A Review on Visual Recognition of RGB Images and Videos by Learning from RGB-D Data

International Conference on Recent Advancements and Effectual Researches in Engineering Science and Technology

Jose, Alphonsa^1 ; Sreejith, V.^2

Electronics and Communication Engineering, St. Josephs College of Engineering and Technology, Palai, Kerala, India^1

Dept. ECE, St. Josephs College of Engineering and Technology, Palai, Kerala, India^2

关键词: Action recognition;    Adaptation techniques;    Data distribution;    Depth information;    Projection matrix;    Training and testing;    Unified framework;    Visual recognition;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/396/1/012040/pdf
DOI  :  10.1088/1757-899X/396/1/012040

来源: IOP

【 摘 要 】

Domain adaptation provides the possibility of research that allows changes in data distribution across training and testing datasets. Recognizing the RGB images by learning RGB-D data contains the additional depth information. The unsupervised domain adaptation (UDA) take advantage of the additional depth features. UDA deals with domain mismatch between the source and the target. The various adaptation techniques deals with the source and target domain. The domain mismatch is minimized by describing a projection matrix that is optimized by reducing the Maximum Mean Discrepancy (MMD) and aligning the source and target domains. To optimize the depth information the correlation between different types of features are to be maximized. Inorder to simultaneously cope with the domain mismatch issues, a unified framework called domain adaptation from multi-view to single-view (DAM2S) is learned. The effectiveness of the proposed methods for recognizing RGB images and videos by learning from RGB-D data is demonstrated by comprehensive experiments for object recognition, cross dataset and cross-view action recognition.