From last decade, Safety plays a major role in automobile industry, which results in the invention of various safety measures such as air bags, central locking system, automatic breaking system, traffic signal detection etc. In such case pedestrian detection in night vision is one of the vital issues in advanced driving assistance systems. The main aim of the night vision systems is to avoid collision of vehicles with the pedestrians while driving on roads. It is very much important in night time, due to the varying light conditions it is very difficult to detect a pedestrian. With the presentation of night vision systems another sort of driver support is achieved, which can compensate the weaknesses of the human visual system after shutdown of sunlight. A NIR (Near Infrared) camera is used in this system to take images of a night scene. As there are large intra class variations in the pedestrian poses, a tree structured classifier is proposed here to handle the problem by training it with different subset of images and different sizes. This research work discusses about combination of Haar-Cascade and HOG-SVM (Histogram of Oriented Gradients-Support Vector Machine) for classification and validation. Haar-Cascade is trained such that to classify the full body of humans which eliminates most of the non-pedestrian regions. For refining the pedestrians after detection, a part based SVM classifier with HOG features is used. Upper and lower body part HOG features of the pedestrians are used for part based validation of detected bounding boxes. A full body validation scheme is also implemented using HOG-SVM when any one of the part based validation does not validate that particular part. Combination of the different types of complementary features yields better results. Experiments on test images determines that the proposed pedestrian detection system has a high detection rate and low false alarm rate since it works on part based validation process.
展开▼
