Computer vision algorithms and hardware implementations: A survey
Алгоритмы компьютерного зрения и их аппаратные реализации: обзор
2019-08-06
SCID: 54.1/e6ku64qg
Discuss with AI
computer visiondeep learninghardware acceleratorsimage classificationobject detection
Figures from the paper
Abstract (AI)
The field of computer vision is experiencing a great-leap-forward development today. This paper aims at providing a comprehensive survey of the recent progress on computer vision algorithms and their corresponding hardware implementations. In particular, the prominent achievements in computer vision tasks such as image classification, object detection and image segmentation brought by deep learning techniques are highlighted. On the other hand, review of techniques for implementing and optimizing deep-learning-based computer vision algorithms on GPU, FPGA and other new generations of hardware accelerators are presented to facilitate real-time and/or energy-efficient operations. Finally, several promising directions for future research are presented to motivate further development in the field.
Key Findings
1
Deep learning has produced prominent achievements in image classification, object detection, and image segmentation.
2
GPU, FPGA, and emerging hardware accelerators enable optimization of deep-learning-based vision algorithms for real-time and energy-efficient operation.
3
The paper identifies promising future research directions for continued development of computer vision algorithms and hardware.
4
The survey emphasizes the importance of co-optimizing algorithms and hardware to support practical computer vision deployment.
5
The survey reviews recent advances in computer vision algorithms and corresponding hardware implementations.
Research Object
deep-learning-based computer vision algorithms and their hardware implementations
Research Subject
recent progress, implementation and optimization for image classification, object detection, and image segmentation, including real-time and energy-efficient operation
Publication Details
Publication Date
2019-08-06
Journal
Publisher
ISSN
Cited by
350
Open access PDF
Access Type
Author Information
Download PDF
Subscribe to digest
References available in scid.ai9
ImageNet classification with deep convolutional neural networks2017
Very Deep Convolutional Networks for Large-Scale Image Recognition2014
ImageNet: A large-scale hierarchical image database2009
Gradient-based learning applied to document recognition1998
Squeeze-and-Excitation Networks2018
ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices2018
Deep Learning for Generic Object Detection: A Survey2019
YFCC100M2016
A Multi-Modal Distributed Real-Time IoT System for Urban Traffic Control (Invited Paper)2024
Cited by4
On the Opportunities and Risks of Foundation Models2021
Integration of IoT-Enabled Technologies and Artificial Intelligence (AI) for Smart City Scenario: Recent Advancements and Future Trends2023
A Review of Machine Learning and Deep Learning for Object Detection, Semantic Segmentation, and Human Action Recognition in Machine and Robotic Vision2024
Artificial Intelligence Technology in the Agricultural Sector: A Systematic Literature Review2022