Self-Supervised Overlapped Multiple Weed and Crop Species Leaf Segmentation under Complex Light Condition

Abstract

Weeds are unwanted plants that compete with target crops and absorbed the required nutrients from the soil, sunlight, air, etc. The farmers are suffering from weed identification detection due to the homogeneous morphological feature of weed and crop leaves. Computer vision is a sophisticated technique which widely used for weed and crop leaves identification and detection in the agricultural field. This work has used the three different datasets such as “Deep weed”, “Crop Weed Filed Image Dataset” (CWFID), and “Leaf Segmentation Challenge” (LSC), and collected 5090 images for training the model. In this work we have used three grass species as Setariaverticillata, Digitariasanguinalis, Echinochloa crus-Galli, and three broad leaf species as Cerastiumvulgatum L.,Chenopodiumalbums, Amaranthusretroflexus in Vignamungo crops. The first dataset includes 2000, the second 1720 images, and 1370 images from the third dataset. We have proposed a deep learning segmentation model as PSPNet-U-SegNet for data classification and compared the data accuracy from existing segmentation models such as U-SegNet, and U-SegNet.Theresult has been shown the deep weed dataset has achieved98.97% data accuracy and 8.9m IoU. Our findings demonstrate that adding more datasets to the actual field picture collection improves network performance while requiring less manual annotation work.

Weed detection and recognition in complex wheat fields based on an improved YOLOv7

“…performing image transformation techniques and then trained it on four YOLO models, which a mAP value of 73.1%. Mishra et al (2024) proposed a deep learning segmentation model named "Pyramid Scene Parsing Network-USegNet" (PSPUSegNet), and by comparing with UNet, SegNet, and USegNet, etc., PSPUSegNet obtained 96.98% accuracy, 97.98% recall, and 98.96% data accuracy in Deep Weed dataset. Compared to the above studies, the proposed CSCW-YOLOV7 shows promising performance, though the five weed datasets constructed in this paper present a complex phenotype scene with similarity between wheat and weeds, multiscale weeds, and overlapping weeds.…”