Goutcher, Ross and Barrington, Chris and Hibbard, Paul and Graham, Bruce (2021) 'Binocular Vision Supports the Development of Scene Segmentation Capabilities: Evidence from a Deep Learning Model.' Journal of Vision, 21 (7). p. 13. ISSN 1534-7362
|
Text
i1534-7362-21-7-13_1626855206.18985.pdf - Published Version Available under License Creative Commons Attribution. Download (1MB) | Preview |
Abstract
The application of deep learning techniques has led to substantial progress in solving a number of critical problems in machine vision, including fundamental problems of scene segmentation and depth estimation. Here, we report a novel deep neural network (DNN) model, capable of simultaneous scene segmentation and depth estimation from a pair of binocular images. By manipulating the arrangement of binocular image pairs, presenting the model with standard left-right image pairs, identical image pairs or swapped left-right images, we show that performance levels depend upon the presence of appropriate binocular image arrangements. Segmentation and depth estimation performance are both impaired when images are swapped. Segmentation performance levels are maintained, however, for identical image pairs, despite the absence of binocular disparity information. Critically, these performance levels exceed those found for an equivalent, monocularly trained, segmentation model. These results provide evidence that binocular image differences support both the direct recovery of depth and segmentation information, and the enhanced learning of monocular segmentation signals. This finding suggests that binocular vision may play an important role in visual development. Better understanding of this role may hold implications for the study and treatment of developmentally acquired perceptual impairments.
Item Type: | Article |
---|---|
Uncontrolled Keywords: | Deep learning; Binocular vision; artificial neural networks; scene segmentation; distance; depth |
Divisions: | Faculty of Science and Health Faculty of Science and Health > Psychology, Department of |
SWORD Depositor: | Elements |
Depositing User: | Elements |
Date Deposited: | 03 Aug 2021 08:26 |
Last Modified: | 06 Jan 2022 14:25 |
URI: | http://repository.essex.ac.uk/id/eprint/30753 |
Actions (login required)
![]() |
View Item |