Search

In this paper, we present an adaptive foreground object extraction algorithm for real-time video surveillance, in conjunction with a human detection technique applied in the extracted foreground regions by using AdaBoost learning algorithm and Histograms of Oriented Gradient (HOG) descriptors. Furthermore, a RANSAC-based temporal tracking algorithm is also applied to refine and trace the detected human windows in order to increase the detection accuracy and reduce the false alarm rate. The traditional background subtraction technique usually cannot work well for situations with lighting variations in the scene. The proposed algorithm employs a two-stage foreground/background classification procedure to perform background subtraction and remove the undesirable subtraction results due to shadow, automatic white balance, and sudden illumination change. Experimental results on some real surveillance video are shown to demonstrate the good performance of the proposed adaptive foreground extraction algorithm under a variety of different environments with lighting variations and human detection system. [ABSTRACT FROM AUTHOR]

In this paper, we propose an algorithm for camera calibration from silhouettes under circular motion with an unknown constant interval angle. Unlike previous silhouette-based methods based on surface of revolution, the proposed algorithm can be applied to sparse and incomplete image sequences. Under the assumption of circular motion with a constant interval angle, epipoles of successive image pairs remain constant and can be determined from silhouettes. A pair of epipoles formed by a certain interval angle can provide a constraint on the angle and focal length. With more pairs of epipoles recovered, the focal length can be determined from the one that most satisfies the constraints and determine the interval angle concurrently. The rest of camera parameters can be recovered from image invariants. Finally, the estimated parameters are optimized by minimizing the epipolar tangency constraints. Experimental results on both synthetic and real images are shown to demonstrate its performance. [ABSTRACT FROM AUTHOR]

The hydraulic servo-valve is the key component of the electro-hydraulic system. But it is difficult to diagnose faults in a hydraulic servo-valve. In this paper, a Genetic Algorithm-based Artificial Neural Network model for fault diagnosis in hydraulic servo-valves is proposed. We use a known set of servo-valve faults as the outputs to the valve-behavior model. Adoption of this approach brings about the advantages of reducing training time and increasing accuracy when compared with the traditional Back Propagation Neural Network. [ABSTRACT FROM AUTHOR]

Regarding the modeling aspects of computer animation, the skeletal animation is a newfangled modeling technology to assist in single-mesh model animation. There are two aspects of advancement proposed in this paper. First, we construct a novel vertical data structure (Modified Body-Tree) to describe the skeletal models in animation. Second, instead of normal methods such as linear interpolation and higher-order spline interpolation to generate in-between frame, we proposes an adaptive and high-performance algorithm based on 4-Point subdivision scheme to generate in-between frame in the skeletal animation. By this advanced algorithm, a smoother skeletal animation with blander vision effect is achieved. Keywords: skeletal animation, in-between frame, 4-Point subdivision, Modified Body-Tree, space displacement. [ABSTRACT FROM AUTHOR]

This paper gives a mathematical description of the undirected network capacity definitions and theorems of computing capacities towards the network. Prove of the theorem correctness is also given. According to them, the paper proposes an algorithm of computing the undirected network capacities based on spanning tree and even an advanced optimization algorithm. In addition, it discusses network capacity expansion problems with constraints. And then, the optimization algorithm in the scenario of undirected network with limited costs is outlined, whose feasibility and process are illustrated via examples. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel paired feature learning system for relevance feedback based image retrieval. To facilitate density estimation in our feature learning system, we employ an ID3-like balance tree quantization method to preserve most discriminative information. In addition, we map all training samples in the relevance feedback onto paired feature spaces to enhance the discrimination power of feature representation. Furthermore, we replace the traditional binary classifiers in the AdaBoost learning algorithm by Bayesian weak classifiers to improve its accuracy, thus producing stronger classifiers. Experimental results on content-based image retrieval show improvement of each step in the proposed learning system. [ABSTRACT FROM AUTHOR]