HOPNet: Heterogeneous Object Priority Network for Unusual Object Detection in Mixed Traffic
Power System Technology · 23.05.2026 · 50 (2) · 926-939
DOI: 10.52783/pst.3468 ↗Kurz gefasst
Fachartikel in der Zeitschrift Power System Technology, online erschienen am 23.05.2026. Verfasst von Abha Sharma und 1 weiteren Autor:innen.
Abstract (Originalsprache)
Indian roads present one of the world's most heterogeneous and unstructured traffic environments, simultaneously accommodating motorized vehicles, e-rickshaws, bicycles, pedestrians, and free-roaming animals without strict lane discipline. Autonomous vehicle (AV) perception systems trained primarily on Western datasets fail catastrophically in such mixed-traffic scenarios. This paper proposes HOPNet (Heterogeneous Object Priority Network), a multi-modal real-time object detection framework integrating YOLOv8-based convolutional neural networks with Swin Transformer attention, camera-LiDAR fusion, and domain-adaptive transfer learning. HOPNet is trained and evaluated on the Indian Traffic Dataset (ITD), a novel dataset of 180,000+ annotated images collected from twelve Indian cities. Experimental results demonstrate a mean Average Precision (mAP@0.5) of 91.4%, surpassing the best baseline (YOLOv7) by 11.1%, with a detection latency of 28 ms on NVIDIA Jetson AGX Xavier edge hardware. Per-class analysis shows particularly significant improvements for underrepresented categories: monkey (+27.6%), goat/sheep (+26.2%), street dog (+21.9%), and loaded bicycle (+18.5%). The proposed Contextual Risk Scoring Module (CRSM) enables priority-based AV decision-making for safety-critical unusual objects. DOI: DOI : https://doi.org/10.52783/pst.3468
Zitieren
APA
Sharma, A., & Joshi, A. (2026). HOPNet: Heterogeneous Object Priority Network for Unusual Object Detection in Mixed Traffic. Power System Technology, 50(2), 926-939. https://doi.org/10.52783/pst.3468
Vancouver
Sharma A, Joshi A. HOPNet: Heterogeneous Object Priority Network for Unusual Object Detection in Mixed Traffic. Power System Technology. 2026;50(2):926-939. doi:10.52783/pst.3468
BibTeX
@article{Sharma2026,
author = {Sharma, Abha and Joshi, Ankush},
title = {HOPNet: Heterogeneous Object Priority Network for Unusual Object Detection in Mixed Traffic},
journal = {Power System Technology},
year = {2026},
volume = {50},
number = {2},
pages = {926--939},
doi = {10.52783/pst.3468}
}
EUVIMED