基于双目视觉模型的运动参数测量

通过建立双目测量的数学模型,由标志点在双摄像机成像平面上的坐标求得运动物体的运动参数。在不考虑摄像机内外参数标定误差的情况下,研究了标志点像元的测量精度对运动参数测量的影响。通过分析图像分割求取标志点形心引起的误差,利用窗口中心迭代算法提高标志点形心测量的精度,从而提高了运动参数的测量精度。由空间飞行器自动交会的仿真试验验证了算法的有效性。     

Block-based motion field segmentation for video coding

In the past few years, motion compensation has been widely used in the coding of image sequences. Most of motion estimation and compensation schemes belong to block-based framework. The framework simplifies the complexity of motion estimation, but gives over constraints to the motion field, which results in worse accuracy on the boundary of moving objects. This paper presents a novel technique for raising motion field accuracy. It uses several pre-defined pattern types to segment the motion fields of the previous frame of a sequence. The segmentation is based on the MAP framework that uses iterative method to obtain the solution. In addition, we develop a predictive scheme to predict the location of motion field discontinuities in the current frame, which further reduces the side information for the representation of segmentation.     

Content adaptive video denoising based on human visual perception

In this paper, we propose content adaptive denoising in highly corrupted videos based on human visual perception. We introduce the human visual perception in video denoising to achieve good performance. In general, smooth regions corrupted by noise are much more annoying to human observers than complex regions. Moreover, human eyes are more interested in complex regions with image details and more sensitive to luminance than chrominance. Based on the human visual perception, we perform perceptual video denoising to effectively preserve image details and remove annoying noise. To successfully remove noise and recover the image details, we extend nonlocal mean filtering to the spatiotemporal domain. With the guidance of content adaptive segmentation and motion detection, we conduct content adaptive filtering in the YUV color space to consider context in images and obtain perceptually pleasant results. Extensive experiments on various video sequences demonstrate that the proposed method reconstructs natural-looking results even in highly corrupted images and achieves good performance in terms of both visual quality and quantitative measures.     

Integrated structure and control design for mechatronic systems with configuration-dependent dynamics

This paper considers the optimal design of mechatronic systems with configuration-dependent dynamics. An optimal mechatronic design requires that, among the structural and control parameters, an optimal choice has to be made with respect to design specifications in the different domains. Two main challenges are treated in this paper: the non-convex nature of the optimization problem and the difficulty in modeling serial machines with flexible components and their embedded controllers. The optimization problem is treated using the direct design strategy which considers simultaneously structural and control parameters as variables and adopts non-convex optimization algorithms. Linear time-invariant and gain-scheduling PID controllers are addressed. This methodology is exploited for the multi-objective optimization of a pick-and-place assembly robot with a gripper carried by a variable-length flexible beam. The resulting design tradeoffs between system accuracy and control efforts demonstrate the advantage of an integrated design approach for mechatronic systems with configuration-dependent dynamics.     

Action recognition on motion capture data using a dynemes and forward differences representation

In this paper we introduce a novel method for action/movement recognition in motion capture data. The joints orientation angles and the forward differences of these angles in different temporal scales are used to represent a motion capture sequence. Initially K-means is applied on training data to discover the most representative patterns on orientation angles and their forward differences. A novel K-means variant that takes into account the periodic nature of angular data is applied on the former. Each frame is then assigned to one or more of these patterns and histograms that describe the frequency of occurrence of these patterns for each movement are constructed. Nearest neighbour and SVM classification are used for action recognition on the test data. The effectiveness and robustness of this method is shown through extensive experimental results on four standard databases of motion capture data and various experimental setups.     

A MULTILAYER FEEDFORWARD NEURAL NETWORK MODEL FOR VISUAL MOTION PERCEPTION

The local visual motion detection mechanism used in the visual systems of primatescan only sense the motion component oriented perpendicularly to the contrast gradient of thebrightness pattern.But the visual system of higher animals can adaptively determine the actualdirection of motion through a learning process.In this paper a multilayered feedforward neuralnetwork model for perception of visual motion is presented.This model employs W.Reichardt'selementary motion detectors array and T.Kohonen's self-organizing feature map.We explored theself-organizing principles for perception of visual motion.The computer simulations show thatthis neural network is able to recognize the true direction of motion through an unsupervisedlearning process.In addition,the neurons with the same or similar motion direction selectivitytend to appear in“functional columns”which seem to be qualitatively similar to the corticalmotion columns observed by electrophysiological and cytohistochemical studies in certain higherareas such as MT.It proves that motion-detection by spatio-temporal coherences,mapping,co-operation,competition,and Hebb rule may be the basic principles for the self-organization ofvisual motion perception networks.     

Motion detection using block based bi-directional optical flow method

Detecting moving objects from video frame sequences has a lot of useful applications in computer vision. This proposed method of moving object detection first estimates the bi-directional optical flow fields between (i) the current frame and the previous frame and between (ii) the current frame and the next frame. The bi-directional optical flow field is then subjected to normalization and enhancement. Each normalized and enhanced optical flow field is then divided into non-overlapping blocks. The moving objects are finally detected in the form of binary blobs by examining the histogram based thresholded values of such optical flow field of each block as well as the optical flow field of the candidate flow value. Our technique has been conceptualized, implemented and tested on real video data sets with complex background environment. The experimental results and quantitative evaluation establish that our technique achieves effective and efficient results than other existing methods.     

基于仿射模型的重叠块运动估计补偿方法

本文对 Ｈ．２６３中基于平移模型的重叠块运动估计补偿方法进行改进,提出了一种基于仿射模型的重叠块运动补偿方法,该方法对复杂运动图像质量有明显改善。     

Motion control of an omnidirectional climbing robot based on dead reckoning method

While omnidirectional wheels enable a holonomic drive and a good maneuverability, the slippage of the wheels as an inherent characteristic of the omnidirectional wheels prevents using rotary shaft encoders as a reliable source of data for the robot’s odometry. When installed on a climbing robot, omnidirectional wheels may suffer from additional slippage on the surface. In a previous study, we described how the resulting vibration decreases the trajectory following accuracy of the robot, and why rotary encoders, as the most popular dead reckoning method cannot be used. In this paper, we address this problem by integration of low cost and light weight exteroceptive sensors, i.e. an accelerometer and an optical flow sensor. The Omniclimber climbing robot was used as the testing platform in this study. Omniclimbers are omnidirectional climbing robots that can climb and navigate over flat and curved structures. We attempt to compensate the errors due to the wheel slippage through closing the position control loop without significantly increasing the robot’s weight, cost and complexity of the robot. We also integrated an algorithm which corrects the robot kinematics on the curved structures based on the curvature diameter and the robot’s heading angle. Taking advantage of these sensors and algorithms we could make remarkable improvements on the path following accuracy of the Omniclimbers, which is presented in this article.     

基于H.263的实时视频编码技术研究

为了提高H．263编码技术现有算法的执行效率，本文提出了一种基于时域预测的预判零方法，该方法在保证一定图像质量的条件下具有较高的判别效率，能节约大量的编码时间：并在此基础上结合“钻石”运动搜索算法、MMX优化技术，实现了利用软件进行实时视频编码。