Accurate and rapid response in complex driving scenarios is a challenging problem in autonomous driving. If a target is detected, the vehicle will not be able to react in time, resulting in fatal safety accidents. Therefore, the application of driver assistance systems requires a model that can accurately detect targets in complex scenes and respond quickly. In this paper, a lightweight feature extraction model, ShuffDet, is proposed to replace the CSPDark53 model used by YOLOX by improving the YOLOX algorithm. At the same time, an attention mechanism is introduced into the path aggregation feature pyramid network (PAFPN) to make the network focus more on important information in the network, thereby improving the accuracy of the model. This model, which combines two methods, is called ShuffYOLOX, and it can improve the accuracy of the model while keeping it lightweight. The performance of the ShuffYOLOX model on the KITTI dataset is tested in this paper, and the experimental results show that compared to the original network, the mean average precision (mAP) of the ShuffYOLOX model on the KITTI dataset reaches 92.20%. In addition, the number of parameters of the ShuffYOLOX model is reduced by 34.57%, the Gflops are reduced by 42.19%, and the FPS is increased by 65%. Therefore, the ShuffYOLOX model is very suitable for autonomous driving applications.

Recently, object detection, as a critical technology to improve the autonomous perception capabilities of optical sensors in Autonomous Driving Systems (ADS), has become a primary research focus in the field of ADS perception. However, the practical implementation of these networks can be challenging due to their scale and complexity, making it difficult to implement them directly on devices with limited resources. To address this issue, a universal two-stage model compression approach has been implemented. During the initial phase, ShuffDet is introduced as a lightweight network architecture to reduce the structural parameters within the network effectively. During the second phase, probability distribution distillation techniques are applied to the network post-lightweighting to mitigate the impact of structural lightening on network precision. The algorithm was tested using two public datasets, BDD100K and KITTI. The experimental outcomes demonstrate that this method enhances precision while substantially lowering the model’s complexity. To demonstrate its universality, we replaced the base network with YOLOX, which produced satisfactory results. To determine the effectiveness of the method in real-world deployment settings, we deployed the model on an NVIDIA Jetson Nano chip. The experimental outcomes confirmed the effectiveness of our proposed approach, achieving real-time detection standards. When compared to alternative lightweighting techniques, this method is more advantageous for deployment in autonomous driving systems.

High-resolution remote sensing image shadow detection has wide applications in target recognition, land information retrieval, and other fields. However, current shadow detection technologies still face challenges, including shadow omission and difficulty in defining boundaries. To address these challenges, this paper proposes a shadow detection method based on a Multi-Branch Channel-Spatial Attention Network (MBCSANet), which combines the Multi-Branch Feature Aggregation Module (MFAM) and the Channel-Spatial Parallel Attention Feature Fusion Module (C-SPAFFM). The MFAM effectively integrates shadow information at different scales, reducing missed detections caused by changes in shadow size and shape. The CSPAFFM enhances channel information to highlight boundary features and optimizes spatial information to more accurately capture spatial variations in shadows, thereby further reducing the possibility of missed detections. The effectiveness of the proposed method was validated on the public dataset AISD and the self-constructed satellite image dataset SISD. On the AISD dataset, the F1-score, OA, IOU, and BER metrics were 93.76%, 97.36%, 88.33%, and 4.19%, respectively. On the SISD dataset, these metrics reached 91.37%, 94.91%, 84.25%, and 6.87%. Experimental results show that the proposed method performs well in shadow detection tasks for high-resolution remote sensing images.