Computer Vision for Detecting Potholes in Asphalt Roads in Real-Time using RC Car

Developed and trained a Convolutional Neural Network (CNN) based on the AlexNet architecture for real-time detection of potholes in asphalt roads, achieving 92.15% accuracy, 91.38% sensitivity, and an F-score of 96.52%. Optimized the model using high-performance GPUs for deployment in real-time systems.

The project involved preprocessing a large dataset of road images and implementing an image analysis pipeline to detect surface anomalies. Collaborated with a cross-disciplinary team to integrate the CNN model with a remote-controlled car for real-world validation, ensuring low-latency response times in dynamic environments.