bullet Sensors & Transducers Journal

    (ISSN 1726- 5479)


2008 e-Impact Factor

25 Top Downloaded Articles

Best Selling Articles 2012

Journal Subscription 2013

Editorial Calendar 2013

Submit an Article

Editorial Board

Current Issue

S&T journal's cover

Sensors & Transducers Journal 2011

Sensors & Transducers Journal 2010

Sensors & Transducers Journal 2009

Sensors & Transducers Journal 2008

Sensors & Transducers Journal 2007

2000-2002 S&T e-Digest Contents

2003 S&T e-Digest Contents

2004 S&T e-Digest Contents

2005 S&T e-Digest Contents

2006 S&T e-Digest Contents


Best Articles 2011




Vol. 155, Issue 8, August 2013, pp. 39-46




A Novel Identification Method of Obstacles Based on Multi-sensor Data Fusion in Forest
Lei Yan, Xiaokang Ding, Zheng Yu, Jianlei Kong, * Jinhao Liu

School of Technology, Beijing Forestry University, Beijing, 100083, China
Tel.: +86-152-0130-9527

* E-mail: liujinhao@vip.163.com


Received: 27 July 2013   /Accepted: 12 August 2013   /Published: 20 August 2013

Digital Sensors and Sensor Sysstems


Abstract: In this paper an obstacle identification system was set up and an artificial neural network (ANN) was established to identify obstacles in forest based on multi-sensor fusion, aiming to improve the efficiency of automated operations of forestry harvester in the complicated environment of forest areas. Firstly, a 2D laser scanner and an infrared thermal imager were used to collect the information of obstacles in forest areas. Based on the collected infrared photo, visible pictures and laser scan data, image fusion and data association were conducted to obtain features of obstacles. Second, a BP neural network was established for forest obstacles identification by training samples. Then, to improve the performance of BP model, several common used functions were adopted to construct BP model by permutations and combinations. The test results showed that the model with trainlm training function had a best performance in forest obstacles identification. Finally, three best models were selected to be evaluated by testing all samples and the results illustrated that the three selected BP neural network models can identify trees, people, stones at a high correct rate of 93.3 % or more.


Keywords: Laser scanner, Infrared image, Visible image, Multi-sensor data fusion, Obstacle identification.


Acrobat reader logo Click <here> or title of paper to download the full pages article in pdf format



Download <here> the Library Journal Recommendation Form






1999 - 2018 Copyright , International Frequency Sensor Association (IFSA). All Rights Reserved.

Home - News - Links - Archives - Tools - Voltage-to-Frequency Converters - Standardization - Patents - Marketplace - Projects - Wish List - e-Shop - Sensor Jobs - Membership - Videos - Publishing - Site Map - Subscribe - Search

 Members Area -Sensors Portal -Training Courses - S&T Digest - For advertisers - Bookstore - Forums - Polls - Submit Press Release - Submit White Paper - Testimonies - Twitter - Facebook - LinkedIn