Inverse Sparse Group Lasso Model For Robust Object Tracking - 2017 PROJECT TITLE :Inverse Sparse Group Lasso Model For Robust Object Tracking - 2017ABSTRACT:Sparse illustration has been applied to visual tracking. The visual tracking models primarily based on sparse representation use a template set as dictionary atoms to reconstruct candidate samples without considering similarity among atoms. In this paper, we tend to gift a robust tracking methodology primarily based on the inverse sparse group lasso model. Our method exploits each the group structure of similar candidate samples and the local structure between templates and samples. Unlike the standard sparse representation, the templates are encoded by the candidate samples, and similar samples are selected to reconstruct the template at the group level, that facilitates inter-group sparsity. Every sample group achieves the intra-cluster sparsity therefore that the information between the connected dictionary atoms is taken into consideration. Moreover, the native structure between templates and samples is considered to make the reconstruction model, that ensures that the computed coefficients similarity is in line with the similarity between templates and samples. A gradient descent-based optimization method is employed and a sparse mapping table is obtained using the coefficient matrix and hash-distance weight matrix. Experiments were conducted with publicly obtainable datasets and a comparison study was performed against 20 state-of-the-art strategies. Each qualitative and quantitative results are reported. The proposed method demonstrated improved robustness and accuracy and exhibited comparable computational complexity. Did you like this research project? To get this research project Guidelines, Training and Code... Click Here facebook twitter google+ linkedin stumble pinterest Rgb-Nir Imaging With Exposure Bracketing For Joint Denoising And Deblurring Of Low-Light Color Images - 2017 Image Retrieval Based On Deep Convolutional Neural Networks And Binary Hashing Learning - 2017