Forward vehicle brake light detection for avoiding road accidents using Yolov7 and IR sensor

This research endeavors to tackle the pressing issue of rear-end collisions by introducing a comprehensive brake light recognition system. The primary focus is on developing a cost-effective and highly accurate solution, leveraging the YOLOv7 algorithm for the classification and detection of rear lights. Complemented by artificial intelligence (AI), the system incorporates an alert warning mechanism to notify distracted drivers promptly. The integration of an infrared (IR) sensor further enhances the system's capabilities, allowing precise measurement of the distance between vehicles. Motivated by the imperative to enhance road safety, the proposed methodology employs deep learning through YOLOv7, facilitating the real-time identification of brake lights. The subsequent application of an artificial intelligent deep learning (AIDL) model ensures proactive alert signals when a distracted driver's vehicle approaches within an extremely short distance (75 cm) of another vehicle. Noteworthy findings underscore the system's effectiveness in monitoring and responding to brake lights, showcasing its potential to prevent collisions from behind. The IR sensor's inclusion refines the precision of the alert system, demonstrating its robust performance in real-world scenarios. Overall, this research contributes a holistic brake light recognition system that combines YOLOv7, AI, and an IR sensor, showcasing its viability in significantly reducing accidents associated with distracted driving and rear-end collisions, thereby emphasizing the critical role of advanced technologies in proactively addressing road safety concerns.