Stereo correspondence computes disparity map needed by many high-level computer vision tasks. Recently local stereo approaches show their ability matching global while keeping efficiency. But it still deserves further research for higher performance. In this paper, we propose a fast edge-aware cost aggregation strategy. It constructs 1D support window based on spatial and gradient information o...

Stereo matching is used in many computer vision applications such as 3D reconstruction, robot navigation, robotic surgery, 3-D video surveillance, and tracking object in 3D space. Real time stereo matching is difficult due to the heavy computation required for matching algorithms. In this paper a CPU/GPU heterogeneous computing platform is used to accelerate the processing and run the system in...

Observers usually cannot discriminate the relative depth of a crowded feature with respect to crowding features about 2 arc min distant if all the features have the same luminance. However, stereo thresholds significantly less than 20 arc sec are obtained when the crowded feature is about twice as luminant as the features crowding it. The thresholds depend only upon the ratio of the luminance o...

We present an experimental study that explores how head tracking and stereo viewing affect user performance when rotating 3D virtual objects using isomorphic and non-isomorphic rotation techniques. Our experiment compares isomorphic with non-isomorphic rotation utilizing four different display modes (no head tracking/no stereo, head tracking/no stereo, no head tracking/stereo, and head tracking...

The omnidirectional vision system has been given increasing attentions in recent years in many engineering research areas such as computer vision and mobile robot since it has wide field of view (FOV). A general method for 360o omnidirectional image acquisition is the catadioptric approach using a coaxially aligned convex mirror and a conventional camera. The catadioptric approach with the conv...

In this work, we introduce a model-based approach to extracting the silhouette of people in motion from stereo video sequences. To this end, we extend a purely stereo-based approach to tracking people proposed in earlier work. This approach is based on an implicit surface model of the body. It lets us accurately predict the silhouette’s location and, therefore, detect them more robustly. In tur...

Fingertip detection and tracking is the foundation of many hand-based natural Human Computer Interaction (HCI) applications. Previous methods either can hardly provide a natural way of interaction, or are too complex to be adopted in practical systems. In this paper, we propose a real-time stereo vision-based fingertip detection and tracking method that works very well in real environment. Our ...

Towed body systems of various configurations have been used for many years to map the seabed. Until recently, single video camera systems were widely used to gather qualitative data, or collect often low-accuracy quantitative data using laser dot patterns projected into the field of view. The introduction of stereo-video systems has enabled the capture of accurate and reliable spatial informati...

Textured surface analysis is essential for many applications. We present a three-dimensional recovery approach for real textured surfaces based on photometric stereo. The aim is to be able to measure the textured surfaces with a high degree of accuracy. For this, we use a color digital sensor and principles of color photometric stereo. This method uses a single color image, instead of a sequenc...

Omni-directional view and stereo information for scene points are both crucial in many computer vision applications. In some demanding applications like autonomous robots, we need to acquire both in real-time without sacrificing too much image resolution. This work describes a novel method to meet all the stringent demands with relatively simple setup and off-the-shelf equipments. Only one simp...