Attention-based Cross-Modality Multiscale Fusion for Multispectral Pedestrian Detection

Multispectral pedestrian detection has wide ap-plications in fields such as autonomous driving and intelli-gent surveillance. Mining complementary information between modalities is one of the most effective approaches to improve the performance of multispectral pedestrian detection. However, the inevitable introduction of redundant information between modalities during the fusion process leads to feature degradation. To address this challenge, we propose a multiscale differen-tial fusion algorithm that leverages complementary information between modalities to suppress feature degradation caused by noise propagation along the network. We compare our algorithm with other cross-modal fusion pedestrian detection algorithms on the LLVIP and cleaned KAIST datasets. Experimental results demonstrate that our algorithm outperforms others, particularly in nighttime scenes where our algorithm achieves a 7.28%improvement in recall rate compared to the baseline on the cleaned KAIST dataset.

@article{Hui2023,
  title     = {Attention-based Cross-Modality Multiscale Fusion for Multispectral Pedestrian Detection},
  journal   = {International Journal of Advanced Computer Science and Applications},
  volume    = {14},
  number    = {11},
  year      = {2023},
  publisher = {The Science and Information Organization},
  author    = {Zhou Hui},
  doi       = {10.14569/IJACSA.2023.01411126},
  url       = {https://doi.org/10.14569/IJACSA.2023.01411126}
}