Multi-View Clustering for Fast Intra Mode Decision in HEVC

• Main Authors: Jillani, Rashad, Hussain, Syed Fawad, Kalva, Hari
• Format: Conference Proceeding
• Language: English
• Subjects: Clustering algorithms; Conferences; Correlation; Encoding; HEVC; Intra prediction; Machine learning; Machine learning algorithms; Multi-view clustering; Real-time systems
• ISSN: 2158-4001
• DOI: 10.1109/ICCE46568.2020.9043106

High Efficiency Video Coding (HEVC) introduced many new coding tools to gain improved coding efficiency. However, it greatly introduces computational cost, and this will give rise to the demand for the fast algorithm that can satisfy the real-time encoding of HEVC encoder for low bandwidth environment. In this paper we introduce and evaluate a novel machine learning based approach that uses multi-view clustering to reduce the complexity of intra-coding algorithm based on the analysis of original texture and its neighborhood. The proposed approach is based on the hypothesis that intra coding mode decisions in HEVC video have a correlation with the intensities of adjacent CUs within a CTU. The proposed approach consists of two steps, coding unit size decision and reduction of candidate modes by using multi-view clustering. This results in a significant reduction in encoding time. The results show that multi-view clustering has a promising application in video encoding and can reduce the complexity substantially with negligible impact on quality. The results show that the proposed method considerably reduces encoding time with a negligible loss in quality.