Spatiotemporal Saliency Detection Research Articles

MULTI-MODAL GRAPHNET LEARNING-BASED FEATURE EXTRACTION FOR SPATIOTEMPORAL SALIENCY DETECTION ON MULTIMEDIA VIDEOS

In multimedia content analysis, spatiotemporal saliency detection plays a crucial role in understanding visual data. However, existing methods often struggle with efficiently capturing complex patterns in videos. To address this, we propose a Multi-modal GraphNet Learning-Based Feature Extraction approach. Our method integrates multi-modal information from both spatial and temporal domains to enhance saliency detection accuracy. By leveraging GraphNet, we effectively model the intricate relationships among video frames. We validate our approach on a diverse set of multimedia videos, demonstrating significant improvements in saliency detection performance. Specifically, our method achieves an average precision of 0.85 and a recall of 0.78, outperforming state-of-the-art techniques. Furthermore, our approach exhibits robustness across various video types and scenarios. Through experimental evaluation, we confirm the efficacy of our proposed method in enhancing spatiotemporal saliency detection. This work contributes to advancing the field of multimedia analysis, offering a promising solution for understanding visual content in videos.

Video Saliency Detection by using an Enhance Methodology Involving a Combination of 3DCNN with Histograms

When watching pictures or videos, the Human Visual System has the potential to concentrate on important locations. Saliency detection is a tool for detecting the abnormality and randomness of images or videos by replicating the human visual system. Video saliency detection has received a lot of attention in recent decades, but due to challenging temporal abstraction and fusion for spatial saliency, computational modelling of spatial perception for video sequences is still limited.Unlike methods for detection of salient objects in still images, one of the most difficult aspects of video saliency detection is figuring out how to isolate and integrate spatial and temporal features.Saliency detection, which is basically a tool to recognize areas in images and videos that catch the attention of the human visual system, may benefit multimedia applications such as video or image retrieval, copy detection, and so on. As the two crucial steps in trajectory-based video classification methods are feature point identification and local feature extraction. We suggest a new spatio-temporal saliency detection using an enhanced 3D Conventional neural network with an inclusion of histogram for optical and orient gradient in this paper.

Depth-aware salient object segmentation

Depth-aware salient object segmentation

Video saliency detection by gestalt theory

Image saliency detection has been widely explored in recent decades, but computational modeling of visual attention for video sequences is limited due to complicated temporal saliency extraction and fusion of spatial and temporal saliency. Inspired by Gestalt theory, we introduce a novel spatiotemporal saliency detection model in this study. First, we compute spatial and temporal saliency maps by low-level visual features. And then we merge these two saliency maps for spatiotemporal saliency prediction of video sequences. The spatial saliency map is calculated by extracting three kinds of features including color, luminance, and texture, while the temporal saliency map is computed by extracting motion features estimated from video sequences. A novel adaptive entropy-based uncertainty weighting method is designed to fuse spatial and temporal saliency maps to predict the final spatiotemporal saliency map by Gestalt theory. The Gestalt principle of similarity is used to estimate spatial uncertainty from spatial saliency, while temporal uncertainty is computed from temporal saliency by the Gestalt principle of common fate. Experimental results on three large-scale databases show that our method can predict visual saliency more accurately than the state-of-art spatiotemporal saliency detection algorithms.

Motion-Aware Rapid Video Saliency Detection

In this paper, we propose a computationally efficient and consistently accurate spatiotemporal salient object detection method to identify the most noticeable object in a video sequence. Intuitively, the underlying motion in a video is a more stable saliency indicator than the apparent color cues that often contain significant variations and complex structures. Based on this observation, we build an efficient and accurate spatiotemporal saliency detection method that uses motion information as a leverage to locate the most dynamic regions in a video sequence. We first analyze the optical flow field to obtain foreground priors, and then incorporate spatial saliency features such as appearance contrasts and compactness measures, into a multi-cue integration framework to combine various saliency cues and achieve temporal consistency. Rigorous experiments on the challenging SegTrackV1, SegTrackV2, and FBMS datasets demonstrate that our method generates comparable or superior performance to state-of-the-art methods while running almost 100× faster at only 0.08 sec/frame. Promising performance and rapid speed imply that the proposed spatiotemporal saliency method can be easily involved in various vision applications.

Spatio-temporal saliency detection using objectness measure

Spatio-temporal saliency detection has gradually gained much attention in various computer vision applications such as intelligent video advertising and visual tracking. In this paper, we present a new approach based on the spatial and temporal information of the input video frame which aims to find the similar salient objects is proposed. First, objectness measure is performed to highlight the regions that may contain the object of interest. Then, for each candidate, newly proposed motion distinctiveness cues and static features including contrast measure and spatial distance are used to compute saliency maps. Experiments over two widely benchmark datasets, using several evaluation metrics such as mean absolute error, F score and area under the ROC curve measures, show the efficiency of our saliency approach compared to recent state-of-the-art methods. More interestingly, our attended scenes locations are coherent with the ground truth video frames. On SegTrack v2 and Fukuchi datasets, our proposed method yielded an overall mean absolute error, respectively, of 0.0669 and 0.0794. These results indicate the potential of our proposed framework in detecting motion salient objects.

