UAV-YOLOv8: A Small-Object-Detection Model Based on Improved YOLOv8 for UAV Aerial Photography Scenarios

Abstract

Unmanned aerial vehicle (UAV) object detection plays a crucial role in civil, commercial, and military domains. However, the high proportion of small objects in UAV images and the limited platform resources lead to the low accuracy of most of the existing detection models embedded in UAVs, and it is difficult to strike a good balance between detection performance and resource consumption. To alleviate the above problems, we optimize YOLOv8 and propose an object detection model based on UAV aerial photography scenarios, called UAV-YOLOv8. Firstly, Wise-IoU (WIoU) v3 is used as a bounding box regression loss, and a wise gradient allocation strategy makes the model focus more on common-quality samples, thus improving the localization ability of the model. Secondly, an attention mechanism called BiFormer is introduced to optimize the backbone network, which improves the model’s attention to critical information. Finally, we design a feature processing module named Focal FasterNet block (FFNB) and propose two new detection scales based on this module, which makes the shallow features and deep features fully integrated. The proposed multiscale feature fusion network substantially increased the detection performance of the model and reduces the missed detection rate of small objects. The experimental results show that our model has fewer parameters compared to the baseline model and has a mean detection accuracy higher than the baseline model by 7.7%. Compared with other mainstream models, the overall performance of our model is much better. The proposed method effectively improves the ability to detect small objects. There is room to optimize the detection effectiveness of our model for small and feature-less objects (such as bicycle-type vehicles), as we will address in subsequent research.

An Efficient Rep-Style Gaussian–Wasserstein Network: Improved UAV Infrared Small Object Detection for Urban Road Surveillance and Safety

“…The ERGW-net consists of a backbone, neck, and head. The backbone leverages modified CSPDarknet53 [29] with a new block called iRepblock, which combines the advantages of InceptionNet [30] and ResNet [31] to improve feature acquisition while decreasing computational demands. The neck fuses and categorizes the infrared image features, and a new loss function is provided at the head to improve the network's ability to process small road objects from aerial infrared images.…”

“…The role of the backbone is to extract features from images. To improve the overall performance of the backbone, we propose a new Rep-style backbone structure based on modified CSPDarknet53 [29] from YOLOv8. In other words, we provide a Rep-style capability that supports the modified CSPDarknet53 by orchestrating ResNet, InceptionNet, and efficient RepVGG ConvNet capabilities [32].…”

DHC-YOLO: Improved YOLOv8 for Lesion Detection in Brain Tumors, Colon Polyps, and Esophageal Cancer

“…The improved YOLOv8 network [16] incorporates the characteristics of small target objects in real-world scenarios by introducing blur and noise operations. Subsequently, the network introduces the Asymptotic Feature Pyramid Network (AFPN) [17] to highlight the impact of key layer features after feature fusion, addressing direct interaction issues between non-adjacent layers.UAV-YOLOv8 [18] has optimized YOLOv8 in several aspects. Firstly, it adopts Wise-IoU (WIoU) [19] v3 as the bounding box regression loss and employs a judicious gradient assignment strategy to focus the model more on samples with common quality, thereby improving the model's localization capability.…”

Enhancing Small Object Detection in Aerial Images: A Novel Approach with PCSG Model

“…Furthermore, processing the context region of targets instead of simple pixel-by-pixel processing during training [24] yields an efficient multi-scale training approach. Another study [25] has demonstrated improved detection performance through the utilization of relevant information across different feature maps.…”