Vehicle detection method based on deep convolution neural network

A convolutional neural network, vehicle detection technology, applied in the field of road safety, to achieve high accuracy and avoid limitations

Inactive Publication Date: 2016-09-07
SOUTH CHINA UNIV OF TECH
View PDF2 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although many passive safety measures have been researched around the world to reduce casualties after accidents, the root cause of traffic accidents has not been fundamentally resolved

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 method based on deep convolution neural network
  • Vehicle detection method based on deep convolution neural network
  • Vehicle detection method based on deep convolution neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0031] Such as Figure 1-Figure 4 As shown, a vehicle detection method based on deep convolutional neural network, including:

[0032] The camera collects the road surface picture in real time, preprocesses and normalizes its size, the preprocessing includes grayscale and mean value filtering, and the camera is a monocular camera;

[0033] Segment the shadow area of ​​road vehicles by selecting an appropriate threshold;

[0034] Since 1 / 3 of a general road image contains irrelevant information such as the sky and mountains, we only need to detect the area below 1 / 3 of the image. Generally speaking, the shadow is caused by the light being obscured by the vehicle, so the gray level of the general shadow The value is lower than the road surface, so just get the normal gray value of the road surface, and the bottom shadow can be segmented out.

[0035] In order to prevent the influence of ground signs such as speed bumps and text, this paper combines the current statistical data...

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 vehicle detection method based on a deep convolution neural network. The vehicle detection method comprises the following steps: acquiring road surface pictures in real time through a camera, and normalizing sizes of the pictures; selecting a threshold to segment a road surface vehicle shadow area; determining a vehicle candidate area in the road surface vehicle shadow area; and training the convolution neural network, recognizing the vehicle candidate area by using the trained convolution neural network, and outputting a detection result. According to the vehicle detection method, the convolution neural network is adopted to perform verification, so that the timeliness and accuracy of a whole system are improved.

Description

technical field [0001] The invention relates to the field of road safety, in particular to a vehicle detection method based on a deep convolutional neural network. Background technique [0002] Undoubtedly, with the development of social economy, people's requirements for transportation tools are also constantly improving. The appearance of automobiles undoubtedly brings great convenience to people's lives, changes people's lifestyles, and improves people's living standards. At present, China has a large number of automobiles, with more than 200 million motor vehicles and nearly 100 million automobiles. In 2010, the production and sales of more than 17 million vehicles. However, with the increase of car ownership, the safety problems brought by convenient transportation cannot be ignored by people. Frequent traffic accidents, heavy casualties and huge property losses make automobile traffic safety issues increasingly become the focus of people's attention. . According to r...

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): G06K9/60G06K9/46G06K9/62
CPCG06V10/40G06V10/20G06V2201/08G06F18/214
Inventor周智恒康磊邝沛江戴铭赵汝正
OwnerSOUTH CHINA UNIV OF TECH