Modelling Nonlinear Dynamic Textures using Hybrid DWT–DCT and Kernel PCA with GPU

• Published in: Journal of the Institution of Engineers (India). Series B, Electrical Engineering, Electronics and telecommunication engineering, Computer engineering Vol. 97; no. 4; pp. 549 - 555
• Main Authors: Ghadekar, Premanand Pralhad, Chopade, Nilkanth Bhikaji
• Format: Journal Article
• Language: English
• Published: New Delhi Springer India 01-12-2016; Springer Nature B.V
• Subjects: Color coding; Communications Engineering; Compression ratio; Engineering; Graphics processing units; Kernels; Networks; Original Contribution; Principal components analysis; Randomness; Redundancy; Self-similarity; Texture; KPCA; Nonlinear; C; DTU; Hybrid DWT–DCT; YC; GPU
• ISSN: 2250-2106; 2250-2114
• DOI: 10.1007/s40031-016-0220-1

Most of the real-world dynamic textures are nonlinear, non-stationary, and irregular. Nonlinear motion also has some repetition of motion, but it exhibits high variation, stochasticity, and randomness. Hybrid DWT–DCT and Kernel Principal Component Analysis (KPCA) with YC
b
C
r
/YIQ colour coding using the Dynamic Texture Unit (DTU) approach is proposed to model a nonlinear dynamic texture, which provides better results than state-of-art methods in terms of PSNR, compression ratio, model coefficients, and model size. Dynamic texture is decomposed into DTUs as they help to extract temporal self-similarity. Hybrid DWT–DCT is used to extract spatial redundancy. YC
b
C
r
/YIQ colour encoding is performed to capture chromatic correlation. KPCA is applied to capture nonlinear motion. Further, the proposed algorithm is implemented on Graphics Processing Unit (GPU), which comprise of hundreds of small processors to decrease time complexity and to achieve parallelism.