A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Machine Learning for Green Smart Video Surveillance
The forthcoming smart environments will have advanced technology for capturing, processing, and analysing high-resolution and high-quality visual information. In future green smart cities, advanced video surveillance with dense deployment of video sensors is definitely necessary to build intelligent and secure urban environments. Since large-scale compression of high-quality video with low bit rate is computationally expensive, a significant impact on energy consumption is inevitable, and green computing approaches become increasingly relevant. The best candidate for video compression is the recently approved Versatile Video Coding (VVC) standard, but its huge computational power requirements have been under investigation to achieve low-energy consumption by means of reducing its algorithmic complexity. This chapter addresses the main sources of computational complexity in the VVC and presents a thorough review of machine learning approaches recently investigated for reducing this burden. Some recent research results, specifically targeted for omnidirectional video surveillance systems, are also presented, including future research directions towards green computing for video coding.
Machine Learning for Green Smart Video Surveillance
The forthcoming smart environments will have advanced technology for capturing, processing, and analysing high-resolution and high-quality visual information. In future green smart cities, advanced video surveillance with dense deployment of video sensors is definitely necessary to build intelligent and secure urban environments. Since large-scale compression of high-quality video with low bit rate is computationally expensive, a significant impact on energy consumption is inevitable, and green computing approaches become increasingly relevant. The best candidate for video compression is the recently approved Versatile Video Coding (VVC) standard, but its huge computational power requirements have been under investigation to achieve low-energy consumption by means of reducing its algorithmic complexity. This chapter addresses the main sources of computational complexity in the VVC and presents a thorough review of machine learning approaches recently investigated for reducing this burden. Some recent research results, specifically targeted for omnidirectional video surveillance systems, are also presented, including future research directions towards green computing for video coding.
Machine Learning for Green Smart Video Surveillance
Green Energy,Technology
Lahby, Mohamed (editor) / Al-Fuqaha, Ala (editor) / Maleh, Yassine (editor) / Filipe, Jose (author) / Navarro, Antonio (author) / Tavora, Luis (author) / de Faria, Sergio M. M. (author) / Assuncao, Pedro A. Amado (author)
2022-04-22
30 pages
Article/Chapter (Book)
Electronic Resource
English
Green video coding , Video surveillance , Video codec complexity , Machine learning , Versatile video coding Environment , Sustainable Development , Power Electronics, Electrical Machines and Networks , Cities, Countries, Regions , Renewable and Green Energy , Communications Engineering, Networks , Energy
Machine Learning for Green Smart Homes
| Springer Verlag | 2022
Enhancing Human Activity Recognition in Smart Surveillance Using Transfer Learning
| Springer Verlag | 2025
Machine Learning for Green Smart Health Toward Improving Cancer Data Feature Awareness
| Springer Verlag | 2022