YOLOv8-SCS: Improved Object Detection for Autonomous Driving Under Adverse Weather Conditions

Adverse weather conditions significantly impact the performance of autonomous driving object detection systems, leading to reduced detection accuracy and an increased false detection rate. Limited annotated data further restricts performance improvement. Hence, improving detection performance under adverse weather conditions is a challenge that remains to be solved. In this paper, we develop an improved object detection model, named <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">YOLOv8-SCS</i>, by incorporating the <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Swin Transformer, Convolutional Block Attention (CBAM)</i>, and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Spatial-Channel Decoupled Downsampling (SCDown) modules</i>. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">YOLOv8-SCS</i> aims to enhance feature extraction from objects and emphasize important features in the feature map, both of which are affected by adverse weather conditions, without compromising model efficiency for real-time applications. Experimental results verify that on the DAWN dataset, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">YOLOv8-SCS</i> achieves performance improvements of 3.22%, 2.22%, 2.63%, 2.90%, and 0.72% in terms of <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Precision, Recall, F1-Score, mAP50</i>, and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">mAP50-95</i> compared to the original YOLOv8. Furthermore, its lightweight variant, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">YOLOv8-SCS-light</i>, also shows gains of 1.72%, 1.48%, 1.60%, 2.18%, and 0.4% in the same metrics, while enhancing model efficiency by reducing the number of parameters and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">GFLOPs</i>, and increasing <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">FPS</i>. In addition, the generalization ability of the proposed model under clear weather conditions is verified using the BDD100K dataset.