Abstract-Using a saliency measure based on the global property of contour closure, we have developed a segmentation method which identifies smooth closed contours bounding objects of unknown shape in real images. The saliency measure incorporates the Gestalt principles of proximity and good continuity that previous methods have also exploited. Unlike previous methods, we incorporate contour closure by finding the eigenvector with the largest positive real eigenvalue of a transition matrix for a Markov process where edges from the image serve as states. Element ði; jÞ of the transition matrix is the conditional probability that a contour which contains edge j will also contain edge i. In this paper, we show how the saliency measure, defined for individual edges, can be used to derive a saliency relation, defined for pairs of edges, and further show that strongly-connected components of the graph representing the saliency relation correspond to smooth closed contours in the image. Finally, we report for the first time, results on large real images for which segmentation takes an average of about 10 seconds per object on a general-purpose workstation.

A neural network model based on the anatomy and physiology of the cerebellum is presented that can generate both simple and complex predictive pursuit, while also responding in a feedback mode to visual perturbations from an ongoing trajectory. The model allows the prediction of complex movements by adding two features that are not present in other pursuit models: an array of inputs distributed over a range of physiologically justified delays, and a novel, biologically plausible learning rule that generated changes in synaptic strengths in response to retinal slip errors that arrive after long delays. To directly test the model, its output was compared with the behavior of monkeys tracking the same trajectories. There was a close correspondence between model and monkey performance. Complex target trajectories were created by summing two or three sinusoidal components of different frequencies along horizontal and/or vertical axes. Both the model and the monkeys were able to track these complex sum-of-sines trajectories with small phase delays that averaged 8 and 20 ms in magnitude, respectively. Both the model and the monkeys showed a consistent relationship between the high- and low-frequency components of pursuit: high-frequency components were tracked with small phase lags, whereas low-frequency components were tracked with phase leads. The model was also trained to track targets moving along a circular trajectory with infrequent right-angle perturbations that moved the target along a circle meridian. Before the perturbation, the model tracked the target with very small phase differences that averaged 5 ms. After the perturbation, the model overshot the target while continuing along the expected nonperturbed circular trajectory for 80 ms, before it moved toward the new perturbed trajectory. Monkeys showed similar behaviors with an average phase difference of 3 ms during circular pursuit, followed by a perturbation response after 90 ms. In both cases, the delays required to process visual information were much longer than delays associated with nonperturbed circular and sum-of-sines pursuit. This suggests that both the model and the eye make short-term predictions about future events to compensate for visual feedback delays in receiving information about the direction of a target moving along a changing trajectory. In addition, both the eye and the model can adjust to abrupt changes in target direction on the basis of visual feedback, but do so after significant processing delays.

No abstract

We develop a multi-class object detection framework whose core component is a nearest neighbor search over object part classes.

Astract: The estimation of the projective structure of a scene from image correspondences can be formulated as the minimization of the mean-squared distance between predicted and observed image points with respect to the projection matrices, the scene point positions, and their depths. Since these unknowns are not independent, constraints must be chosen to ensure that the optimization process is well posed. This paper examines three plausible choices, and shows that the first one leads to the Sturm-Triggs projective factorization algorithm, while the other two lead to new provably-convergent approaches. Experiments with synthetic and real data are used to compare the proposed techniques to the Sturm-Triggs algorithm and bundle adjustment. IntroductionLet us consider n fixed points P I , .., P,, observed by m perspective cameras. Given some fixed world coordinate system, we can write for i = 1, .., m and j = 1, ..,n, where p i j = (tiij,vij, l)T and zij denote respectively the (homogeneous) coordinate vector of the projection of Pj into image number i, expressed in the corresponding camera's coordinate frame and the depth of Pj relative to that frame, Mi is the 3 x 4 projection matrix associated with this camera in the world coordinate frame, and Pj is the homogeneous coordinate vector of the point Pj in that frame.We address the problem of reconstructing both the matrices Mi (i = l , ..,m) and the vectors Pj ( j = l, ..,TI) from the image correspondences p . . . Of course, zij is also unknown, but its value is not independent of the values of M i and Pi: indeed zij = mi3 . Pj , where m$ denotes the third row of the matrix M i . Faugeras [3] and Hartley et al. [7] have shown that when the internal parameters of the cameras are unknown, the cam-*3 'This work waa done while Y. Omori was visiting the Beckman Institute. He is now with the era motion and the scene structure can only be reconstructed up t o an arbitrary projective transformation