Staff Members - Benha University
Q. Abbas, Mostafa E.A. Ibrahim, and M. Jaffar. A comprehensive review of recent advances on deep vision systems. Springer Artificial Intelligence Review (Impact Factor 2017: 3.814) (2018). https://doi. 10.1007/s10462-018-9633-3
Artificial Intelligence Review • 2019
Publication Information
Authors
Mostafa E.A. Ibrahim; Q. Abbas; M. Jaffar
Keywords
Computer vision; Video processing; Object detection; Object tracking; Object recognition; Deep learning; Convolutional neural network; Deep belief network; Deep residual learning
Journal
Artificial Intelligence Review
Publisher
Springer
Volume
52
Issue
Not Available
Pages
39–76
publication.type
International
Paper Link
Open Link
Supplementary Materials
Not Available
Abstract
Real-time video objects detection, tracking, and recognition are challenging issues
due to the real-time processing requirements of the machine learning algorithms. In recent
years, video processing is performed by deep learning (DL) based techniques that achieve
higher accuracy but require higher computations cost. This paper presents a recent survey of
the state-of-the-art DL platforms and architectures used for deep vision systems. It highlights
the contributions and challenges from over numerous research studies. In particular, this paper
first describes the architecture of various DL models such as AutoEncoders, deep Boltzmann
machines, convolution neural networks, recurrent neural networks and deep residual learning.
Next, deep real-time video objects detection, tracking and recognition studies are highlighted
to illustrate the key trends in terms of cost of computation, number of layers and the accuracy
of results. Finally, the paper discusses the challenges of applying DL for real-time video
processing and draw some directions for the future of DL algorithms.
due to the real-time processing requirements of the machine learning algorithms. In recent
years, video processing is performed by deep learning (DL) based techniques that achieve
higher accuracy but require higher computations cost. This paper presents a recent survey of
the state-of-the-art DL platforms and architectures used for deep vision systems. It highlights
the contributions and challenges from over numerous research studies. In particular, this paper
first describes the architecture of various DL models such as AutoEncoders, deep Boltzmann
machines, convolution neural networks, recurrent neural networks and deep residual learning.
Next, deep real-time video objects detection, tracking and recognition studies are highlighted
to illustrate the key trends in terms of cost of computation, number of layers and the accuracy
of results. Finally, the paper discusses the challenges of applying DL for real-time video
processing and draw some directions for the future of DL algorithms.