A method and system for real-time detection of multimodal pedestrian images

By using the improved MAFD-DETR model and employing adaptive frequency-domain gated wavelet convolution and thermal gradient-guided windmill convolution modules, the problems of insufficient feature extraction and high false alarm rate in multimodal pedestrian detection under adverse lighting conditions are solved, achieving high-precision and real-time pedestrian detection.

CN121884396BActive Publication Date: 2026-05-26WUXI UNIV
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
WUXI UNIV
Filing Date
2026-03-23
Publication Date
2026-05-26

AI Technical Summary

Technical Problem

Existing multimodal pedestrian detection technologies struggle to adaptively suppress frequency domain noise under adverse lighting conditions, neglect edge gradient information in infrared images, and fail to balance high accuracy with real-time performance, resulting in inaccurate detection and high computational demands.

Method used

An improved MAFD-DETR model is adopted, which uses a dual-stream backbone network, including an adaptive frequency-domain gated wavelet convolution module and a thermal gradient-guided windmill convolution module, combined with a progressive semantic fusion module, to adaptively process visible light and infrared image features, thereby achieving multi-scale feature extraction and cross-modal feature fusion.

Benefits of technology

It significantly reduces the false alarm rate of small targets, improves the robustness and detection accuracy of the model under complex lighting conditions, meets real-time requirements, reduces the false alarm rate, and enables all-weather pedestrian detection.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121884396B_ABST
    Figure CN121884396B_ABST
Patent Text Reader

Abstract

A real-time multimodal pedestrian image detection method and system is disclosed. This invention relates to the fields of intelligent transportation systems, autonomous driving environmental perception, and computer vision, specifically a real-time multimodal pedestrian image detection method and system. The invention constructs a MAFD-DETR detection model: In the visible light branch, an adaptive frequency-domain gated wavelet convolution is introduced. By constructing a global frequency-domain gated unit, frequency band weights are dynamically learned to adaptively suppress high-frequency noise and enhance texture features. In the infrared branch, a thermal gradient-guided windmill-shaped convolution is introduced. Central difference convolution is used to extract edge temperature gradients, and gradient masks are used to modulate the windmill-shaped intensity features, effectively filtering background thermal noise. Finally, a progressive semantic fusion module integrates dual-stream features and outputs the detection results. This invention significantly improves the accuracy and robustness of pedestrian detection in all-weather scenarios and meets the real-time requirements of in-vehicle systems.
Need to check novelty before this filing date? Find Prior Art