Visual Saliency Detection Using Group Lasso Regularization in Videos of Natural Scenes

Abstract

Visual saliency is the ability of a vision system to promptly select the most relevant data in the scene and reduce the amount of visual data that needs to be processed. Thus, its applications for complex tasks such as object detection, object recognition and video compression have attained interest in computer vision studies. In this paper, we introduce a novel unsupervised method for detecting visual saliency in videos of natural scenes. For this, we divide a video into non-overlapping cuboids and create a matrix whose columns correspond to intensity values of these cuboids. Simultaneously, we segment the video using a hierarchical segmentation method and obtain super-voxels. A dictionary learned from the feature data matrix of the video is subsequently used to represent the video as coefficients of atoms. Then, these coefficients are decomposed into salient and nonsalient parts. We propose to use group lasso regularization to find the sparse representation of a video, which benefits from grouping information provided by super-voxels and extracted features from the cuboids. We find saliency regions by decomposing the feature matrix of a video into low-rank and sparse matrices by using robust principal component analysis matrix recovery method. The applicability of our method is tested on four video data sets of natural scenes. Our experiments provide promising results in terms of predicting eye movement using standard evaluation methods. In addition, we show our video saliency can be used to improve Communicated by the performance of human action recognition on a standard dataset.

Resting-State Brain Functional Hyper-Network Construction Based on Elastic Net and Group Lasso Methods

“…To solve the problem of the grouping effect among brain regions, we propose two alternative methods to improve the construction of a hyper-network: (1) the elastic net (De Mol et al, 2008 ; Furqan and Siyal, 2016 ; Teipel et al, 2017 ) and (2) the group lasso method (Friedman et al, 2010a ; Yu et al, 2015 ; Souly and Shah, 2016 ). Then we extracted features using the different clustering coefficients defined by hyper-network to depict the functional brain network topology and performed non-parametric test to select those features with significant difference.…”

Human activity recognition by using MHIs of frame sequences

“…Accuracy (Souly and Shah, 2016) [21] 85.10% (Wang et al, 2009) [16] 85.60% (Le et al, 2011) [1] 86.50% (Kovashka and Grauman, 2010) [17] 87.20% (Wang et al, 2011) [18] 89.10% (Weinzaepfel et al, 2015) [22] 90.50% (Abdulmunem et al, 2016) [20] 90.90% (Ravanbakhsh et al, 2015) [37] 88.10% (Wang et al, 2018) [39] 91.89% (Zhou et al, 2017) [28] 90.00% Basic method 85.30% Proposed method 92.00% UCF-11 Methods Accuracy (Hasan et al, 2014) [2] 54.50% (Liu et al, 2009) [43] 71.20% (Ikizler-Cinbis et al, 2010) [36] 75.20% (Wang et al, 2011) [18] 84.20% (Sharma et al, 2015) [27] 84.90% (Cho et al, 2014) [19] 88.00% (Ravanbakhsh et al, 2015) [37] 77.10% (Wang et al, 2018) [39] 98.76% (Gammulle et al, 2017) [38] 89.20% (Gilbert et al, 2017) [3] 86.70% Basic method 82.40% Proposed method 92.40%…”

“…Thus the saliency guided 3D SIFT-HOOF (SGSH) feature was used for feature representation. Simultaneously, Souly and Shah [21] used group lasso regularization to find the sparse representation for video saliency detection.…”

A Novel Parameter Initialization Technique Using RBM-NN for Human Action Recognition

“…Action detection and recognition were performed using CNN based on pose appearance and motion. Souly et al [ 116 ] proposed an unsupervised method for detection using visual saliency [ 117 ] in videos. The video frames are divided into nonoverlapping cuboids and segmented using hierarchical segmentation to obtain the supervoxels from the cuboids.…”