Objectives The freespace detection is a crucial foundation for scene perception in advanced driver assistance systems. Convolutional neural network-based methods are unable to build global contextual infortmation that generate voids and interruptions in predicted results. At the same time, Transformer-based methods lack local understanding resulting in boundary misalignment and exceed.
Methods To this end, we propose a pyramid Transformer architecture with learnable deep position encoding for road freespace detection. First, the pyramid Transformer backbone is designed to extract road features from global perspectives. Second, local window attention is employed in dual-Transformer blocks to compensate for detail loss. Finally, to address the problem that traditional unlearnable position encoding ignores the spatial correlation between pixels and the real world, a learnable position encoding from deep convolutional features is constructed to solve the attention and semantic misalignment.
Results This model is tested and evaluated on KITTI road, Cityscapes, and Xiamen road datasets. The results show that our method achieves maximum F measure of 97.53% and 98.54% in KITTI and Cityscapes, respectively.
Conclusions Our method outperforms existing algorithms in the KITTI road benchmark by ensuring higher efficiency while providing higher stability and accuracy. Meanwhile, our method provides high-precision semantic prior information for tasks such as path planning and trajectory prediction in automotive driving assistance systems.
DownLoad: