Image analysis: Problems,progress and prospects

Over the past 25 years, many ad hoc techniques for analyzing images have been developed and the subject has gradually begun to develop a scientific basis. This paper outlines the basic steps in a general image analysis process. It summarizes the state of the art with respect to each step, points out limitations of present methods and indicates potential directions for future work.     

Paul A. Kolers (1926-1986).

Presents an obituary for Paul Kolers, psychologist and University of Toronto faculty member, who died of lung cancer on January 27, 1986. Kolers' early work was in vision research, and he maintained that interest throughout his career, although in his later writings he became progressively more concerned with the nature of symbolic representation and other semi-philosophical problems of mind. He contributed substantially to our knowledge of perceptual and cognitive processes, both through his trenchant analyses and critiques of current theories, and through his own imaginative experimental demonstrations and theoretical insights. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

基于模型的水下目标三维视觉信息复原

水下目标三维视觉信息复原是水下智能机器人（ＡＵＶ）感知环境信息、进行自主作业的关键技术。本文介绍了一种基于模型的复原方法，即通过检测目标边缘拟合轮廓，根据模型知识复原三维信息。该方法已经成功地导引ＡＵＶ进行了水下自主避障、自主剪缆、自主投掷等智能作业。     

Computational models for integrating linguistic and visual information: A survey

This paper surveys research in developing computational models for integrating linguistic and visual information. It begins with a discussion of systems which have been actually implemented and continues with computationally motivated theories of human cognition. Since existing research spans several disciplines (e.g., natural language understanding, computer vision, knowledge representation), as well as several application areas, an important contribution of this paper is to categorize existing research based on inputs and objectives. Finally, some key issues related to integrating information from two such diverse sources are outlined and related to existing research. Throughout, the key issue addressed is the correspondence problem, namely how to associate visual events with words and vice versa.     

主动视觉系统中的摄像机姿态校准

提出了在镜头畸变径向约束下,用平面上四个点及其成像关系来建立摄像机姿态的几何 方法.并运用随机样本一致性技术和多视点下摄像机内参数一致性约束提高计算的稳定性和 精度.指出了只利用摄像机正、反投影关系检验其姿态正确性是不充分的,提出将视点间运 动变换关系作为评价相应摄像机姿态精度的重要标准.     

On-line recognition (OLREC): A novel approach to visual pattern recognition

A pattern recognition system has been developed which is capable of recognizing high contrast two-dimensional visual patterns and which is insensitive to the translation, rotation and size of a pattern. The unique characteristics of the system are its speed, its low cost and the fact that it is completely self-contained.

A new technique for image recognition, suitable for applications such as industrial robotics, is presented. The technique provides invariance to rotation, translation and magnification of the image. An intelligent camera system is used to input an image, to center it, to normalize it with respect to size and to convert it into polar coordinate form. The image is then integrated over r and θ to provide two orthogonal profiles. The input profiles are compared to the reference images using a threshold comparison technique designed to provide a simple hardware implementation. Rotation of the image is handled by a one-dimensional shifting of the radial profile.

Seven experiments were performed to test the system. The results of these experiments are discussed and possible improvements to the system are suggested.     

Color vision research and trichromatic theory: A historical review.

"After more than a century of scientific research in color vision the trichromatic theory continues to face theoretical contradictions and unexplained facts. Trichromatic theories everywhere should rigorously examine the theory's basic assumptions, provide much more experimental data on the basic visual functions, and honestly ask themselves the question: should the theory be subject to drastic revision or should it be replaced by some other theory?" (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

Aging and the detection of observer and moving object collisions.

The authors examined age-related differences in the detection of collision events. Older and younger observers were presented with displays simulating approaching objects that would either collide or pass by the observer. In 4 experiments, the authors found that older observers, as compared with younger observers, had less sensitivity in detecting collisions with an increase in speed, at shorter display durations, and with longer time-to-contact conditions. Older observers also had greater difficulty when the scenario simulated observer motion, suggesting that older observers have difficulty discriminating object motion expansion from background expansion from observer motion. The results of these studies support the expansion sensitivity hypothesis-that age-related decrements in detecting collision events involving moving objects are the result of a decreased sensitivity to recover expansion information. (PsycINFO Database Record (c) 2010 APA, all rights reserved)     

集成DSP的视频处理卡在机器视觉中的应用

针对在机器视觉的应用中普遍存在的待处理的图像数据量多且算法复杂，单机CPU无法实时完成图像处理任务，需要多台计算机组成局域网平行处理，成本高昂且可靠性低的问题。给出了集成DSP芯片的高速图像采集卡以替代主机CPU进行图像算法处理的解决方案，并指出在单台PC机上插入多块高速图像采集卡，主机的CPU只负责统一协调作用就可以较好的处理此类问题。由于该高速卡设计灵活，只需稍作改动即可应用于嵌入式设备。该高速图像处理卡在机器视觉领域内有着重要和广泛的应用前景。     

Exploiting parallelism in 3-D object recognition using the connection machine

This paper addresses the problem of parallelism in 3-D object recognition and localization using a fine-grained SIMD architecture such as the Connection Machine^TM. The input images of partially occluding three-dimensional objects. The objects are made up of piecewise compositions of curved surfaces. The surfaces of interest are cylindrical, conical and spherical surfaces since they cover a large portion of objects encountered in an industrial environment. Qualitative classification of surfaces based on the signs of the Mean and Gaussian curvature is used to come up with Dihedral feature junctions. Dihedral feature junctions are shown to be robust to occlusion and offer a viewpoint independent scheme for modeling the object models and are well suited for matching and pose determination. Hough clustering is chosen as the constraint propagation mechanism on account of the ease of parallelization. Issues regarding parallelism on the Connection Machine^TM for every stage of the recognition and localization process such as segmentations, feature extraction matching and pose determination are discussed. Experimental results on the Connection Machine^TM bring out the advantages of exploiting parallelism for 3-D object recognition and localization on a fine-grained SIMD architecture.