Abstract: Efficient and instant recognition of pedestrian moving across road by vehicle’s ECU system is very challenging and it is crucial. As the shape features of on-road pedestrians are irregular and complex, and the computation for detection is very complex. To resolve this challenge, we propose fast pedestrian detection algorithms based on histogram of oriented gradients (HOGs), and support vector machines (SVMs). This technique is evaluated and implemented in on any embedded systems which can communicate with vehicle ECU and make the detection of pedestrian with the required action to avoid collision. This approach is improvised for this challenge.

Keywords: Pedestrian collision, Application of HOG, Accident avoidance.