שמור ב:
| Main Authors: | , , , , , |
|---|---|
| פורמט: | Preprint |
| יצא לאור: |
2026
|
| נושאים: | |
| גישה מקוונת: | https://arxiv.org/abs/2602.06363 |
| תגים: |
הוספת תג
אין תגיות, היה/י הראשונ/ה לתייג את הרשומה!
|
| _version_ | 1866917254092816384 |
|---|---|
| author | Bie, Qian Wang, Xiao Yang, Bin Yu, Zhixi Chen, Jun Xu, Xin |
| author_facet | Bie, Qian Wang, Xiao Yang, Bin Yu, Zhixi Chen, Jun Xu, Xin |
| contents | Existing cross-modal pedestrian detection (CMPD) employs complementary information from RGB and thermal-infrared (TIR) modalities to detect pedestrians in 24h-surveillance systems.RGB captures rich pedestrian details under daylight, while TIR excels at night. However, TIR focuses primarily on the person's silhouette, neglecting critical texture details essential for detection. While the near-infrared (NIR) captures texture under low-light conditions, which effectively alleviates performance issues of RGB and detail loss in TIR, thereby reducing missed detections. To this end, we construct a new Triplet RGB-NIR-TIR (TRNT) dataset, comprising 8,281 pixel-aligned image triplets, establishing a comprehensive foundation for algorithmic research. However, due to the variable nature of real-world scenarios, imaging devices may not always capture all three modalities simultaneously. This results in input data with unpredictable combinations of modal types, which challenge existing CMPD methods that fail to extract robust pedestrian information under arbitrary input combinations, leading to significant performance degradation. To address these challenges, we propose the Adaptive Uncertainty-aware Network (AUNet) for accurately discriminating modal availability and fully utilizing the available information under uncertain inputs. Specifically, we introduce Unified Modality Validation Refinement (UMVR), which includes an uncertainty-aware router to validate modal availability and a semantic refinement to ensure the reliability of information within the modality. Furthermore, we design a Modality-Aware Interaction (MAI) module to adaptively activate or deactivate its internal interaction mechanisms per UMVR output, enabling effective complementary information fusion from available modalities. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_06363 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Robust Pedestrian Detection with Uncertain Modality Bie, Qian Wang, Xiao Yang, Bin Yu, Zhixi Chen, Jun Xu, Xin Computer Vision and Pattern Recognition Existing cross-modal pedestrian detection (CMPD) employs complementary information from RGB and thermal-infrared (TIR) modalities to detect pedestrians in 24h-surveillance systems.RGB captures rich pedestrian details under daylight, while TIR excels at night. However, TIR focuses primarily on the person's silhouette, neglecting critical texture details essential for detection. While the near-infrared (NIR) captures texture under low-light conditions, which effectively alleviates performance issues of RGB and detail loss in TIR, thereby reducing missed detections. To this end, we construct a new Triplet RGB-NIR-TIR (TRNT) dataset, comprising 8,281 pixel-aligned image triplets, establishing a comprehensive foundation for algorithmic research. However, due to the variable nature of real-world scenarios, imaging devices may not always capture all three modalities simultaneously. This results in input data with unpredictable combinations of modal types, which challenge existing CMPD methods that fail to extract robust pedestrian information under arbitrary input combinations, leading to significant performance degradation. To address these challenges, we propose the Adaptive Uncertainty-aware Network (AUNet) for accurately discriminating modal availability and fully utilizing the available information under uncertain inputs. Specifically, we introduce Unified Modality Validation Refinement (UMVR), which includes an uncertainty-aware router to validate modal availability and a semantic refinement to ensure the reliability of information within the modality. Furthermore, we design a Modality-Aware Interaction (MAI) module to adaptively activate or deactivate its internal interaction mechanisms per UMVR output, enabling effective complementary information fusion from available modalities. |
| title | Robust Pedestrian Detection with Uncertain Modality |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.06363 |