• Bandari Suchithra
• Patiballa Sri Krishna Chaitanya
• Gorantla Sishir Kumar

Intelligent Transportation Systems (ITS) play a crucial role in enhancing road safety and optimizing traffic management. Central to the effectiveness of these systems is the rapid and accurate detection and classification of traffic light states. This research contributes to the ongoing advancements in computer vision and machine learning within the context of ITS by presenting a novel methodology for real-time traffic light recognition. Leveraging the ResNet (Residual Networks) architecture, our approach addresses the multifaceted challenges presented by diverse environmental conditions, including adverse weather, varying illumination, and occlusions. The ResNet's deep learning capabilities enable our system to discern intricate patterns and features, showcasing its adaptability to the complexities of real-world traffic scenarios. Beyond the technical aspects, the study underscores the significance of accurate traffic light detection and classification. These processes are not merely technical necessities but hold profound implications for optimizing traffic flow, minimizing congestion, and ultimately enhancing road safety within the dynamic landscape of modern urban environments. This research contributes to the broader discourse in computer vision and machine learning, aiming to provide practical solutions for the challenges posed by real-world ITS applications. By emphasizing the importance of accurate traffic light recognition, our study seeks to propel advancements in the field, with potential implications for the development of intelligent traffic management systems that can positively impact urban mobility and safety.

Traffic lights, ResNet, Deep learning, Computer vision.

"Traffic Light Detection and Classification using Resnet", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 4, page no.i219-i224, April-2024, Available :http://www.jetir.org/papers/JETIR2404827.pdf

"Traffic Light Detection and Classification using Resnet", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 4, page no. ppi219-i224, April-2024, Available at : http://www.jetir.org/papers/JETIR2404827.pdf