Development of an Algorithm for Goldenrod Detection using Digital Image Processing Techniques
Description: The improved management practices alleviated the overall wild blue berry productivity but the problem of uniform herbicide application still pertains, resulting into the increased cost of production and posing a sever threat to the local climatology. One of the major weed often found in wild blueberry fields is Goldenrod that expands due to rhizomes.This patched growth of Goldenrod enables us to take an advantage of the spot or site specific application of herbicide. In order to apply the herbicides in the site specific manner, digital image processing techniques offers a viable solution and will be used for sensing the spatial location of the weed patches followed by the automatic spray applications. Co-occurrence matrix based textural features extraction technique will be used to differentiate between the wild blueberry plants and weed patches. An algorithm will be developed in order to extract these features and multiple discriminant analysis to classify the plant and Goldenrod weeds. Overall accuracy of classification can be checked by calculating the number of correctly classified and misclassified pixels and the overall time required to process these images will be calculated. The developed algorithm and the trained model will be tested in the field to identify the real time application of the developed system.
Keywords: Goldenrod; Co-occurrence matrix; Wild blueberry; Digital images.
Conference name: CSBE/SCGAB 2016 Annual Conference, Halifax, 3-6 July 2016.
Session name: Session 4C: Precision Agriculture/Power and Machinery
Citation: . 2016. Development of an Algorithm for Goldenrod Detection using Digital Image Processing Techniques. CSBE/SCGAB 2016 Annual Conference, Halifax, 3-6 July 2016.
Publisher: Canadian Society for Bioengineering
Language 1: en
Rights: Canadian Society for Bioengineering