|
An area of computer vision is active vision, sometimes also called ''active computer vision''. An active vision system is one that can manipulate the viewpoint of the camera(s) in order to investigate the environment and get better information from it.〔(http://axiom.anu.edu.au/~rsl/rsl_active.html )〕〔Ballard, D.H., "Animate vision," Artificial Intelligence Journal 48, 57-86, 1991〕〔Active Vision, J. Aloimonos, I. Weiss, A. Bandopadhay, 1988, International Journal of Computer Vision 1 (4), pages 333-356〕〔 (Ecological Active Vision: Four Bio-Inspired Principles to Integrate Bottom-Up and Adaptive Top-Down Attention Tested With a Simple Camera-Arm Robot, D. Ognibene, G. Baldassarre, 2014, Autonomous Mental Development, IEEE Transactions on )〕 ==Background== The interest in active camera system started as early as two decades ago. Beginning in the late 1980s, Aloimonos et al. introduced the first general framework for active vision in order to improve the perceptual quality of tracking results.〔Aloimonos, J., Weiss, I., Bandyopadhyay, A.: Active vision. Int. J. Comput. Vis. 1(4), 333– 356 (1988)〕 Active vision is particularly important to cope with problems like occlusions, limited field of view and limited resolution of the camera.〔Denzler, J.; Zobel, M. & Niemann, H. Information theoretic focal length selection for real-time active 3D object tracking Computer Vision, 2003. Proceedings. Ninth IEEE International Conference on, 2003, 400 -407 vol.1〕 Other advantages can be reducing the motion blur of a moving object 〔Control of a Camera for Active Vision: Foveal Vision, Smooth Tracking and Saccade International Journal of Computer Vision, Springer, 2000, 39, 81-96〕 and enhancing depth perception of an object by focusing two cameras on the same object or moving the cameras.〔 Active control of the camera view point also helps in focusing computational resources on the relevant element of the scene.〔Tatler, B. W.; Hayhoe, M. M.; Land, M. F. & Ballard, D. Eye guidance in natural vision: Reinterpreting salience J Vis, 2011, 11, 1-23〕 In this selective aspect, active vision can be seen as strictly related to (overt & covert) visual attention in biological organisms, which has been shown to enhance the perception of selected part of the visual field. This selective aspect of human (active) vision can be easily related to the foveal structure of the human eye,〔〔Tistarelli, M. & Sandini, G. On the Advantages of Polar and Log-Polar Mapping for Direct Estimation of Time-To-Impact from Optical Flow IEEE Trans. Pattern Anal. Mach. Intell., IEEE Computer Society, 1993, 15, 401-410〕 where in about 5% of the retina more than the 50% of the colour receptors are located. It has also been suggested that visual attention and the selective aspect of active camera control can help in other tasks like learning more robust models of objects and environments with less labeled samples or autonomously .〔〔Walther, D.; Rutishauser, U.; Koch, C. & Perona, P. Selective visual attention enables learning and recognition of multiple objects in cluttered scenes Computer Vision and Image Understanding, 2005, 100, 41-63〕〔Larochelle, H. & Hinton, G. Learning to combine foveal glimpses with a third-order Boltzmann machin, NIPS, 2010〕 抄文引用元・出典: フリー百科事典『 ウィキペディア（Wikipedia）』 ■ウィキペディアで「active vision」の詳細全文を読む スポンサード リンク
|