3D computer vision based on machine learning with deep neural networks: A review. Issue 11 (25th January 2018)

• Record Type: Journal Article
• Authors: Vodrahalli, Kailas; Bhowmik, Achintya K.
• Is Part Of: Journal of the Society for Information Display. Volume 25:Issue 11(2017)
• Page Start: 676
• Page End: 694
• Publication Date: 2018-01-25
• Subjects: computer vision -- artificial intelligence -- machine learning -- deep neural networks; Information display systems -- Periodicals; 621.38154205
• DOI: 10.1002/jsid.617
• Languages: English
• ISSNs: 1071-0922

Abstract

Abstract: Recent advances in the field of computer vision can be attributed to the emergence of deep learning techniques, in particular convolutional neural networks. Neural networks, partially inspired by the brain's visual cortex, enable a computer to "learn" the most important features of the images it is shown in relation to a specific, specified task. Given sufficient data and time, (deep) convolutional neural networks offer more easily designed, more generalizable, and significantly more accurate end‐to‐end systems than is possible with previously employed computer vision techniques. This review paper seeks to provide an overview of deep learning in the field of computer vision with an emphasis on recent progress in tasks involving 3D visual data. Through a backdrop of the mammalian visual processing system, we hope to also provide inspiration for future advances in automated visual processing. Abstract : Recent progress in the field of computer vision, in particular three‐dimensional computer vision, can be attributed to deep convolutional neural networks. This survey presents some of these key results against a backdrop of the mammalian visual processing system to provide inspiration for future advances in the field. [Reprinted with permission: S. Gupta, R. Girshick, P. Arbeláez and J. Malik, "Learning rich features from RGB‐D images for object detection and segmentation, " in European Conference on Computer Vision, 2014.]