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

Barrier detection method in vegetation environment based on multispectral and 3D feature fusion

A technology for obstacle detection and three-dimensional features, which is applied in image data processing, instruments, calculations, etc., and can solve problems such as greater influence of changes in light intensity and poor effect of three-dimensional point clouds

Inactive Publication Date: 2015-09-23
ZHEJIANG UNIV
View PDF3 Cites 72 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this method still has shortcomings in terms of detection accuracy and robustness. The NDVI feature is greatly affected by changes in the light intensity of the environment, and the distribution characteristics of the 3D point cloud are not effective when the point cloud is sparse.

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 method in vegetation environment based on multispectral and 3D feature fusion
  • Barrier detection method in vegetation environment based on multispectral and 3D feature fusion
  • Barrier detection method in vegetation environment based on multispectral and 3D feature fusion

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment

[0057] In the test of the real scene, an ordinary 5-seat off-road vehicle was used as the experimental platform, and the Velodyne HDL-64E S2 three-dimensional lidar was installed on the roof, and the Bumblebee2 binocular camera and the MER-040-60UM-L digital camera (in front of the lens) were installed in front of the vehicle. Configure a 780nm filter). Such as image 3 , the 3D lidar is used to collect 3D point cloud data; the right eye of the Bumblebee2 binocular camera is used to collect color images, hereinafter referred to as the color camera, and the color image resolution is 1024*768; the MER-040-60UM-L digital camera is used to collect Near-infrared image, hereinafter referred to as near-infrared camera, the resolution of near-infrared image is 752*476. Calibrate the internal and external parameters of the fusion sensor system, the internal parameters of the color camera are: f c =[917.2670,896.3891],k c =[-0.3217,0.1558,0.0052,0.0095,0], the external parameters bet...

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 barrier detection method in the vegetation environment based on multispectral and 3D feature fusion. The method comprises that 3D point cloud data is collected, and color and near-infrared images are collected at the same time; 3D point cloud data is registered with multispectral data to obtain multispectral 3D point cloud; a grid map is established, and candidate barrier grids are obtained via a height threshold; the scale of the near-infrared image is adjusted to normalize the infrared light intensity; the near-infrared intensity value and the visible light intensity of RGB color information within the grids are combined and serve as feature information, and 2D feature is obtained via calculation; and the candidates barrier grids are processed and filtered by utilizing a Gaussian mixture model to obtain a final barrier detection result. According to the method, influence caused by change of illumination condition is reduced by normalizing the infrared light intensity, and multispectral 3D features are sued to realize effective barrier detection.

Description

technical field [0001] The invention relates to an obstacle detection method in the field of artificial intelligence, in particular to an obstacle detection method in a vegetation environment based on multispectral three-dimensional feature fusion, which can be used for obstacle detection of unmanned vehicles in complex environments. Background technique [0002] For autonomous vehicles, obstacle detection systems have been one of the key components. Autonomous vehicles can safely and reliably navigate and walk without a good obstacle detection system. With the improvement of the performance of various sensors and the development of technology, today's intelligent navigation technology can well deal with the scenes of structured and semi-structured roads. Most of the objects in these scenes are rigid. Generally, according to their volume and The height and the performance of the car body itself can determine which obstacles need to be avoided and which ones can pass safely....

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): G06T7/00
CPCG06T7/0002G06T2207/10036G06T2207/10044G06T2207/10048G06T2207/30181
Inventor 项志宇王盛
Owner ZHEJIANG 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