Abstract
The notion of pedestrian detection is used in computer vision, which not only detects humans but also counts the numbers of pedestrians and determines their movement in real time. This technique is used in many applications such as surveillance, advanced robotics, intelligent vehicles and Advanced Driver Assistance Systems (ADAS). The pedestrian detection system needs acceleration to enable real-time adaptive processing. Hardware acceleration has the potential to speedup these algorithms, making real-time processing for many image and video processing. In order to meet the real-time requirement, high-speed pedestrian detection architecture must be designed carefully.
This paper presents a pedestrian detection application for Advanced Driver Assistance Systems based on a Deep Learning algorithm. It's about proposing a structure of a Deep Learning model which makes it possible to improve the precisions existing in the state-of-the-art and the processing time by images. This is a very difficult problem because of the complexity of the task and the challenges presented by the detection of humans in general.