern recognition, instruments, computer components, etc., can solve the problems of increasing vehicle position detection error and reducing the accuracy of positioning vehicle position

Active Publication Date: 2016-04-06
NETPOSA TECH
View PDF3 Cites 18 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In the process of a car detecting the vehicle position of its surrounding vehicles, when the size of the acquired vehicle image is very different from the size of the training model, scaling the size of the vehicle image will increase the detection error of the detected vehicle position and reduce the Accuracy of locating vehicle position

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
  • Vehicle detection and tracking method and device
  • Vehicle detection and tracking method and device
  • Vehicle detection and tracking method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0100] see figure 2 , the present embodiment provides a vehicle detection and tracking method, comprising the following steps:

[0101] Step 200: Detect the currently captured vehicle image to obtain vehicle features of the vehicle image; wherein the vehicle feature includes at least one of the following: image grayscale feature, gradient magnitude feature, and gradient direction feature.

[0102] The vehicle image is each frame of the vehicle image captured by the driving recorder or the vehicle panoramic imaging system pre-installed on the vehicle through the camera of the driving recorder or the vehicle panoramic imaging system during the driving of the vehicle.

[0103] Image grayscale features, gradient magnitude features and gradient direction features can be obtained using the improved aggregation channel feature algorithm (SACF); of course, other existing image grayscale features and gradient magnitude features that can obtain vehicle images can also be used And the ...

Embodiment 2

[0180] see image 3 , this embodiment provides another vehicle detection and tracking method, the vehicle detection and tracking method can be divided into two main steps of detection and tracking, and video-based vehicle detection can be divided into two stages of training and detection. Video-based vehicle detection is trained by using machine learning methods. The features and feature calculation methods in the vehicle detection process are designed. Mixed channel features are used as vehicle features for training and detection. The trainer uses cascaded Adaboost Algorithm, the detection adopts the multi-scale multi-model detection mode combined with global and local, and the vehicle tracking adopts the detection correlation integration method to achieve fast vehicle tracking effect.

[0181] The feature calculation method provided in this embodiment is described as follows:

[0182] The vehicle detection features are described by SACF features, which include the combinati...

Embodiment 3

[0218] see Figure 4 , the present embodiment provides a vehicle detection and tracking device for performing the above vehicle detection and tracking method, including: a vehicle feature detection module 400, a model selection module 402, a position information determination module 404 and a vehicle tracking module 406;

[0219]The vehicle feature detection module 400 is used to detect the currently captured vehicle image to obtain the vehicle feature of the vehicle image; wherein the vehicle feature includes at least one of the following: image grayscale feature, gradient amplitude feature and gradient direction feature;

[0220] The model selection module 402 is connected with the vehicle feature detection module 400, and is used to select a group of models adapting to the vehicle image size from the pre-trained multi-model network structure;

[0221] The location information determination module 404 is connected with the model selection module 402, and is used to perform v...

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 vehicle detection and tracking method and device. The method includes the following steps that: vehicle images which are shot currently are detected, so that the vehicle characteristics of the vehicle images can be obtained; one group of models which are suitable for the sizes of the vehicle images are selected from a pre-trained multi-model network structure; vehicle detection is performed on the vehicle characteristics through the selected models, so that the position information of vehicles in the vehicle images can be obtained; and the vehicles in the vehicle images are tracked according to the obtained position information of the vehicles. With the vehicle detection and tracking method and device provided by the invention adopted, the accuracy of vehicle positioning can be improved, so that vehicle tracking speed can be also improved.

Description

technical field [0001] The invention relates to the field of video image processing, in particular to a vehicle detection and tracking method and device. Background technique [0002] At present, in the process of driving a car, the vehicles around the normal driving car may approach it. If the distance is too close, it may cause rear-end collisions between the normal driving car and the vehicles close to it, which will affect the driving safety of the vehicle. create a threat. In order to ensure the driving safety of a normal running car, the normal running car can detect the vehicle position of the surrounding vehicles, and find the surrounding approaching vehicles in time. [0003] In the related art, in the process of the vehicle detecting the vehicle position of its surrounding vehicles, the vehicle image of the surrounding vehicles of the vehicle is first acquired, and then the acquired vehicle image is scaled to a size that meets the preset model size, and the image ...

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 Applications(China)
IPC IPC(8): G06K9/00
CPCG06V20/584
Inventor 田波魏磊磊张丛喆
Owner NETPOSA TECH
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
Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com