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

Barrier detection early-warning system based on monocular and binocular vision fusion

An obstacle detection and early warning system technology, applied in the field of image processing, can solve problems such as large time complexity, and achieve the effect of reducing program running time and improving practicability.

Inactive Publication Date: 2018-06-26
ZHONGYUAN WISDOM CITY DESIGN RES INST CO LTD
View PDF7 Cites 25 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Extract the features of pedestrians and put them into the classifier for training. Similar methods include Harr features and Adaboost algorithm. The advantages of this type of method are high accuracy and small impact of camera shake, but the disadvantage is that the time complexity is large, and training is required in advance. Need to retrain after transformation

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
  • Barrier detection early-warning system based on monocular and binocular vision fusion
  • Barrier detection early-warning system based on monocular and binocular vision fusion
  • Barrier detection early-warning system based on monocular and binocular vision fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0060] The technical solutions of the present invention will be described in further detail below through specific implementation methods.

[0061] Such as figure 1 and figure 2 As shown, the present invention provides an obstacle detection and early warning system based on single and binocular vision fusion, including a binocular camera, a display device, a power module and JetsonTX1, and realizes obstacle detection and early warning through the following steps:

[0062] 1) According to the input left and right original images, use the calibrated camera information to perform image correction to obtain line-aligned left and right image pairs. The binocular camera is first calibrated to obtain its internal and external parameters for subsequent image correction operations. Table 1 shows that the internal parameters of the camera include the focal length (f x ,f y ), principal point position (x 0 ,y 0 ), radial distortion (k 1 ,k 2 ) and tangential distortion (p 1 ,p ...

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 barrier detection early-warning system based on monocular and binocular vision fusion. Barrier detection early-warning is realized through the steps that first, according to an input left original image and an input right original image, calibrated camera information is utilized to perform image correction, and a left-right image pair in row alignment is obtained; second,a semi-global stereo matching algorithm based on a mobile terminal is adopted to process the left-right image pair, and a left parallax image is acquired through algorithm optimization; third, monocular-vision barrier detection is performed on the corrected left image, and pedestrians and vehicles in the image are recognized; and fourth, the distance and direction of a barrier are determined according to the pedestrians and vehicles detected in the third step in combination with depth information of binocular vision, and whether the barrier is in a safe range is determined according to a set early-warning threshold.

Description

technical field [0001] The invention relates to the technical field of image processing, in particular to an obstacle detection and early warning system based on single and binocular vision fusion. Background technique [0002] Binocular stereo vision is to simulate the human eyes, use two cameras to take left and right images from different angles, obtain the disparity map through the stereo matching algorithm, and restore the depth information in the scene according to the relationship between the disparity map and the depth map. [0003] Stereo matching algorithm is the focus of its research. At present, traditional stereo matching algorithms are mainly divided into three categories: local matching algorithms, global matching algorithms and semi-global matching algorithms. [0004] The local matching algorithm mainly performs matching by comparing the local characteristics within a certain range of the points to be matched. The advantage is that the calculation speed is...

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): G06K9/00G06K9/62
CPCG06V20/58G06F18/241
Inventor 马杰杜红民肖进胜孔晓阳王莹莹王茹川王磊
Owner ZHONGYUAN WISDOM CITY DESIGN RES INST CO LTD
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