PlantDet: A benchmark for Plant Detection in the Three-Rivers-Source Region
This work addresses plant detection for botanical research and management in a specific natural reserve, presenting an incremental improvement with a new dataset and method.
The authors tackled plant detection in the Three-River-Source region by constructing a dataset (PTRS) with 21 types and 6965 high-resolution images, and developed the PlantDet network, achieving a precision of 88.1% and mAP of 77.6%.
The Three-River-Source region is a highly significant natural reserve in China that harbors a plethora of botanical resources. To meet the practical requirements of botanical research and intelligent plant management, we construct a dataset for Plant detection in the Three-River-Source region (PTRS). It comprises 21 types, 6965 high-resolution images of 2160*3840 pixels, captured by diverse sensors and platforms, and featuring objects of varying shapes and sizes. The PTRS presents us with challenges such as dense occlusion, varying leaf resolutions, and high feature similarity among plants, prompting us to develop a novel object detection network named PlantDet. This network employs a window-based efficient self-attention module (ST block) to generate robust feature representation at multiple scales, improving the detection efficiency for small and densely-occluded objects. Our experimental results validate the efficacy of our proposed plant detection benchmark, with a precision of 88.1%, a mean average precision (mAP) of 77.6%, and a higher recall compared to the baseline. Additionally, our method effectively overcomes the issue of missing small objects.