Vehicle detection algorithm based on improved RT-DETR

Vehicle detection algorithms are integral to intelligent traffic management and AI-assisted driving systems. However, the complexity and variability of traffic scenarios present significant challenges. Spatial pyramid pooling enhances a model’s ability to capture multi-scale contextual information by offering different levels of feature representation, which is particularly beneficial in complex traffic scenarios. In this paper, we extend spatial pyramid pooling to Transformer-based models and propose an abstracted linear spatial pyramid attention. This mechanism enables the model to perceive multi-scale information and facilitates inter-level communication through an information broadcasting strategy, thereby enhancing its adaptability to complex traffic scenarios. Additionally, we propose a spatial coordination filtering module to explicitly aggregate global spatial dependencies, filter spatial redundancies, and suppress irrelevant information. To address computational costs, we employ partial convolution in the model’s backbone network to minimize redundant computation. Experiments conducted on the BDD100K and KITTI datasets demonstrate that our model improves the mean average precision (mAP@50) by 2.7% and reduces model parameters by approximately 16% compared to the existing RT-DETR model. These findings confirm the efficacy and advantages of our proposed method.