Safeguarding the Lives of Riders from Crashes using Embedded and Image Processing

In our project we detect the persons who are not wearing helmets, then tracking their number plate and sending warning message to their mobile phones and also to the nearby police station using GSM. New techniques are introduced to detect the objects. The technique combines two methods for helmet detection to achieve better detection rates. The First method is to detect faces using Haar-like features and Background subtraction. Purpose of Haar like features is to meet the real time requirements. The key advantage over most other features is its calculation speed and accuracy. The second method is Circle Hough Transform. The circle Hough Transform (CHT) is a feature extraction technique for detecting circles. It is a specialization of Hough Transform. The purpose of the technique is to find circles in imperfect image inputs. Then the number plate of the rider is notified by the Number Plate Recognition. Number plate recognition (NPR) sensors are embedded camera systems that monitor road traffic. When a vehicle passes by a sensor, the vehicle's number plate, the location, and the time of observation are recorded.