Improving Multispectral Pedestrian Detection by Addressing Modality Imbalance Problems
Multispectral pedestrian detection is capable of adapting to insufficient illumination conditions by leveraging color-thermal modalities. On the other hand, it is still lacking of in-depth insights on how to fuse the two modalities effectively. Compared with traditional pedestrian detection, we find multispectral pedestrian detection suffers from modality imbalance problems which will hinder the optimization process of dual-modality network and depress the performance of detector. Inspired by this observation, we propose Modality Balance Network (MBNet) which facilitates the optimization process in a much more flexible and balanced manner. Firstly, we design a novel Differential Modality Aware Fusion (DMAF) module to make the two modalities complement each other. Secondly, an illumination aware feature alignment module selects complementary features according to the illumination conditions and aligns the two modality features adaptively. Extensive experimental results demonstrate MBNet outperforms the state-of-the-arts on both the challenging KAIST and CVC-14 multispectral pedestrian datasets in terms of the accuracy and the computational efficiency. Code is available at https://github.com/CalayZhou/MBNet.
Code (2)
Tasks
Computational EfficiencyMultispectral Object DetectionPedestrian DetectionSimilar Papers 제목 키워드 기반
MSCoTDet: Language-driven Multi-modal Fusion for Improved Multispectral Pedestrian Detection
Multispectral pedestrian detection is attractive for around-the-clock applications due to the complementary information between RGB and thermal modalities. However, current models often fail to detect pedestrians in cert…
Pedestrian DetectionMS-DETR: Multispectral Pedestrian Detection Transformer with Loosely Coupled Fusion and Modality-Balanced Optimization
Multispectral pedestrian detection is an important task for many around-the-clock applications, since the visible and thermal modalities can provide complementary information especially under low light conditions. Due to…
DecoderPedestrian DetectionStrip-Fusion: Spatiotemporal Fusion for Multispectral Pedestrian Detection
Pedestrian detection is a critical task in robot perception. Multispectral modalities (visible light and thermal) can boost pedestrian detection performance by providing complementary visual information. Several gaps rem…
Pedestrian DetectionCausal Mode Multiplexer: A Novel Framework for Unbiased Multispectral Pedestrian Detection
RGBT multispectral pedestrian detection has emerged as a promising solution for safety-critical applications that require day/night operations. However, the modality bias problem remains unsolved as multispectral pedestr…
Pedestrian DetectionGuided Attentive Feature Fusion for Multispectral Pedestrian Detection
Multispectral image pairs can provide complementary visual information, making pedestrian detection systems more robust and reliable. To benefit from both RGB and thermal IR modalities, we introduce a novel attentive …
Multispectral Object Detectionobject-detectionObject DetectionPedestrian Detection