home    about    browse    search    latest    help 
Login | Create Account

Weed identification using an automated active shape matching (AASM) technique

Swain, Kishore; Nørremark, Michael; Jørgensen, Rasmus N.; Midtiby, Henrik S. and Green, Ole (2011) Weed identification using an automated active shape matching (AASM) technique. Biosystems Engineering, 110, pp. 450-457.

[thumbnail of 20658.pdf] PDF - English
Limited to [Depositor and staff only]

679kB


Summary

Weed identification and control is a challenge for intercultural operations in agriculture. As an alternative to chemical pest control, a smart weed identification technique followed by mechanical weed control system could be developed. The proposed smart identification technique works on the concept of ‘active shape modelling’ to identify weed and crop plants based on their morphology. The automated active shape matching system (AASM) technique consisted of, i) a Pixelink camera ii) an LTI Lehrstuhlfuer technische informatik) image processing library, iii) a laptop pc with the Linux OS. A 2-leaf growth stage model for Solanum nigrum L. (nightshade) is generated from 32 segmented training images in Matlab software environment. Using the AASM algorithm, the leaf model was aligned and placed at the centre of the target plant and a model deformation process carried out. The parameters used for model deformation were estimated, updated and an improved model was compared to the target plant shape to obtain the best fit. Around 90% of the nightshade plants were identified correctly with AASM. The time required for identifying target plant as a nightshade was approximately 0.053 s and a non-identification process required 0.062 s for eight iterations with the Linux platform used.


EPrint Type:Journal paper
Subjects: Crop husbandry > Weed management
Research affiliation: Denmark > DARCOF III (2005-2010) > WEEDS - Control of weeds in organic cropping
Denmark > SDU - University of Southern Denmark
Denmark > AU - Aarhus University > AU, DJF - Faculty of Agricultural Sciences
DOI:10.1016/j.biosystemseng.2011.09.011
Deposited By: Nørremark, Michael
ID Code:20658
Deposited On:26 Mar 2012 13:13
Last Modified:28 Mar 2012 13:17
Document Language:English
Status:Published
Refereed:Peer-reviewed and accepted

Repository Staff Only: item control page

Downloads

Downloads per month over past year

View more statistics