Moving Object Localization Using Optical Flow for Pedestrian Detection from a Moving Vehicle

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.

Generalized dynamic object removal for dense stereo vision based scene mapping using synthesised optical flow

“…The same limitation is found with detection driven techniques to identify all objects that could be in motion (e.g. car, trucks, bicycles and pedestrians [12]). However such detection based approaches are limited by their generality (in detecting people, vehicles, bicycles, animals, horse drawn vehicles, prams...…”

“…The dense optical flow map is then used to remap the raw intensity images to the same virtual view point. A 2D projective transform, [16,17,12], does not take into account the 3D nature of the scene. By contrast, our approach uses full scene structure and camera motion information to re-project a 2D image with full 3D constraints.…”

“…This approach is insufficient by the fact that a homography transform is a 2D projective transform and does not take into account the 3D nature of the scene. [12] attempts to solve this by applying multiple homograph transforms to image regions of 14x14 pixels. Accurate dense optical flow techniques [20] required for this level of intensity projection are computationally expensive.…”

A Review of Object Detection and Tracking Methods

“…The two widely used methods are: Lucas-Kanade and Horn-Schunck [5]. Hariyono et al [44]., presented a pedestrian detection method using optical flow to extract a moving object and used HOG features to recognize the object using linear SVM. kim et.…”

Intelligent Pedestrian Detection using Optical Flow and HOG

“…Hariyono et al [43] presented a novel method for moving pedestrian detection through moving camera using motion information and HOG features. After segmenting the regions that represent same motion vectors different moving objects are extracted.…”