Xue, XiangJi, Ya TuLiu, YangXu, H. T.Ren, Q. D. E. J.Shi, B.Wu, N. E.Lu, M.Zhuang, X. F.Chen, RenjieRitschel, TobiasWhiting, Emily2024-10-132024-10-132024978-3-03868-250-9https://doi.org/10.2312/pg.20241327https://diglib.eg.org/handle/10.2312/pg20241327Aerial images captured by drones often suffer from blurriness and low resolution, which is particularly problematic for small targets. In such scenarios, the YOLO object detection algorithm tends to confuse or misidentify targets like bicycles and tricycles due to the complex features and local similarities. To address these issues, this paper proposes a SPDD-YOLO model based on YOLOv8. Firstly, the model enhances its ability to extract local features of small targets by introducing the Spatial-to- Depth Module (SPDM). Secondly, addressing the issue that SPDM reduces the receptive field, leading the model to overly focus on local features, we introduced Deep Separable Dilated Convolution (DSDC), which expands the receptive field while reducing parameters and forms the Deep Dilated Module (DDM) together with SPDM. Experiments on the VisDrone2019 dataset demonstrate that the proposed model improved precision, recall, and mAP50 by 5.8%, 5.7%, and 6.4%, respectively.Attribution 4.0 International LicenseCCS Concepts: Computing methodologies → Object recognition; Object identificationComputing methodologies → Object recognitionObject identification10.2312/pg.202413272 pages