Real-time pedestrian detection technique for embedded driver assistance systems

Fast detection of pedestrians moving across the roads is a big challenge for in-vehicle embedded systems. Because the shape features of on-road pedestrians are irregular and complex, so that the detection techniques cost large computational resources. However, the in-vehicle embedded systems only have limited computational resources. To resolve this challenge, we propose fast pedestrian detection algorithms based on histogram of oriented gradients (HOGs), and support vector machines (SVMs). The proposed techniques are evaluated and implemented on a digital signal processing (DSP) based embedded platform. The experimental results demonstrate that the proposed detection techniques can provide high computational efficiency and detection accuracy.