Search

Instead of using global-appearance information for visual tracking, as adopted by many methods, we propose a tracking-by-parts (TBP) approach that uses partial appearance information for the task. The proposed method considers the collaborations between parts and derives a probability propagation framework by encoding the spatial coherence in a Bayesian formulation. To resolve this formulation, a TBP particle-filtering method is introduced. Unlike existing methods that only use the spatial-coherence relationship for particle-weight estimation, our method further applies this relationship for state prediction based on system dynamics. Thus, the part-based information can be utilized efficiently, and the tracking performance can be improved. Experimental results show that our approach outperforms the factored-likelihood and particle reweight methods, which only use spatial coherence for weight estimation. Index Terms--Component collaboration, contrast histogram, particle filtering, tracking by parts (TBP), visual tracking.

To link to full-text access for this article, visit this link: http://dx.doi.org/10.1016/j.sysarc.2008.09.002 Byline: Neng-Chung Wang (a), Yi-Ping Hung (b) Keywords: Hamiltonian cycle; Multicast; Parallel computing; Torus networks; Wormhole routing Abstract: In this paper, we propose an efficient multipath multicast routing algorithm in wormhole-routed 2D torus networks. We first introduce a hamiltonian cycle model for exploiting the feature of torus networks. Based on this model, we find a hamiltonian cycle in torus networks. Then, an efficient multipath multicast routing algorithm with hamiltonian cycle model (mulitpath-HCM) is presented. The proposed multipath multicast routing algorithm utilizes communication channels more uniformly in order to reduce the path length of the routing messages, making the multicasting more efficient. Simulation results show that the multicast latency of the proposed multipath-HCM routing algorithm is superior to that of fixed and dual-path routing algorithms. Author Affiliation: (a) Department of Computer Science and Information Engineering, National United University, Miao-Li 360, Taiwan, ROC (b) Department of Computer Science and Information Engineering, Chaoyang University of Technology, Taichung 413, Taiwan, ROC Article History: Received 1 September 2006; Revised 19 April 2008; Accepted 18 September 2008

In this letter, we propose a Bayesian approach to video object segmentation. Our method consists of two stages. In the first stage, we partition the video data into a set of three-dimensional (3-D) watershed volumes, where each watershed volume is a series of corresponding two-dimensional (2-D) image regions. These 2-D image regions are obtained by applying to each image frame the marker-controlled watershed segmentation, where the markers are extracted by first generating a set of initial markers via temporal tracking and then refining the markers with two shrinking schemes: the iterative adaptive erosion and the verification against a presimplified watershed segmentation. Next, in the second stage, we use a Markov random field to model the spatio-temporal relationship among the 3-D watershed volumes that are obtained from the first stage. Then, the desired video objects can be extracted by merging watershed volumes having similar motion characteristics within a Bayesian framework. A major advantage of this method is that it can take into account the global motion information contained in each watershed volume. Our experiments have shown that the proposed method has potential for extracting moving objects from a video sequence. Index Terms--Markov random field, three-dimensional (3-D) watershed volume, video object segmentation, watershed segmentation.

In this paper, we show how an active binocular head, the IIS head, can be easily calibrated with very high accuracy. Our calibration method can also be applied to many other binocular heads. In addition to the proposal and demonstration of a four-stage calibration process, there are three major contributions in this paper. First, we propose a motorized-focus lens (MFL) camera model which assumes constant nominal extrinsic parameters. The advantage of having constant extrinsic parameters is to having a simple head/eye relation. Second, a calibration method for the MFL camera model is proposed in this paper, which separates estimation of the image center and effective focal length from estimation of the camera orientation and position. This separation has been proved to be crucial; otherwise, estimates of camera parameters would be very noise-sensitive. Thirdly, we show that, once the parameters of the MFL camera model is calibrated, a nonlinear recursive least-square estimator can be used to refine all the 35 kinematic parameters. Real experiments have shown that the proposed method can achieve accuracy of one pixel prediction error and 0.2 pixel epipolar error, even when ali the joints, including the left and right focus motors, are moved simultaneously. This accuracy is good enough for many three-dimensional (3-D) vision applications, such as 3-D navigation, 3-D object tracking, and even 3-D reconstruction. Index Terms - Active vision, binocular head, head calibration, head/eye calibration, motorized lens calibration.

This paper proposes a new closed-form solution for identifying the kinematic parameters of an active binocular head having four revolute joints and two prismatic joints by using three-dimensional (3-D) point (position) measurements of a calibration point. Since this binocular head is composed of off-the-shelf components, its kinematic parameters are unknown. Therefore, we can not directly apply those existing nonlinear optimization methods. Even if we want to use the nonlinear optimization methods, a closed-form solution can be first applied to obtain accurate enough initial values. Hence, this paper considers only methods that provide closed-form solutions, i.e., those requiring no initial estimates. Notice that most existing closed-form solutions require pose (i.e., both position and orientation) measurements. However, as far as we know, there is no inexpensive technique which can provide accurate pose measurements. Therefore, existing closed-form solutions based on pose measurements can not give us the required accuracy. As a result, we have developed a new method that does not require orientation measurements and can use only the position measurements of a calibration point to obtain highly accurate estimates of kinematic parameters using closed-form solutions. The proposed method is based on the complete and parametrically continuous (CPC) kinematic model, and can be applied to any kind of kinematic parameter identification problems with or without multiple end-effectors, providing that the links are rigid, the joints are either revolute or prismatic and no closed-loop kinematic chain is included. Simulations and real experiments have shown that the proposed method of using only point measurements is more robust against noise than those existing closed-form solutions using both position and orientation measurements when calibrating our binocular head. Index Terms - Active vision, binocular head, kinematic calibration, three-dimensional (3-D) circle fitting, 3-D line fitting.

The paper by Zhuang and Roth presents a linear solution to kinematic parameter identification of robot manipulators. With their method, the orientation parameters for all revolute joints have to be solved first before solving for the translation parameters for all revolute joints and the orientation parameters for all prismatic joints simultaneously. Our major modification here is to decompose the kinematic parameters estimation problem into many subproblems of a single joint axis such that the complexity is reduced and easier implementation is derived. In addition, this gives a unified solution for any serial manipulator with an arbitrary combination of prismatic and revolute joints.

In this paper, we propose a new method, the RANSAC-based DARCES method, which can solve the partially overlapping 3D registration problem without any initial estimation. For the noiseless case, the basic algorithm of our method can guarantee that the solution it finds is the true one, and its time complexity can be shown to be relatively low. An extra characteristic is that our method can be used even for the case that there are no local features in the 3D data sets. Index Terms--Computer vision, range data, range image, registration, 3D imaging.

It has been possible to develop a fast new algorithm based on the winner-update strategy which uses an ascending lower bound list of the matching error to ascertain the temporary winner. It is demonstrated that the proposed winner-update algorithm can save 91.6% to 98% of the absolute operations required by the FS algorithm.

An adaptive signal smoothing approach based on vertically invariant morphological (MV) openings and closings has been developed. The method involves the use of vertically invariant morphological filters for time-varying or adaptive signal processing. Vertically invariant openings and closings, which were the morphological filters used, have intuitive geometric interpretations and give different filtering scales with respect to different spacial positions. The results showed that the approach can eliminate noises without oversmoothing the important features of a signal.