Full-Text Search:
Home|Journal Papers|About CNKI|User Service|FAQ|Contact Us|中文
《Forestry Machinery & Woodworking Equipment》 2018-06
Add to Favorite Get Latest Update

A Harvesting Target Recognition Method Based on Laser and Visual Information Fusion

PENG Yang;KONG Jian-lei;LIU Jin-hao;HUANG Qing-qing;WANG Dian;School of Technology,Beijing Forestry University;  
A harvesting target recognition method based on visual and laser information fusion is proposed in this paper. On the basis of data fusion,laser data are corrected using inertial unit information and nine features of an independent target point cloud cluster are extracted using the difference algorithm. A high-dimensional fuzzy support vector machine( FSVM-HIGH)-based recognition model is proposed to classify the harvesting targets in the forest area environment. The experimental results show that the average rate of correct recognition of trees,pedestrians and rocks using the high dimensional fuzzy support vector machine( FSVM-HIGH) reaches up to 93%. Compared with other traditional recognition models,the proposed algorithm has better recognition effect on harvesting targets and the comprehensive correct recognition rate of trees can be as high as 91. 79%. This method can help operators rapidly and accurately judge the operating environment-related information.
【Fund】: 林业公益性行业科研专项经费项目(201504508)
【CateGory Index】: S776;TP391.41
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
©2006 Tsinghua Tongfang Knowledge Network Technology Co., Ltd.(Beijing)(TTKN) All rights reserved