• Sudharshan S M
• Dr. Kiran A Gupta

Advanced Driver Assistance System (ADAS) is the most researched area in the automobile industry since the last decade. ADAS includes different features that help the driver for a safer and easier driving. In this work, we have designed an ADAS system that incorporates camera and ultrasonic sensors for object detection in real-time. The system has Raspberry Pi 3 model B+ for processing. Single Shot multibox Detector (SSD) algorithm is used for real-time object detection in the video. We have achieved an average precision of about 74.3% at an average of 35fps (frames per second). The ultrasonic sensor (HC-SR04) used at the rear of the vehicle has a precision of 0.1-0.5cm and range between 2cm to 400cm.

Deep learning, SSD, YOLO, real-time video processing, ADAS.

"Design of ADAS for Vehicles using Single-Shot Multibox Detector (SSD)", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 6, page no.1037-1043, June-2019, Available :http://www.jetir.org/papers/JETIR1906581.pdf

"Design of ADAS for Vehicles using Single-Shot Multibox Detector (SSD)", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 6, page no. pp1037-1043, June-2019, Available at : http://www.jetir.org/papers/JETIR1906581.pdf