Artificial neural networks for 3-D motion analysis-Part II:Nonrigid motion

For pt. I see ibid., p. 1386-93 (1995). An approach applying artificial neural net techniques to 3D nonrigid motion analysis is proposed. The 3D nonrigid motion of the left ventricle of a human heart is examined using biplanar cineangiography data, consisting of 3D coordinates of 30 coronary artery bifurcation points of the left ventricle and the correspondences of these points taken over 10 time instants during the heart cardiac cycle. The motion is decomposed into global rigid motion and a set of local nonrigid deformations which are coupled with the global motion. The global rigid motion can be estimated precisely as a translation vecto and a rotation matrix. Local nonrigid deformation estimation is discussed. A set of neural nets similar in structure and dynamics but different in physical size is proposed to tackle the problem of nonrigidity. These neural networks are interconnected through feedbacks. The activation function of the output layer is selected so that a feedback is involved in the output updating. The constraints are specified to ensure stable and globally consistent estimation. The objective is to find the optimal deformation matrices that satisfy the constraints for all coronary artery bifurcation points of the left ventricle. The proposed neural networks differ from other existing neural network models in their unique structure and dynamics.     

Mesh simplification with hierarchical shape analysis and iterative edge contraction

We present a novel mesh simplification algorithm. It decouples the simplification process into two phases: shape analysis and edge contraction. In the analysis phase, it imposes a hierarchical structure on a surface mesh by uniform hierarchical partitioning, marks the importance of each vertex in the hierarchical structure, and determines the affected regions of each vertex at the hierarchical levels. In the contraction phase, it also divides the simplification procedure into two steps: half-edge contraction and optimization. In the first step, memoryless quadric metric error and the importance of vertices in the hierarchical structure are combined to determine one operation of half-edge contraction. In the second step, it repositions the vertices in the half-edge simplified mesh by minimizing the multilevel synthesized quadric error on the corresponding affected regions from the immediately local to the more global. The experiments illustrate the competitive results.     

等级制度下带有时变时滞的群集运动

主要研究了等级制度下带有时变时滞的群集运动。证明了在一定条件的等级制度下,当时间趋于无穷大时,智能体之间即使存在着时变的通信时滞,也能达到群集运动。最后,用数值仿真的例子来证明结论的有效性。     

ASSET-2: real-time motion segmentation and shape tracking

This paper describes a system for detecting and tracking moving objects in a moving world. The feature-based optic flow field is segmented into clusters with affine internal motion which are tracked over time. The system runs in real-time, and is accurate and reliable     

Whole-body hierarchical motion and force control for humanoid robots

Robots acting in human environments usually need to perform multiple motion and force tasks while respecting a set of constraints. When a physical contact with the environment is established, the newly activated force task or contact constraint may interfere with other tasks. The objective of this paper is to provide a control framework that can achieve real-time control of humanoid robots performing both strict and non strict prioritized motion and force tasks. It is a torque-based quasi-static control framework, which handles a dynamically changing task hierarchy with simultaneous priority transitions as well as activation or deactivation of tasks. A quadratic programming problem is solved to maintain desired task hierarchies, subject to constraints. A generalized projector is used to quantitatively regulate how much a task can influence or be influenced by other tasks through the modulation of a priority matrix. By the smooth variations of the priority matrix, sudden hierarchy rearrangements can be avoided to reduce the risk of instability. The effectiveness of this approach is demonstrated on both a simulated and a real humanoid robot.     

Recursive non-rigid structure from motion with online learned shape prior

Most existing approaches in structure from motion for deformable objects focus on non-incremental solutions utilizing batch type algorithms. All data is collected before shape and motion reconstruction take place. This methodology is inherently unsuitable for applications that require real-time learning. Ideally the online system is capable of incrementally learning and building accurate shapes using current measurement data and past reconstructed shapes. Estimation of 3D structure and camera position is done online. To rely only on the measurements up until that moment is still a challenging problem.     

