Abstract
This paper presents a pedestrian detection method from a moving vehicle using optical flows and histogram of oriented gradients (HOG). A moving object is extracted from the relative motion by segmenting the region representing the same optical flows after compensating the egomotion of the camera. To obtain the optical flow, two consecutive images are divided into grid cells 14 × 14 pixels; then each cell is tracked in the current frame to find corresponding cell in the next frame. Using at least three corresponding cells, affine transformation is performed according to each corresponding cell in the consecutive images, so that conformed optical flows are extracted. The regions of moving object are detected as transformed objects, which are different from the previously registered background. Morphological process is applied to get the candidate human regions. In order to recognize the object, the HOG features are extracted on the candidate region and classified using linear support vector machine (SVM). The HOG feature vectors are used as input of linear SVM to classify the given input into pedestrian/nonpedestrian. The proposed method was tested in a moving vehicle and also confirmed through experiments using pedestrian dataset. It shows a significant improvement compared with original HOG using ETHZ pedestrian dataset.
Highlights
Vision-based environment detection methods have been actively developed in robot vision
In order to recognize the object, histogram of oriented gradients (HOG) features were extracted on a candidate region and classified using linear support vector machine (SVM) [5, 14]
The HOG feature vectors are used as an input of linear SVM to classify the given input into pedestrian/nonpedestrian
Summary
Vision-based environment detection methods have been actively developed in robot vision. In the past few years, moving object and pedestrian detection methods for a mobile robot or moving vehicle have been actively developed. For a practical real-time pedestrian detection system, Gavrila and Munder [1] employed hierarchical shape matching to find pedestrian candidates from moving vehicle. Their method uses a multicue vision system for the real-time detection and tracking of pedestrians. Nishida and Kurita [2] applied SVM with the automated selection process of the components by using AdaBoost These researches show that the selection of the components and their combination are important to get a good pedestrian detector
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
