Thermal Detection of People with Mobility Restrictions for Barrier Reduction at Traffic Lights Controlled Intersections

Rapid advances in deep learning for computer vision have driven the adoption of RGB camera-based adaptive traffic light systems to improve traffic safety and pedestrian comfort. However, these systems often overlook the needs of people with mobility restrictions. Moreover, the use of RGB cameras presents significant challenges, including limited detection performance under adverse weather or low-visibility conditions, as well as heightened privacy concerns. To address these issues, we propose a fully automated, thermal detector-based traffic light system that dynamically adjusts signal durations for individuals with walking impairments or mobility burden and triggers the auditory signal for visually impaired individuals, thereby advancing towards barrier-free intersection for all users. To this end, we build the thermal dataset for people with mobility restrictions (TD4PWMR), designed to capture diverse pedestrian scenarios, particularly focusing on individuals with mobility aids or mobility burden under varying environmental conditions, such as different lighting, weather, and crowded urban settings. While thermal imaging offers advantages in terms of privacy and robustness to adverse conditions, it also introduces inherent hurdles for object detection due to its lack of color and fine texture details and generally lower resolution of thermal images. To overcome these limitations, we develop YOLO-Thermal, a novel variant of the YOLO architecture that integrates advanced feature extraction and attention mechanisms for enhanced detection accuracy and robustness in thermal imaging. Experiments demonstrate that the proposed thermal detector outperforms existing detectors, while the proposed traffic light system effectively enhances barrier-free intersection. The source codes and dataset are available at https://github.com/leon2014dresden/YOLO-THERMAL.

Vision-based Warning System for Maintenance Personnel on Short-Term Roadwork Site

We propose a vision-based warning system for the maintenance personnel working on short-term construction sites. Traditional solutions use passive protection, like setting up traffic cones, safety beacons, or even nothing. However, such methods cannot function as physical safety barriers to separate working areas from used lanes. In contrast, our system provides active protection, leveraging acoustic and visual warning signals to help road workers be cautious of approaching vehicles before they pass the working area. To decrease too many warnings to relieve a disturbance of road workers, we implemented our traffic flow check algorithm, by which about 80% of the useless notices can be filtered. We conduct the evaluations in laboratory conditions and the real world, proving our system's applicability and reliability.