DCCLA: Dense Cross Connections With Linear Attention for LiDAR-Based 3D Pedestrian Detection

摘要

LiDAR-based 3D pedestrian detection has recently been extensively applied in autonomous driving and intelligent mobile robots. However, it remains a highly challenging perceptual task due to the sparsity of pedestrian point cloud data and the significant deformation of pedestrian body postures. To address these challenges, we propose a Dense Cross Connections network with Linear Attention (DCCLA), which mitigates the semantic discrepancy between the encoder and decoder of the network by integrating multiple 3D sparse convolutional layers within the skip connections. Furthermore, we enhance these connections by introducing cross-connections, thereby effectively promoting information interaction among various channels. To effectively retain crucial information while summarizing diverse pedestrian representations, we propose the Linear Self-Attention module for 3D point clouds (LSA3D), which significantly reduces model complexity. The experimental results demonstrate that our DCCLA achieves state-of-the-art Average Precision (AP) for the 3D pedestrian detection task on the JRDB large-scale dataset, outperforming the second-ranked method by 2.7% AP. Furthermore, our DCCLA enhances 1.6% mIoU over the benchmark method on the SemanticKITTI dataset. Therefore, our method achieves excellent performance through a cross-scale feature fusion strategy and linear attention that fully combines the advantages of convolution and transformer architectures. The project is publicly available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/jinzhengguang/DCCLA</uri>.