• Rishikesh Phatangare
• Rohit Sanas
• Pranit Yadav

Higher speed increases the likelihood of an accident and speeding is a major cause in approximately a one-third of all traffic fatalities. Not only does speeding cause crashes but it can also make accidents worse when they do happen. The idea is to develop a vehicle speed detection system using video streaming. This system requires a video scene which consists of components like vehicles which are in state of motion, starting point and ending point. The system is designed to detect and track the vehicles to calculate the speed of each vehicle. The idea is to develop a Speed Detection System (SDS) which can be used as an alternative for radar and other existing system. SDS uses several image processing techniques on video stream captured from camera, which makes SDS capable of calculating the speed of moving objects avoiding the traditional radar problems. SDS process is divided into three phases; first phase is the object detection followed by the object tracking in which the detected vehicle having assigned ID is tracked over frames. From distance and traveled time of detected vehicle, speed of that vehicle is determined.

Keywords = Image processing, Camera, Object Recognition, Object tracking.

"SPEED DETECTION USING BACK-TRACKING ALGORITHM ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 4, page no.122-124, April-2019, Available :http://www.jetir.org/papers/JETIR1904625.pdf

"SPEED DETECTION USING BACK-TRACKING ALGORITHM ", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 4, page no. pp122-124, April-2019, Available at : http://www.jetir.org/papers/JETIR1904625.pdf