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

A Vehicle Detection Method Based on Adaptive Local Feature Background Model

A background model and local feature technology, applied in the field of intelligent transportation research, can solve problems such as background model light pollution

Active Publication Date: 2017-11-03
SOUTHEAST UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Purpose of the invention: In order to solve the problems existing in the prior art and effectively solve the problem that the background model is easily polluted by sudden or gradually changing illumination in complex traffic scenes, the present invention provides a vehicle detection based on an adaptive local feature background model method

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 Adaptive Local Feature Background Model
  • A Vehicle Detection Method Based on Adaptive Local Feature Background Model
  • A Vehicle Detection Method Based on Adaptive Local Feature Background Model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0017] The present invention will be further described below in combination with the accompanying drawings and specific embodiments.

[0018] The method includes the following steps:

[0019] (1) The video sensor collects video images of traffic scenes in real time, and defines the adaptive local binary mode feature of the pixels in the image in the pixel block centered on the current pixel as ALMP, and the calculation formula is:

[0020]

[0021]

[0022]

[0023] In the formula, the position (x, y) is the center pixel of the pixel block, i x,y is the pixel value of the central pixel at the (x,y) position, i x,y,p Corresponding to the pixel value of the Pth pixel in the set of P pixels in the neighborhood of the center pixel at the position (x, y), m is the average value of the center pixel in the pixel block and its neighbors, and T is the adaptive Distance threshold; where, position (x, y) is the central pixel of the pixel block, ALMP (x, y) is the adaptive loca...

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 provides a vehicle detection method based on an adaptive local feature background model. First, an adaptive distance threshold is used to calculate the texture in a pixel-predefined area, and a background model is constructed through the latest calculated feature, and the difference between the input video frame and the background model is The difference between them is calculated by the texture feature of the adaptive local mean binary mode, according to the adaptive local mean binary mode feature of the input pixel of the current frame and the adaptive local mean binary mode feature of the background model. The bright distance divides the pixels into background and foreground, and finally the background model is updated based on the method of joint conservative update and random sampling to adapt to changing lighting and dynamic background. The invention can effectively solve the problem that the background model is easily polluted by sudden or gradually changing illumination in complex traffic scenes.

Description

technical field [0001] The invention relates to the field of intelligent transportation research, in particular to the research on vehicle detection methods in complex urban traffic scenes. Background technique [0002] In recent years, as an important part of intelligent transportation systems and smart cities, the intelligence of urban traffic has received more attention. At present, video sensors are installed at many traffic checkpoints in the city, and thousands of videos are generated every day. However, in urban traffic, the traffic density is high, the traffic congestion is serious, and the road users are diverse. It is very important to obtain the prospect of movement from the complex background of urban traffic for urban traffic and urban public safety. However, finding a common Lu A good method for foreground detection and segmentation of urban traffic vehicles remains a challenge. [0003] In the process of vehicle detection, the current background model is easi...

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): G06K9/00G06K9/38
CPCG06V20/52G06V10/28
Inventor 赵池航张运胜陈爱伟
Owner SOUTHEAST UNIV