Low-visibility environment pedestrian detection method based on improved YOLOv8n model

By improving the YOLOv8n model, introducing a dual-branch fusion attention network, a feature aggregation and calibration pyramid network, and an adaptive task alignment detection head, the problems of poor target detection accuracy and robustness in low-visibility environments are solved, and more accurate pedestrian detection in foggy conditions is achieved.

CN120689903APending Publication Date: 2025-09-23DALIAN NATIONALITIES UNIVERSITY
0 Cites 6 Cited by

Patent Information

Application Number
CN202510682464.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-05-26
Publication Date
2025-09-23

AI Technical Summary

Technical Problem

In low-visibility environments, existing technologies make it difficult for image models to effectively extract target features, resulting in poor detection accuracy and robustness. Especially in foggy weather conditions, visual sensors are severely affected by fog noise and find it difficult to accurately detect pedestrians.

Method used

An improved YOLOv8n model is adopted, and a dual-branch fusion attention network, a feature aggregation and calibration pyramid network, and an adaptive task alignment detection head are introduced. The network's detection ability in complex backgrounds is enhanced through feature fusion and calibration mechanisms. A multi-expanded hierarchical attention module is designed to replace SPPF, and dynamic convolution alignment task decomposition is performed.

Benefits of technology

The accuracy and stability of pedestrian detection in foggy weather are improved, the ability to extract fuzzy target boundaries and detailed features is enhanced, the accuracy and robustness of detection are improved, and the requirements of pedestrian detection in foggy weather are met.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention provides a low-visibility environment pedestrian detection method based on an improved YOLOv8n model. A double-branch fusion attention network is adopted in a backbone network of an original YOLOv8n model, and a CBFuse module and a CBLinear module are introduced for feature fusion between different branches; a feature aggregation and calibration pyramid network is introduced, multi-scale feature fusion is carried out through an up-sampling module, a down-sampling module and a feature aggregation and calibration module, and the feature aggregation and calibration module carries out feature calibration and enhancement through a local attention mechanism, a global attention mechanism and a pixel attention mechanism; an adaptive task alignment detection head is introduced to execute a dynamic convolution mechanism, a task decomposition mechanism and a dynamic feature alignment mechanism; an improved YOLOv8n model is formed based on the improvement and serves as a foggy day pedestrian detection network model; according to the method, the detection accuracy and stability of the network in processing shielded and background complex images can be enhanced, and the boundary and detail features of a fuzzy target can be extracted more accurately in low-visibility environments such as foggy days and the like.
Need to check novelty before this filing date? Find Prior Art