Robust view-invariant representation for classification and retrieval in image and video data

We propose a novel robust retrieval and classification system for video and motion events based on null space representation. The proposed view invariant representation based on the NSI operator is invariant to affine transformations and preserves the null space matrix. Different classification algorithm can be utilized for indexing and classification of the NSI operator for recognition and retrieval of motion events. To analyze the robustness of the system, the perturbed null operators have been derived with perturbation theory. Optimal sampling are subsequently investigated and the convergence of the SNR and the error ratio are proved. The simulation results are provided to demonstrate the effectiveness and robustness of our system in motion event indexing, retrieval and classification that is invariant to affine transformation due to camera motions.;Subsequently, we propose a novel general framework for tensor based null space affine invariants (TNSI) with a linear classifier for high order data classification and retrieval. We first derive TNSI, which is perfectly invariant to multidimensional affine transformations due to camera motions for multiple motion trajectories in consecutive motion events. We subsequently propose an efficient classification and retrieval system relying on TNSI for archiving and searching motion events consisting of multiple motion trajectories. The simulation results demonstrate superior performance of the proposed systems.;Moreover, we consider the splitting and merging of null space view invariant representation in the video database with partial queries and dynamical updatings. We present a novel robust multi---dimensional Localized Null Space and associated dynamic updating and downdating techniques, thus allowing classification and retrieval in the presence of affine transformations and partial information. We further determine the optimal segmentation of the data by minimizing a distortion criterion. We demonstrate the effectiveness and robustness of the proposed techniques for motion event classification and retrieval applications by posing different affine transformations of partial queries.;Finally, we propose the Non-linear Kernel Space Invariants (NKSI) for non-linear transformation of the raw data and Bilinear Invariants (BI) for view invariant retrieval of raw data with unequal length of different dimensions. We also extend the concept of Bilinear Invariants to Tensor Multilinear Invariants for high dimensional data. We provide the simulation results to demonstrate the effectiveness of our approach.