Weed Detection and Localization in Soybean Crops Using YOLOv4 Deep Learning Model

Abstract

In precision agriculture, detection of weed is vital to control or remove it, as the weeds will impact the crop's yield. Also accurately distinguishing weeds and crop and their localization is important, to reduce the herbicides and pesticides usage. Deep learning techniques are effective for classification and detection of these. You Only Look Once v4 (YOLOv4) deep learning architecture is very widely used for object detection and localization of objects in an image. In this work, YOLOv4 is used for detection and localization of weeds in soybean fields. The experiments are done on publicly available soybean and weed dataset containing soybean, grass, broadleaf and soil images, each group having 1000 images. YOLOv4 architecture yielded an accuracy of 98.42%, recall of 93.13% and mAP of 81.24%, better than the performance of R -CNN and SSD networks. Additionally, different pre -trained networks viz., Darknet19, Mobilenetv2, VGG19, Resnet18, Inceptionv3 and Densenet201 are also investigated for classification of weed/crop which yielded an accuracy of 98.75%, 98.9%, 99.25%, 99.25%, 99.42%, 99.58% and 99.67% respectively. For preprocessing of images CLAHE algorithm is used. From different models investigated, it is observed that YOLOv4 is efficient for both classification and detection along with localization.