Improved Detection and Location of Small Crop Organs by Fusing UAV Orthophoto Maps and Raw Images

Extracting the quantity and geolocation data of small objects at the organ level via large-scale aerial drone monitoring is both essential and challenging for precision agriculture. The quality of reconstructed digital orthophoto maps (DOMs) often suffers from seamline distortion and ghost effects, making it difficult to meet the requirements for organ-level detection. While raw images do not exhibit these issues, they pose challenges in accurately obtaining the geolocation data of detected small objects. The detection of small objects was improved in this study through the fusion of orthophoto maps with raw images using the EasyIDP tool, thereby establishing a mapping relationship from the raw images to geolocation data. Small object detection was conducted by using the Slicing-Aided Hyper Inference (SAHI) framework and YOLOv10n on raw images to accelerate the inferencing speed for large-scale farmland. As a result, comparing detection directly using a DOM, the speed of detection was accelerated and the accuracy was improved. The proposed SAHI-YOLOv10n achieved precision and mean average precision (mAP) scores of 0.825 and 0.864, respectively. It also achieved a processing latency of 1.84 milliseconds on 640x640 resolution frames for large-scale application. Subsequently, a novel crop canopy organ-level object detection dataset (CCOD-Dataset) was created via interactive annotation with SAHI-YOLOv10n, featuring 3986 images and 410,910 annotated boxes. The proposed fusion method demonstrated feasibility for detecting small objects at the organ level in three large-scale in-field farmlands, potentially benefiting future wide-range applications.