Application of deep learning for real-time detection, localization, and counting of the malignant invasive weed Solanum rostratum Dunal.

Abstract

Solanum rostratum Dunal (SrD) is a globally harmful invasive weed that has spread widely across many countries, posing a serious threat to agriculture and ecosystem security. A deep learning network model, TrackSolanum, was designed for real-time detection, location, and counting of SrD in the field. The TrackSolanmu network model comprises four modules: detection, tracking, localization, and counting. The detection module uses YOLO_EAND for SrD identification, the tracking module applies DeepSort for multi-target tracking of SrD in consecutive video frames, the localization module determines the position of the SrD through center-of-mass localization, and the counting module counts the plants using a target ID over-the-line invalidation method. The field test results show that for UAV video at a height of 2m, TrackSolanum achieved precision and recall of 0.950 and 0.970, with MOTA and IDF1 scores of 0.826 and 0.960, a counting error rate of 2.438%, and FPS of 17. For UAV video at a height of 3m, the model reached precision and recall of 0.846 and 0.934, MOTA and IDF1 scores of 0.708 and 0.888, a counting error rate of 4.634%, and FPS of 79. Thus, the TrackSolanum supports real-time SrD detection, offering crucial technical support for hazard assessment and precise management of SrD.