This paper presents an innovative retrofittable advanced driver assistance system (ADAS) that is designed specifically to address the issue of heavy-vehicle blind spots in high-volume traffic conditions. The novel approach uses the DATS_2022 dataset containing Indian traffic scenarios and deploys a YOLOv5 small model on a Jetson Nano developer kit optimized to support real-time object detection. The research specifically addresses the challenges posed by right-hand drive configurations in India, with emphasis on the blind spots towards the left and back sides of the vehicle. It employs a dynamic view-switching functionality in the graphical user interface (GUI), which automatically switches views with alerts to enhance visibility of the left and back blind spots, crucial for right-hand drive configuration of heavy vehicles. The design emphasizes high frame-per-second (FPS) performance, data stream with low latency, as well as depth estimation for alert generation. Furthermore, it comes with a bespoke user interface with a wired interface and an Android App for wireless connection. The YOLOV5 model has achieved an accuracy of 80% while running at an average FPS of 12 on a Jetson Nano 4 GB developer kit.