CVMar 22, 2024

MSCoTDet: Language-driven Multi-modal Fusion for Improved Multispectral Pedestrian Detection

arXiv:2403.15209v310 citationsh-index: 19IEEE transactions on circuits and systems for video technology (Print)
Originality Incremental advance
AI Analysis

This addresses detection failures in around-the-clock applications like autonomous driving, but it is incremental as it builds on existing multispectral detection methods.

The paper tackles modality bias in multispectral pedestrian detection by using Large Language Models (LLMs) with a novel prompting strategy and fusion framework, resulting in improved detection performance as validated through experiments.

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 certain cases (e.g., thermal-obscured pedestrians), particularly due to the modality bias learned from statistically biased datasets. In this paper, we investigate how to mitigate modality bias in multispectral pedestrian detection using Large Language Models (LLMs). Accordingly, we design a Multispectral Chain-of-Thought (MSCoT) prompting strategy, which prompts the LLM to perform multispectral pedestrian detection. Moreover, we propose a novel Multispectral Chain-of-Thought Detection (MSCoTDet) framework that integrates MSCoT prompting into multispectral pedestrian detection. To this end, we design a Language-driven Multi-modal Fusion (LMF) strategy that enables fusing the outputs of MSCoT prompting with the detection results of vision-based multispectral pedestrian detection models. Extensive experiments validate that MSCoTDet effectively mitigates modality biases and improves multispectral pedestrian detection.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes