Learn More
This paper presents a novel Graphics Processing Unit (GPU)-based system for pedestrian detection with stereo vision in real images on mobile robot. The process of obtaining a dense disparity map on a GPU for real-time applications and the edge property of the scene to extract a region of interest (ROI) is designed. After extracting the histograms of the(More)
This paper presents a novel method to recognize the human gesture using binary decision tree and Multi-class Support Vector Machine (MCSVM). In a learning stage, 3D trajectory of the human gesture by a kinect sensor is assigned into the tree node of the binary decision tree according to its distribution property. The user's gesture trajectory is resampled(More)
This paper presents a gesture tracking method using 3D blobs and a skeleton model for interactive application. A disparity map is obtained from stereo matching based on GPGPU and we generate 3D foreground blobs using depth information. The distribution of 3D blobs is applied to determine the human position combined with the face and torso detection. The(More)
This paper presents a novel method to generate an index word for the topological map in robot localization. Previous studies extract only appearance features from an input image to match the visual words of the model images. However, the localization performance is much affected by the miss or false matches. First, we segment a robot navigation environment(More)
This paper presents a novel omnidirectional camera calibration technique based on automatic contour matching. In this proposed method, the initial parameters, translation and rotation, are computed using the epipolar constraint from matched feature points. By using a normal vector to a 3-D plane connecting the contour with the center of the camera(More)
Dense disparity map estimation from a high-resolution stereo image is a very difficult problem in terms of both matching accuracy and computation efficiency. Thus, an exhaustive disparity search at full resolution is required. In general, examining more pixels in the stereo view results in more ambiguous correspondences. When a high-resolution image is(More)
Augmented Reality (AR) has been one of the most important research areas in mobile and interactive application. This paper presents a novel mobile rendering method using the surrounding light sources. The location and color intensity of the environmental light such as a fluorescent lamp is computed with Android mobile device. The proposed system is able to(More)
  • 1