Seungwoo Yoo

Background subtraction using hybrid feature coding in the bag-of-features framework

Although numerous algorithms have been proposed for background subtraction with demonstrated success, it remains a challenging problem. One of the main reasons is the lack of effective background model to account for the complex variations of backgrounds. Although researchers have strived to obtain a background model effectively attenuating false positives from dynamic background variations, their methods are still sensitive to structured motion patterns of background (e.g., waving leaves, rippling water, spouting fountain, etc.). In this paper, inspired by the bag-of-features framework, we present a simple, novel, yet powerful approach for background subtraction. It relies on the hypothesis that texture variations in the background scenes can be well attenuated by effectively encoding the local color and texture information. Specifically, the proposed method adopts joint domain-range features, which are encoded in the soft-assignment coding procedure. We also propose a novel method for deciding the appropriate kernel variances in the soft-assignment coding, which result in strong adaptability and robustness to dynamic scenes compared to employing fixed kernel variances. Experimental results demonstrate that our proposed method is able to handle severe textural variations of backgrounds and perform favorably against the state-of-the-art methods.

Saliency Combined Particle Filtering for Aircraft Tracking

Vision-based aircraft tracking has been considered for emerging real-world applications, such as collision avoidance, air traffic surveillance, and target tracking for military use. However, conventional tracking methods often fail in following aircraft due to 1) variations of object shape, 2) continuously varying background, and 3) unpredictable flight motion. In this paper, we address the problems of vision-based aircraft tracking. To this ends, we propose a principled manner of improving color-based tracking algorithm by combining a biologically inspired saliency feature. More specifically, we exploit the integration of color distributions into particle filtering, which is a Monte Carlo method for general nonlinear filtering problems. To overcome the varying appearances which are usually from changing illumination and pose conditions, we update the target color model. Furthermore, we adopt a structure tensor based saliency algorithm to incorporate the saliency features into particle filter framework, which results in robustly assigning appropriate particle weights even in complex backgrounds. The rationale behind our approach is that color and saliency information are complementary, both mutually fulfilling and completing each other, especially when tracking aircraft in a harsh environment. Tests on real flight sequences reveal that the proposed system yields convincing tracking outcomes under both variations of background and sudden target motion changes.

Estimating Scene-Oriented Pseudo Depth With Pictorial Depth Cues

Estimating depth information from a single image has recently attracted great attention in 3D-TV applications, such as 2D-to-3D conversion owing to an insufficient supply of 3-D contents. In this paper, we present a new framework for estimating depth from a single image via scene classification techniques. Our goal is to produce perceptually reasonable depth for human viewers; we refer to this as pesudo depth estimation. Since the human visual system highly relies on structural information and salient objects in understanding scenes, we propose a framework that combines two depth maps: initial pseudo depth map (PDM) and focus depth map. We use machine learning based scene classification to classify the image into one of two classes, namely, object-view and non-object-view. The initial PDM is estimated by segmenting salient objects (in the case of object-view) and by analyzing scene structures (in the case of non-object-view). The focus blur is locally measured to improve the initial PDM. Two depth maps are combined, and a simple filtering method is employed to generate the final PDM. Simulation results show that the proposed method outperforms other state-of-the-art approaches for depth estimation in 2D-to-3D conversion, both quantitatively and qualitatively. Furthermore, we discuss how the proposed method can effectively be extended to image sequences by employing depth propagation techniques.

A novel monochromatic cue for detecting regions of visual interest

Abstract Finding regions of interest (ROIs) is a fundamentally important problem in the area of computer vision and image processing. Previous studies addressing this issue have mainly focused on investigating chromatic cues to characterize visually salient image regions, while less attention has been devoted to monochromatic cues. The purpose of this paper is the study of monochromatic cues, which have the potential to complement chromatic cues, for the detection of ROIs in an image. This paper first presents a taxonomy of existing ROI detection approaches using monochromatic cues, ranging from well-known algorithms to the most recently published techniques. We then propose a novel monochromatic cue for ROI detection. Finally, a comparative evaluation has been conducted on large scale challenging test sets of real-world natural scenes. Experimental results demonstrate that the use of our proposed monochromatic cue yields a more accurate identification of ROIs. This paper serves as a benchmark for future research on this particular topic and a steppingstone for developers and practitioners interested in adopting monochromatic cues to ROI detection systems and methodologies.