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

Convolutional neural network-based method for recognizing targets in front of vehicles

A convolutional neural network and target recognition technology, applied in biological neural network models, neural architecture, character and pattern recognition, etc., can solve the problem of inability to guarantee the recognition success rate, and achieve the effect of strong environmental adaptability and high recognition rate

Inactive Publication Date: 2018-01-26
JILIN UNIV
View PDF2 Cites 41 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, visual sensors are easily interfered by factors such as camera shooting angles, complex backgrounds, and overlapping obstacles, which cannot guarantee a high recognition success rate.

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
  • Convolutional neural network-based method for recognizing targets in front of vehicles
  • Convolutional neural network-based method for recognizing targets in front of vehicles
  • Convolutional neural network-based method for recognizing targets in front of vehicles

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] refer to figure 1 , a vehicle front target recognition method based on convolutional neural network, the steps are as follows:

[0041] Step 1. Sample acquisition and image processing

[0042] 1) Acquire target samples in front of the vehicle: Obtain images from public datasets of vehicle recognition algorithms such as vehicle detection, vehicle tracking, and semantic segmentation. Part of the images are used as original training samples, and the rest are used as original test samples.

[0043] The data used for training and testing are MIT (Massachusetts Institute of Technology, Massachusetts Institute of Technology) data and KITTI (Karlsruhe Institute of Technology and Toyota Technological Institute, computer vision algorithm evaluation platform) data sets published on the Internet. The original training samples are 2000 images with a size of 50*50 pixels, and the object to be recognized is in the center of the image. The original test samples are 500 images with a ...

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 convolutional neural network-based method for recognizing targets in front of vehicles. The method comprises the following steps that: 1, a large number of traffic-related images are obtained and are adopted as samples, left-and-right mirroring transformation is performed on the collected images, data sets are expanded, and labels are fabricated; color channel combinationis performed on each color image, and a grayed training data set and a test data set are fabricated; 3, a convolutional neural network model is constructed on an MATLAB platform; and 4, the trainingdata set is inputted into the convolutional neural network, so that a trained convolutional neural network is obtained; and 5, the test data set is inputted to the trained convolutional neural network, so that a recognition rate can be obtained. The method of the invention can detect vehicles and pedestrians in pictures taken by monocular cameras, has a high recognition rate and can realize the function of classifying obstacles in front of different types of vehicles.

Description

technical field [0001] The invention belongs to the field of advanced driver assistant system (Advanced Driver Assistant System, referred to as ADAS) and the field of vehicle unmanned driving, and is a method for recognizing objects in front of a vehicle based on a convolutional neural network, which can classify obstacles in front of a vehicle , which can better classify and identify the vehicles and pedestrians ahead. Background technique [0002] In recent years, the advanced driver assistance system market has grown rapidly. The advanced driver assistance system uses various sensors installed on the car to sense the surrounding environment at any time during the driving process of the car, collect data, and identify and detect static and dynamic objects. and tracking, combined with navigator map data, for systematic calculation and analysis, so that the driver can be aware of possible dangers in advance, or actively control the vehicle, effectively increasing the comfort...

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): G06K9/00G06K9/62G06N3/04
Inventor 杨正才高镇海胡宏宇何磊吕科
Owner JILIN UNIV
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

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