Branch-and-Mincut: Global Optimization for Image Segmentation with High-Level Priors

Efficient global optimization techniques such as graph cut exist for energies corresponding to binary image segmentation from low-level cues. However, introducing a high-level prior such as a shape prior or a color-distribution prior into the segmentation process typically results in an energy that is much harder to optimize. The main contribution of the paper is a new global optimization framework for a wide class of such energies. The framework is built upon two powerful techniques: graph cut and branch-and-bound. These techniques are unified through the derivation of lower bounds on the energies. Being computable via graph cut, these bounds are used to prune branches within a branch-and-bound search. We demonstrate that the new framework can compute globally optimal segmentations for a variety of segmentation scenarios in a reasonable time on a modern CPU. These scenarios include unsupervised segmentation of an object undergoing 3D pose change, category-specific shape segmentation, and the segmentation under intensity/color priors defined by Chan-Vese and GrabCut functionals.     

Texture,contour, shape,and motion

Intrinsic magic calculation exploits constraints arising from physical and imaging processes to derive physical scene parameters from input images. After a brief review of a paradigmatic intrinsic image calculation we turn to a recent result in shape from texture and then to a new result that derives shape and motion from a sequence of patterned inputs. Experimental results are demonstrated for synthetic and natural images.     

2D shape morphing via automatic feature matching and hierarchical interpolation

The paper presents a new method to interpolate a pair of 2D shapes that are represented by piecewise linear curves. The method addresses two key problems in 2D shape morphing process: feature correspondence and path interpolation. First, a robust feature metric is defined to measure the similarity of a pair of 2D shapes in terms of visual appearance, orientation and relative size. Based on the metric, an optimal problem is defined and solved to associate the features on the source shape with the corresponding ones on the target shape. Then, a two-level hierarchical approach is proposed to solve the corresponding features interpolation trajectory problem. The algorithm decomposes the input shapes into a pair of corresponding coarse polygons and several pairs of corresponding features. Then the corresponding coarse polygons are interpolated in an as-rigid-as-possible plausible way; meanwhile the corresponding features are interpolated using the intrinsic method. Thus interior distortions of the intermediate shapes could be avoided and the feature details on the input shapes could be well preserved. Experimental results show that the method can generate smooth, natural and visually pleasing 2D shape morphing effects.     

A shape adaptive motion control system with application to robotic polishing

This paper presents a new shape adaptive motion control system that integrates part measurement with motion control. The proposed system consists of four blocks: surface measurement; surface reconstruction; tool trajectory planning; and axis motion control. The key technology used in surface measurement and surface reconstruction is the spatial spectral analysis. In the surface measurement block, a new spectral spectrum comparison method is proposed to determine an optimal digitizing frequency. In the surface reconstruction block, different interpolation methods are compared in the spatial spectral domain. A spatial spectral B-spline method is presented. In the tool trajectory planning block, a method is developed to select a motion profile first and then determine tool locations according to the reconstructed surface in order to improve the accuracy of the planned toolpath. Based on the proposed methods, a software package is developed and implemented on the polishing robot constructed at Ryerson University. The effectiveness of the proposed system has been demonstrated by the experiment on edge polishing. In this experiment, the shape of the part edges is measured first, and then constructed as a wire-frame CAD model, based on which the tool trajectory is planned to control the tool to polish the edges.     

Articulated soft objects for multiview shape and motion capture

We develop a framework for 3D shape and motion recovery of articulated deformable objects. We propose a formalism that incorporates the use of implicit surfaces into earlier robotics approaches that were designed to handle articulated structures. We demonstrate its effectiveness for human body modeling from synchronized video sequences. Our method is both robust and generic. It could easily be applied to other shape and motion recovery problems.     

A hierarchical method combining gait and phase of motion with spatiotemporal model for person re-identification

Re-identification refers to the problem of establishing correspondence among various observations of the same subject viewed at different time instances in different camera positions. We propose a hierarchical approach for re-identifying a subject by combining gait with phase of motion and a spatiotemporal model. The fundamental nature of the gait biometric of being amenable to capturing from a distance even at low resolution without active co-operation of subjects, has motivated us to use it for re-identification. We use two features related to a subject’s motion dynamics, one is his exit/entry phase of motion and the other is his gait signature. An additional third feature is obtained from the spatiotemporal model of the camera network which is learnt during the training phase in the form of a multivariate probability density of space–time variables (entry/exit location, exit velocity, and inter-camera travel time) using kernel density estimation. Once all these three features have been computed, correspondences are established by dynamic programing based maximum likelihood (ML) estimation. The performance of our method has been evaluated on a real data set featuring a two-camera and a three-camera network in a hallway monitoring situation. The proposed approach shows promising results on both the data sets.     

