Cross-Modal Purification and Fusion for Small-Object RGB-D Transmission-Line Defect Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cui, Jiaming, Li, Wenqiang, Zhou, Shuai, Qin, Ruifeng, Shen, Feng
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917285416927232
author Cui, Jiaming
Li, Wenqiang
Zhou, Shuai
Qin, Ruifeng
Shen, Feng
author_facet Cui, Jiaming
Li, Wenqiang
Zhou, Shuai
Qin, Ruifeng
Shen, Feng
contents Transmission line defect detection remains challenging for automated UAV inspection due to the dominance of small-scale defects, complex backgrounds, and illumination variations. Existing RGB-based detectors, despite recent progress, struggle to distinguish geometrically subtle defects from visually similar background structures under limited chromatic contrast. This paper proposes CMAFNet, a Cross-Modal Alignment and Fusion Network that integrates RGB appearance and depth geometry through a principled purify-then-fuse paradigm. CMAFNet consists of a Semantic Recomposition Module that performs dictionary-based feature purification via a learned codebook to suppress modality-specific noise while preserving defect-discriminative information, and a Contextual Semantic Integration Framework that captures global spatial dependencies using partial-channel attention to enhance structural semantic reasoning. Position-wise normalization within the purification stage enforces explicit reconstruction-driven cross-modal alignment, ensuring statistical compatibility between heterogeneous features prior to fusion. Extensive experiments on the TLRGBD benchmark, where 94.5% of instances are small objects, demonstrate that CMAFNet achieves 32.2% mAP@50 and 12.5% APs, outperforming the strongest baseline by 9.8 and 4.0 percentage points, respectively. A lightweight variant reaches 24.8% mAP50 at 228 FPS with only 4.9M parameters, surpassing all YOLO-based detectors while matching transformer-based methods at substantially lower computational cost.
format Preprint
id arxiv_https___arxiv_org_abs_2602_01696
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Cross-Modal Purification and Fusion for Small-Object RGB-D Transmission-Line Defect Detection
Cui, Jiaming
Li, Wenqiang
Zhou, Shuai
Qin, Ruifeng
Shen, Feng
Computer Vision and Pattern Recognition
Artificial Intelligence
Transmission line defect detection remains challenging for automated UAV inspection due to the dominance of small-scale defects, complex backgrounds, and illumination variations. Existing RGB-based detectors, despite recent progress, struggle to distinguish geometrically subtle defects from visually similar background structures under limited chromatic contrast. This paper proposes CMAFNet, a Cross-Modal Alignment and Fusion Network that integrates RGB appearance and depth geometry through a principled purify-then-fuse paradigm. CMAFNet consists of a Semantic Recomposition Module that performs dictionary-based feature purification via a learned codebook to suppress modality-specific noise while preserving defect-discriminative information, and a Contextual Semantic Integration Framework that captures global spatial dependencies using partial-channel attention to enhance structural semantic reasoning. Position-wise normalization within the purification stage enforces explicit reconstruction-driven cross-modal alignment, ensuring statistical compatibility between heterogeneous features prior to fusion. Extensive experiments on the TLRGBD benchmark, where 94.5% of instances are small objects, demonstrate that CMAFNet achieves 32.2% mAP@50 and 12.5% APs, outperforming the strongest baseline by 9.8 and 4.0 percentage points, respectively. A lightweight variant reaches 24.8% mAP50 at 228 FPS with only 4.9M parameters, surpassing all YOLO-based detectors while matching transformer-based methods at substantially lower computational cost.
title Cross-Modal Purification and Fusion for Small-Object RGB-D Transmission-Line Defect Detection
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2602.01696