Developmental Constraints Aid the Acquisition of Binocular Disparity Sensitivities
نویسندگان
چکیده
This article considers the hypothesis that systems learning aspects of visual perception may benefit from the use of suitably designed developmental progressions during training. We report the results of simulations in which four models were trained to detect binocular disparities in pairs of visual images. Three of the models were developmental models in the sense that the nature of their visual input changed during the course of training. These models received a relatively impoverished visual input early in training, and the quality of this input improved as training progressed. One model used a coarse-scale-to-multiscale developmental progression, another used a fine-scale-to-multiscale progression, and the third used a random progression. The final model was nondevelopmental in the sense that the nature of its input remained the same throughout the training period. The simulation results show that the two developmental models whose progressions were organized by spatial frequency content consistently outperformed the nondevelopmental and random developmental models. We speculate that the superior performance of these two models is due to two important features of their developmental progressions: (1) these models were exposed to visual inputs at a single scale early in training, and (2) the spatial scale of their inputs progressed in an orderly fashion from one scale to a neighboring scale during training. Simulation results consistent with these speculations are presented. We conclude that suitably designed developmental sequences can be useful to systems learning to detect binocular disparities. The idea that visual development can aid visual learning is a viable hypothesis in need of study.
منابع مشابه
The Role of Contrast Sensitivity in the Development of Binocular Vision: Computational Study
The development of accurate binocular vision relies on the acquisition of disparity tuning and the calibration of vergence eye movements. Both processes are fundamentally limited by visual acuity, which increases only gradually during the first year of life. Next to limiting performance, however, early limitations of visual acuity may also aid rapid learning analogous to Newport’s “less-is-more...
متن کاملCamera Arrangement in Visual 3D Systems using Iso-disparity Model to Enhance Depth Estimation Accuracy
In this paper we address the problem of automatic arrangement of cameras in a 3D system to enhance the performance of depth acquisition procedure. Lacking ground truth or a priori information, a measure of uncertainty is required to assess the quality of reconstruction. The mathematical model of iso-disparity surfaces provides an efficient way to estimate the depth estimation uncertainty which ...
متن کاملThe relative sensitivities of sensory and motor fusion to small binocular disparities
Horizontal binocular disparity is the fundamental stimulus for both fusional vergence and stereopsis, but whether common disparity-sensitive mechanisms are involved in both responses is unknown. To determine whether the sensitivities of motor and sensory fusion are interdependent, we studied vergence eye movements and depth discrimination, using stimuli with haplopic binocular disparities, in s...
متن کاملTesting Probabilistic Models of Binocular 3d Motion Perception
Geometric constraints for the perception of three-dimensional (3D) binocular motion are discussed in a probabilistic framework. Two alternative Bayesian models of binocular integration are put forward to explain perceptual bias under uncertainty. The models exploit biologically plausible constraints of local motion and disparity processing in a binocular viewing geometry. Results from computer ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
- Neural computation
دوره 15 1 شماره
صفحات -
تاریخ انتشار 2003