Anzeige
Erschienen in:
2018 | OriginalPaper | Buchkapitel
Shallow and Deep Model Investigation for Distinguishing Corn and Weeds
verfasst von : Yu Xia, Hongxun Yao, Xiaoshuai Sun, Yanhao Zhang
Erschienen in: Advances in Multimedia Information Processing – PCM 2017
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Abstract
Nowadays, the development of agriculture is growing very fast. The yields of corn is also an important indicator and a great part in the agriculture, which makes automatic weeds removal a necessary and urgent task. There are many challenges to distinguish the corn and weed, the biggest one is the similarity in both color and shape between corn and weeds. The processing speed is also very important in practical application. In this paper, we investigate two methods to fulfill this task. The first one is training and computing the SIFT and HARRIS feature descriptors, then using the SVM classifier to distinguish the corn and weeds. The second one is an End-to-End solution based on the faster R-CNN model. In addition, we design a specific module in order to improve the processing speed and ensure the accuracy at the same time. The experiment results conducted on our dataset demonstrate that detection based on improved Faster R-CNN model can better handle the problem.