LTV-YOLO: A Lightweight Thermal Object Detector for Young Pedestrians in Adverse Conditions

TL;DR

LTV-YOLO is a lightweight, thermal imaging-based object detection model optimized for real-time identification of young pedestrians in adverse conditions, enhancing safety in autonomous and surveillance systems.

Contribution

The paper introduces a novel thermal-only YOLO-based detector tailored for small, occluded, and young pedestrians, integrating separable convolutions and FPN for efficiency and accuracy.

Findings

Achieves high detection accuracy in low-light and adverse weather conditions.

Maintains real-time performance on edge devices.

Outperforms prior thermal detectors in detecting small and occluded VRUs.

Abstract

Detecting vulnerable road users (VRUs), particularly children and adolescents, in low light and adverse weather conditions remains a critical challenge in computer vision, surveillance, and autonomous vehicle systems. This paper presents a purpose-built lightweight object detection model designed to identify young pedestrians in various environmental scenarios. To address these challenges, our approach leverages thermal imaging from long-wave infrared (LWIR) cameras, which enhances detection reliability in conditions where traditional RGB cameras operating in the visible spectrum fail. Based on the YOLO11 architecture and customized for thermal detection, our model, termed LTV-YOLO (Lightweight Thermal Vision YOLO), is optimized for computational efficiency, accuracy and real-time performance on edge devices. By integrating separable convolutions in depth and a feature pyramid network (FPN), LTV-YOLO achieves strong performance in detecting small-scale, partially occluded, and thermally distinct VRUs while maintaining a compact architecture. This work contributes a practical and scalable solution to improve pedestrian safety in intelligent transportation systems, particularly in school zones, autonomous navigation, and smart city infrastructure. Unlike prior thermal detectors, our contribution is task-specific: a thermally only edge-capable design designed for young and small VRUs (children and distant adults). Although FPN and depthwise separable convolutions are standard components, their integration into a thermal-only pipeline optimized for short/occluded VRUs under adverse conditions is, to the best of our knowledge, novel.