Moving object classification using local shape and HOG features in wavelet-transformed space with hierarchical SVM classifiers

This paper proposes an integrated system for the segmentation and classification of four moving objects, including pedestrians, cars, motorcycles, and bicycles, from their side-views in a video sequence. Based on the use of an adaptive background in the red–green–blue (RGB) color model, each moving object is segmented with its minimum enclosing rectangle (MER) window by using a histogram-based projection approach or a tracking-based approach. Additionally, a shadow removal technique is applied to the segmented objects to improve the classification performance. For the MER windows with different sizes, a window scaling operation followed by an adaptive block-shifting operation is applied to obtain a fixed feature dimension. A weight mask, which is constructed according to the frequency of occurrence of an object in each position within a square window, is proposed to enhance the distinguishing pixels in the rescaled MER window. To extract classification features, a two-level Haar wavelet transform is applied to the rescaled MER window. The local shape features and the modified histogram of oriented gradients (HOG) are extracted from the level-two and level-one sub-bands, respectively, of the wavelet-transformed space. A hierarchical linear support vector machine classification configuration is proposed to classify the four classes of objects. Six video sequences are used to test the classification performance of the proposed method. The computer processing times of the object segmentation, object tracking, and feature extraction and classification approaches are 79 ms, 211 ms, and 0.01 ms, respectively. Comparisons with different well-known classification approaches verify the superiority of the proposed classification method.     

Towards gesture-based programming: shape from motion primordial learning of sensorimotor primitives

Gesture-based programming (GBP) is a paradigm for the evolutionary programming of dextrous robotic systems by human demonstration. We call the paradigm “gesture-based” because we try to capture, in real-time, the intention behind the demonstratrator's fleeting, context-dependent hand motions, contact conditions, finger poses, and even cryptic utterances, rather than just recording and replaying movement. The paradigm depends on a pre-existing knowledge base of capabilities, collectively called “encapsulated expertise”, that comprise the real-time sensorimotor primitives from which the run-time executable is constructed as well as providing the basis for interpreting the teacher's actions during programming. In this paper we first describe the GBP environment, which is not fully implemented. We then present a technique based on principal components analysis, augmentable with model-based information, for learing and recognizing sensorimotor primitives. This paper describes simple applications of the technique to a small mobile robot and a PUMA manipulator. The mobile robot learned to escape from jams while the manipulator learned guarded moves and rotational accommodation that are composable to allow flat plate mating operations. While these initial applications are simple, they demonstrate the ability to extract primitives from demonstration, recognize the learned primitives in subsequent demonstrations, and combine and transform primitives to create different capabilities, which are all critical to the GBP paradigm.     

Direct computation of qualitative 3-D shape and motion invariants

Structure from motion often refers to the computation of three-dimensional structure from a matched sequence of images. However, a depth map of a surface is difficult to compute and may not be a good representation for storage and recognition. Given matched images it is shown that the sign of the normal curvature in a given direction at a given point in the image can be computed from a simple difference of slopes of line segments in one image. Using this result, local surface patches can be classified as convex, concave, cylindrical, hyperbolic (saddle point), or planar. At the same time, the translational component of the optical flow, from which the focus of expansion can be computed, is obtained     

Euclidean shape and motion from multiple perspective views byaffine iterations

We describe a method for solving the Euclidean reconstruction problem with a perspective camera model by incrementally performing Euclidean reconstruction with either a weak or a paraperspective camera model. With respect to other methods that compute shape and motion from a sequence of images with a calibrated camera, this method converges in a few iterations, is computationally efficient, and solves for the sign (reversal) ambiguity. We give a detailed account of the method, analyze its convergence, and test it with both synthetic and real data     

Efficient fall activity recognition by combining shape and motion features

Computational Visual Media - This paper presents a vision-based system for recognizing when elderly adults fall. A fall is characterized by shape deformation and high motion. We represent shape...