Next Article in Journal
TY-SpectralNet: An Interpretable Adaptive Network for the Pattern of Multimode Fiber Spectral Analysis
Previous Article in Journal
Academic Level as a Moderator in University Students’ Acceptance of Educational AI Chatbots: An Extended TAM3 Model
Previous Article in Special Issue
Benchmarking Anomaly Detection Methods for Extracardiac Findings in Cardiac MRI
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Article

Adaptive Energy–Gradient–Contrast (EGC) Fusion with AIFI-YOLOv12 for Improving Nighttime Pedestrian Detection in Security

1
School of Electronic and Optical Engineering, Nanjing University of Science and Technology Zijin College, Nanjing 210023, China
2
School of Electronic and Optical Engineering, Nanjing University of Science and Technology, Nanjing 210094, China
*
Author to whom correspondence should be addressed.
Appl. Sci. 2025, 15(19), 10607; https://doi.org/10.3390/app151910607
Submission received: 3 September 2025 / Revised: 25 September 2025 / Accepted: 29 September 2025 / Published: 30 September 2025
(This article belongs to the Special Issue Advanced Image Analysis and Processing Technologies and Applications)

Abstract

In security applications, visible-light pedestrian detectors are highly sensitive to changes in illumination and fail under low-light or nighttime conditions, while infrared sensors, though resilient to lighting, often produce blurred object boundaries that hinder precise localization. To address these complementary limitations, we propose a practical multimodal pipeline—Adaptive Energy–Gradient–Contrast (EGC) Fusion with AIFI-YOLOv12—that first fuses infrared and low-light visible images using per-pixel weights derived from local energy, gradient magnitude and contrast measures, then detects pedestrians with an improved YOLOv12 backbone. The detector integrates an AIFI attention module at high semantic levels, replaces selected modules with A2C2f blocks to enhance cross-channel feature aggregation, and preserves P3–P5 outputs to improve small-object localization. We evaluate the complete pipeline on the LLVIP dataset and report Precision, Recall, mAP@50, mAP@50–95, GFLOPs, FPS and detection time, comparing against YOLOv8, YOLOv10–YOLOv12 baselines (n and s scales). Quantitative and qualitative results show that the proposed fusion restores complementary thermal and visible details and that the AIFI-enhanced detector yields more robust nighttime pedestrian detection while maintaining a competitive computational profile suitable for real-world security deployments.
Keywords: multimodal image fusion; energy–gradient–contrast fusion (EGC); AIFI attention; yolov12; nighttime pedestrian detection multimodal image fusion; energy–gradient–contrast fusion (EGC); AIFI attention; yolov12; nighttime pedestrian detection

Share and Cite

MDPI and ACS Style

Wang, L.; Bao, Z.; Lu, D. Adaptive Energy–Gradient–Contrast (EGC) Fusion with AIFI-YOLOv12 for Improving Nighttime Pedestrian Detection in Security. Appl. Sci. 2025, 15, 10607. https://doi.org/10.3390/app151910607

AMA Style

Wang L, Bao Z, Lu D. Adaptive Energy–Gradient–Contrast (EGC) Fusion with AIFI-YOLOv12 for Improving Nighttime Pedestrian Detection in Security. Applied Sciences. 2025; 15(19):10607. https://doi.org/10.3390/app151910607

Chicago/Turabian Style

Wang, Lijuan, Zuchao Bao, and Dongming Lu. 2025. "Adaptive Energy–Gradient–Contrast (EGC) Fusion with AIFI-YOLOv12 for Improving Nighttime Pedestrian Detection in Security" Applied Sciences 15, no. 19: 10607. https://doi.org/10.3390/app151910607

APA Style

Wang, L., Bao, Z., & Lu, D. (2025). Adaptive Energy–Gradient–Contrast (EGC) Fusion with AIFI-YOLOv12 for Improving Nighttime Pedestrian Detection in Security. Applied Sciences, 15(19), 10607. https://doi.org/10.3390/app151910607

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop