Click on “Download PDF” for the PDF version or on the title for the HTML version.


If you are not an ASABE member or if your employer has not arranged for access to the full-text, Click here for options.

Machine Vision Technology for Indoor Simulated Tree Image Acquisition and Recognition

Published by the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan www.asabe.org

Citation:  Paper number  035013,  2003 ASAE Annual Meeting . (doi: 10.13031/2013.13904) @2003
Authors:   Haitao Xiang, Jiaqiang Zheng, Hongping Zhou
Keywords:   Machine Vision, Image Processing, Tree Image, Image Recognition, Precision Pesticide Spraying

The paper mainly studied the technology of acquisition and recognition of indoor simulated tree image based on machine vision instead of the human eyes. A tree image processing and analyzing system were developed, which included a CCD camera, an image grabber, a computer, and an experimental set-up based on the conveyer belt for simulating the outside conditions. First, the real-time simulated tree images were captured continually and the single frame image was elicited from the video images in a certain interval according to the relative speed between the camera and the simulated trees. At the same time, this single frame image was converted from the RGB image to the chroma image. Furthermore, the green channel of the chroma image was extracted for further processing. Then, the tree image was segmented by the iterative thresholding method. Based on the segmented image, the boundary of the tree image was extracted and the geometrical features were measured such as area, perimeter, roundness, shape factor, inscribed circle diameter, barycenter. Using the two-classification method, the features of the tree image were classified according to the thresholding of each geometrical feature. The results of indoor and outdoor tests showed that the system was suitable to recognize the tree images. According to the recognition results, the non-or off-target pesticide contamination could be decreased by accurately spraying the pesticide on the desired target.

(Download PDF)    (Export to EndNotes)