Dae Youn Lee

SOWP: Spatially Ordered and Weighted Patch Descriptor for Visual Tracking

A simple yet effective object descriptor for visual tracking is proposed in this paper. We first decompose the bounding box of a target object into multiple patches, which are described by color and gradient histograms. Then, we concatenate the features of the spatially ordered patches to represent the object appearance. Moreover, to alleviate the impacts of background information possibly included in the bounding box, we determine patch weights using random walk with restart (RWR) simulations. The patch weights represent the importance of each patch in the description of foreground information, and are used to construct an object descriptor, called spatially ordered and weighted patch (SOWP) descriptor. We incorporate the proposed SOWP descriptor into the structured output tracking framework. Experimental results demonstrate that the proposed algorithm yields significantly better performance than the state-of-the-art trackers on a recent benchmark dataset, and also excels in another recent benchmark dataset.

Visual Tracking Using Pertinent Patch Selection and Masking

A novel visual tracking algorithm using patch-based appearance models is proposed in this paper. We first divide the bounding box of a target object into multiple patches and then select only pertinent patches, which occur repeatedly near the center of the bounding box, to construct the foreground appearance model. We also divide the input image into non-overlapping blocks, construct a background model at each block location, and integrate these background models for tracking. Using the appearance models, we obtain an accurate foreground probability map. Finally, we estimate the optimal object position by maximizing the likelihood, which is obtained by convolving the foreground probability map with the pertinence mask. Experimental results demonstrate that the proposed algorithm outperforms state-of-the-art tracking algorithms significantly in terms of center position errors and success rates.

Multihypothesis trajectory analysis for robust visual tracking

The notion of multihypothesis trajectory analysis (MTA) for robust visual tracking is proposed in this work. We employ multiple component trackers using texture, color, and illumination invariant features, respectively. Each component tracker traces a target object forwardly and then backwardly over a time interval. By analyzing the pair of the forward and backward trajectories, we measure the robustness of the component tracker. To this end, we extract the geometry similarity, the cyclic weight, and the appearance similarity from the forward and backward trajectories. We select the optimal component tracker to yield the maximum robustness score, and use its forward trajectory as the final tracking result. Experimental results show that the proposed MTA tracker improves the robustness and the accuracy of tracking, outperforming the state-of-the-art trackers on a recent benchmark dataset.

Progressive compression of 3D triangular meshes using topology-based Karhunen-Loève transform

In this work, we propose a progressive compression algorithm using topology-based Karhunen-Loeve transform(KLT). First, we simplify an input mesh to represents an original mesh in several level of details. Then, coordinates of decimated vertices at each level are predicted from the coarser level mesh, and the prediction residuals are transmitted to a decoder. To provide high coding efficiency, we apply the topology-based KLT, which compacts the energy into a few coefficients, to the prediction residuals. Moreover, we develop a bit plane coder, which uses a context-adaptive arithmetic coder, for the entropy coding. Experiments on various 3D meshes show that the proposed algorithm provides enhanced compression performance.

R-D optimized progressive compression of 3D meshes using prioritized gate selection and curvature prediction

A rate-distortion (R-D) optimized progressive coding algorithm for three-dimensional (3D) meshes is proposed in this work. We propose the prioritized gate selection and the curvature prediction to improve the connectivity and geometry compression performance, respectively. Furthermore, based on the bit plane coding, we develop a progressive transmission method, which improves the qualities of intermediate meshes as well as that of the fully reconstructed mesh, and extend it to the view-dependent transmission method. Experiments on various 3D mesh models show that the proposed algorithm provides significantly better compression performance than the conventional algorithms, while supporting progressive reconstruction efficiently.

Fast background subtraction algorithm using two-level sampling and silhouette detection

An efficient background subtraction algorithm using two-level sampling and silhouette detection is proposed in this work. In the two-level sampling, we identify moving objects at the block level and then at the pixel level. Then, in the silhouette detection, around each sampled foreground pixel, we refine the shapes of foreground objects. We also develop two fast modes for the silhouette detection, which utilizes the spatio-temporal coherence of moving foreground objects. Simulation results demonstrate that the proposed algorithm provides accurate segmentation results without flickering artifacts, while requiring a low computational load.

3D mesh compression based on dual-ring prediction and MMSE prediction

A three-dimensional (3D) mesh compression algorithm based on novel prediction methods and a mode decision scheme is proposed in this work. After decomposing an input mesh into base and refinement layers, we segment the geometry data of each layer into clusters. To encode vertex positions efficiently, we propose two prediction methods: the dual ring prediction and the minimum mean square error (MMSE) prediction. Also, we develop a mode decision scheme that selects the best prediction mode for each cluster. Simulation results demonstrate that the proposed algorithm provides significantly better compression performance than conventional techniques.

Fast object tracking using color histograms and patch differences

A fast visual object tracking algorithm using novel object appearance models is proposed in this work. We develop a color histogram model and a patch difference model to extract color and texture feature vectors, respectively. Then, we apply k-nearest neighbor classifiers to the color and texture feature vectors and obtain the foreground probability map. We then perform a hierarchical mean shift process on the map to identify the object window. Experimental results demonstrate that proposed algorithm outperforms the conventional algorithms in terms of both tracking accuracy and processing speed.

High quality video acquisition and segmentation using alternate flashing system

A high quality video acquisition algorithm is proposed in this work.We construct a flashing system to capture lit and unlit frames alternately. We develop a reliable motion estimation scheme, which matches correspondences between an unlit frame and a lit frame. Then, we construct a high quality frame, which combines natural scene mood in the unlit frame and textural details in the lit frame. Furthermore, we propose an object segmentation algorithm based on the observation that foreground objects are more sensitive to flash lights than backgrounds. Simulation results demonstrate that the proposed algorithm can acquire high quality video sequences and segment foreground objects from the sequences efficiently.