Video saliency detection based on low-level saliency fusion and saliency-aware geodesic

We present a spatiotemporal saliency detection method for videos. In contrast to previous methods that focus on exploiting the different underlying saliency cues or ignore motion information, the proposed method aims to use both appearance information based on spatial edges and spatial color saliency and motion information based on temporal motion boundaries as indicators of foreground object locations. Spatial color saliency is obtained from the fusion of three color features: color edge connectivity, color rarity, and color compactness. Subsequently, we further smooth the color saliency to eliminate background noises and to further boost the detection accuracy. Then, we propose a strategy-based low-level saliency fusion that guarantees to complementarily employ the smoothed color saliency, spatial edges, and temporal motion boundaries clues toward producing high-accuracy low-level saliency. Subsequently, we generate framewise spatiotemporal saliency maps using a geodesic distance from the low-level saliency. Subsequently, high-quality results are obtained through the geodesic distance to the background area in the subsequent frames. Extensive quantitative and qualitative experiments on three public video datasets demonstrate the superiority of the proposed method over the state-of-the-art algorithms.

Correction: A parallel spatiotemporal saliency and discriminative online learning method for visual target tracking in aerial videos.

[This corrects the article DOI: 10.1371/journal.pone.0192246.].

A parallel spatiotemporal saliency and discriminative online learning method for visual target tracking in aerial videos.

Visual tracking in aerial videos is a challenging task in computer vision and remote sensing technologies due to appearance variation difficulties. Appearance variations are caused by camera and target motion, low resolution noisy images, scale changes, and pose variations. Various approaches have been proposed to deal with appearance variation difficulties in aerial videos, and amongst these methods, the spatiotemporal saliency detection approach reported promising results in the context of moving target detection. However, it is not accurate for moving target detection when visual tracking is performed under appearance variations. In this study, a visual tracking method is proposed based on spatiotemporal saliency and discriminative online learning methods to deal with appearance variations difficulties. Temporal saliency is used to represent moving target regions, and it was extracted based on the frame difference with Sauvola local adaptive thresholding algorithms. The spatial saliency is used to represent the target appearance details in candidate moving regions. SLIC superpixel segmentation, color, and moment features can be used to compute feature uniqueness and spatial compactness of saliency measurements to detect spatial saliency. It is a time consuming process, which prompted the development of a parallel algorithm to optimize and distribute the saliency detection processes that are loaded into the multi-processors. Spatiotemporal saliency is then obtained by combining the temporal and spatial saliencies to represent moving targets. Finally, a discriminative online learning algorithm was applied to generate a sample model based on spatiotemporal saliency. This sample model is then incrementally updated to detect the target in appearance variation conditions. Experiments conducted on the VIVID dataset demonstrated that the proposed visual tracking method is effective and is computationally efficient compared to state-of-the-art methods.

A deep-learning based feature hybrid framework for spatiotemporal saliency detection inside videos

Abstract Although research on detection of saliency and visual attention has been active over recent years, most of the existing work focuses on still image rather than video based saliency. In this paper, a deep learning based hybrid spatiotemporal saliency feature extraction framework is proposed for saliency detection from video footages. The deep learning model is used for the extraction of high-level features from raw video data, and they are then integrated with other high-level features. The deep learning network has been found extremely effective for extracting hidden features than that of conventional handcrafted methodology. The effectiveness for using hybrid high-level features for saliency detection in video is demonstrated in this work. Rather than using only one static image, the proposed deep learning model take several consecutive frames as input and both the spatial and temporal characteristics are considered when computing saliency maps. The efficacy of the proposed hybrid feature framework is evaluated by five databases with human gaze complex scenes. Experimental results show that the proposed model outperforms five other state-of-the-art video saliency detection approaches. In addition, the proposed framework is found useful for other video content based applications such as video highlights. As a result, a large movie clip dataset together with labeled video highlights is generated.

Video saliency detection via bagging-based prediction and spatiotemporal propagation

The task of spatiotemporal saliency detection is to distinguish the salient objects from background across all the frames in the video. Although many spatiotemporal models have been designed from various aspects, it is still a very challenging task for handing the unconstrained videos with complicated motions and complex scenes. Therefore, in this paper we propose a novel spatiotemporal saliency model to estimate salient objects in unconstrained videos. Specifically, a bagging-based saliency prediction model, i.e. an ensembling regressor, which is the combination of random forest regressors learned from undersampled training sets, is first used to perform saliency prediction for each current frame. Then, both forward and backward propagation within a local temporal window are deployed on each current frame to make a complement to the predicted saliency map and yield the temporal saliency map, in which the backward propagation is constructed based on the temporary saliency estimation of the following frames. Finally, by building the appearance and motion based graphs in a parallel way, spatial propagation is employed over the temporal saliency map to generate the final spatiotemporal saliency map. Through experiments on two challenging datasets, the proposed model consistently outperforms the state-of-the-art models for popping out salient objects in unconstrained videos.

