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 cells14×14pixels; 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.

The purpose of this study was to produce a low cost 3D scanner system using a rotating 2D laser scanner. There are two key parameters of this system, the rotation axis and the rotation radius. These two parameters were extracted through a calibration procedure. The calibration requires a planar checkerboard calibration pattern. Several poses were scanned to obtain the observation data. The rotation axis and the rotation radius were extracted by solving a linear equation constructed from a point-plane constraint, where all points lie on a plane and have a zero dot product to the surface normal to the plane. This method was tested on a simulation environment by generating synthetic data of the scanned calibration pattern. A comprehensive analysis was carried out to evaluate the performance of the proposed method. From the simulation results, it was demonstrated that this method achieved highly accurate results with an orientation error of 0.018 degree and a radius error of 0.2 cm.