Rapid camera rotations (e.g. camera shake) are a significant problem when real-time computer vision algorithms are applied to video from a handheld or head-mounted camera. Such camera motions cause image features to move large distances in the image and cause significant motion blur. Here we propose a very fast method of estimating the camera rotation from a single frame which does not require ...

Motion blur is a common degradation which usually brings difficulties to subsequent image process and analysis of a machine vision system. In this paper, an effective restoration scheme is proposed for high-overlapped image sequence with composite motion blurs which refer to the blurs caused during the exposure time by dual relative motions among the background of the scene, the moving objects ...

Natural or artiicial vision systems process the images that they collect with their eyes or cameras in order to derive information for performing tasks related to navigation and recognition. Since the way images are acquired determines how diicult it is to perform a visual task, and since systems have to cope with limited resources, the eyes used by a speciic system should be designed to optimi...

In this paper we introduce visual compliance, a new vision-based control scheme that lends itself to task-level speciication of manipulation goals. Visual compliance is eeected by a hybrid vision/position control structure. Speciically, the two degrees of freedom parallel to the image plane of a supervisory camera are controlled using visual feedback, and the remaining degree of freedom (perpen...

A system to track an uninstrumented conductor’s baton by computer vision techniques is developed. An initial seek mode locates a baton in an image frame without prior knowledge; a subsequent track mode uses temporal information to cope with motion blur and noise. The seek mode utilises the characteristic form of detected edges to guide a maximal intensity trace. The track mode enhances this tec...

This paper explores an interesting image projection produced by scanning dynamic scenes with a slit camera. Based on the concept of Anorthoscopic Perception, we investigate how a two-dimensional Dynamic Projection Image of three-dimensional scenes is generated from consecutive 1-D snapshots taken through a slit, when the relative motion is homogeneous between the viewer and scenes. By moving th...

Continuous computer vision (CV) tasks increasingly rely on convolutional neural networks (CNN). However, CNNs have massive compute demands that far exceed the performance and energy constraints of mobile devices. In this paper, we propose and develop an algorithm-architecture co-designed system, Euphrates, that simultaneously improves the energyefficiency and performance of continuous vision ta...

The goal of visual modeling research is to develop mathematical models and associated algorithms for the analysis and synthesis of visual information. Image analysis and synthesis characterize the domains of computer vision and computer graphics, respectively. For nearly three decades, the vision and graphics fields have been developing almost entirely independently—this despite the fact that, ...

The analysis of medical images has been woven into the fabric of the Pattern Analysis and Machine Intelligence (PAMI) community since t h e earliest days of these Transactions. Initially, the efforts in this area were seen as applying pattern analysis and computer vision techniquss lo another interesting dataset. However. over the last two to three decades, the unique nature of the problems pre...

We study the impact of local context of an image (contrast and 2D structure) on spatial motion integration by MT neurons. To do so, we revisited the seminal work by Heeger and Simoncelli (HS) [4] using spatio-temporal filters to estimate optical flow from V1-MT feedforward interactions. However, the HS model has difficulties to deal with several problems encountered in real scenes (e.g., blank ...