Authors - Mandala Nagarjuna Naidu, Bandi Hemalatha, Kadavakallu Viswanath, Kotapati Venkata Pavan, Ms.Ragavarthini Abstract - Autonomous vehicles rely on powerful perception systems with real-time object detection and tracking capabilities. Our paper presents a unified deep learning framework based on YOLOv8n and ByteTrack for multi-class detection of vehicles, pedestrians, traffic signs and lights on roads. Our work maintains consistent tracking between frames without the limitations of previous works that rely on static images or single-object-type detection. The lightweight model, with only 3.2 million parameters in YOLOv8n, provides a good trade-off between accuracy and efficiency for embedded automotive hardware. Experiments conducted on the COCO validation dataset, achieving 52.11% mAP @ 0.5,with precision and recall values of 63.42% and 47.44% respectively.It runs real-time on traffic videos with an average frame rate of 62 FPS and a mean inference time of 10.10 ms.Results for tests on traffic videos show, on average 10.15 objects detected with 68.29% confidence.These findings make this approach apt for both autonomous navigation and intelligent traffic monitoring.
Open Zoom