Foreground extraction for freely moving RGBD cameras

Abstract

In this study, the authors propose a novel method to perform foreground extraction for freely moving RGBD cameras. Although the field of foreground extraction or background subtraction has been explored by the computer vision researcher community since a long time, the depth-based subtraction is relatively new and has not been extensively addressed as of yet. Most of the current methods make heavy use of geometric reconstruction, making the solutions quite restrictive. In this study, the authors make a novel use of RGB and depth data: from the RGB frame, they first extract corner features and then represent these features with the histogram of oriented gradients (HoG) descriptor. They then train a non-linear SVM on these HoG descriptors. During the test phase, they make use of the fact that the foreground object has a distinct depth ordering with respect to the rest of the scene. Hence, they use the positively classified features from accelerated segment test (FAST) features on the test frame to initiate a region growing algorithm to obtain an accurate foreground segmentation from the depth data alone. The authors demonstrate the proposed method on six datasets, and demonstrate encouraging quantitative and qualitative results.

A Background Subtraction Algorithm in Complex Environments Based on Category Entropy Analysis

“…For example, Han et al [24] integrated 11 features such as RGB color model and gradient, as well as Haar-like features, in a kernel density framework, and used support vector machines (SVM) to distinguish between the foreground and background. Junejo et al [25] proposed a novel method to perform foreground extraction for freely moving RGBD (depth) cameras. This method used the efficient features from accelerated segment test (FAST) and represented them using the histogram of oriented gradients (HoG) descriptors to learn the foreground object.…”

Background subtraction in dynamic scenes using the dynamic principal component analysis

“…It was motivated by its ability to represent both the motion and appearance. In addition to colour features, depth features have been introduced on many algorithms as in [15] provided that the background and foreground have different depths.…”

Foreground Extraction Combining Graph Cut and Histogram Shape Analysis

“…The foreground, user's interested objects, provides useful information for image analysis and comprehension. Foreground extraction is a task of distinguishing between the specific object and background [1]. Existing methods rely on one or more low-level features, such as the intensity distributions [2], edges, and region connectivity [3], where the overall aim is to achieve an accurate object with minimal user interaction.…”