Spatiotemporal Saliency Estimation by Spectral Foreground Detection

We present a novel approach for spatiotemporal saliency detection by optimizing a unified criterion of color contrast, motion contrast, appearance, and background cues. To this end, we first abstract the video by temporal superpixels. Second, we propose a novel graph structure exploiting the saliency cues to assign the edge weights. The salient segments are then extracted by applying a spectral foreground detection method, quantum cuts, on this graph. We evaluate our approach on several public datasets for video saliency and activity localization to demonstrate the favorable performance of the proposed video quantum cuts compared to the state of the art.

Pattern mining-based video saliency detection: Application to moving object segmentation

In this paper, we present a new model for spatiotemporal saliency detection. Instead of previous works which combine the image saliency in the spatial domain with motion cues to build their video saliency model, we propose to apply the pattern mining (PM) algorithm. From initial saliency maps computed in spatial and temporal domains, discriminative spatiotemporal saliency patterns can be recognized and their label information is propagated to obtain the final saliency map. Our model ensures a good compromise between image saliency and motion saliency and presents an accurate prediction to estimate salient regions in comparison with other methods for video saliency detection. Finally, as an application of our algorithm, our spatiotemporal saliency map is combined with appearance models and dynamic location models into an energy minimization framework to segment salient moving object. Experiments show a good performance of our algorithm for moving object segmentation (MOS) on benchmark datasets.

Novelty-based Spatiotemporal Saliency Detection for Prediction of Gaze in Egocentric Video

The automated analysis of video captured from a first-person perspective has gained increased interest since the advent of marketed miniaturized wearable cameras. With this a person is taking visual measurements about the world in a sequence of fixations which contain relevant information about the most salient parts of the environment and the goals of the actor. We present a novel model for gaze prediction in egocentric video based on the spatiotemporal visual information captured from the wearer’s camera, specifically extended using a subjective function of surprise by means of motion memory, referring to the human aspect of visual attention. Spatiotemporal saliency detection is computed in a bioinspired framework using a superposition of superpixel- and contrast based conspicuity maps as well as an optical flow based motion saliency map. Motion is further processed into a motion novelty map that is constructed by a comparison between most recent motion information with an exponentially decreasing memory of motion information. The innovative motion novelty map is experienced to be able to provide a significant increase in the performance of gaze prediction. Experimental results are gained from egocentric videos using eye-tracking glasses in a natural shopping task and prove a 6.48% increase in the mean saliency at a fixation in terms of a measure of mimicking human attention.

Consistent Video Saliency Using Local Gradient Flow Optimization and Global Refinement.

We present a novel spatiotemporal saliency detection method to estimate salient regions in videos based on the gradient flow field and energy optimization. The proposed gradient flow field incorporates two distinctive features: 1) intra-frame boundary information and 2) inter-frame motion information together for indicating the salient regions. Based on the effective utilization of both intra-frame and inter-frame information in the gradient flow field, our algorithm is robust enough to estimate the object and background in complex scenes with various motion patterns and appearances. Then, we introduce local as well as global contrast saliency measures using the foreground and background information estimated from the gradient flow field. These enhanced contrast saliency cues uniformly highlight an entire object. We further propose a new energy function to encourage the spatiotemporal consistency of the output saliency maps, which is seldom explored in previous video saliency methods. The experimental results show that the proposed algorithm outperforms state-of-the-art video saliency detection methods.

Spatiotemporal saliency detection based on superpixel-level trajectory

In this paper, we propose a novel spatiotemporal saliency model based on superpixel-level trajectories for saliency detection in videos. The input video is first decomposed into a set of temporally consistent superpixels, on which superpixel-level trajectories are directly generated, and motion histograms at superpixel level as well as frame level are extracted. Based on motion vector fields of multiple successive frames, the inside–outside maps are estimated to roughly indicate whether pixels are inside or outside objects with motion different from background. Then two descriptors, i.e. accumulated motion histogram and trajectory velocity entropy, are exploited to characterize the short-term and long-term temporal features of superpixel-level trajectories. Based on trajectory descriptors and inside–outside maps, superpixel-level trajectory distinctiveness is evaluated and trajectory classification is performed to obtain trajectory-level temporal saliency. Superpixel-level and pixel-level temporal saliency maps are generated in turn by exploiting motion similarity with neighboring superpixels around each trajectory, and color-spatial similarity with neighboring superpixels around each pixel, respectively. Finally, a quality-guided fusion method is proposed to integrate the pixel-level temporal saliency map with the pixel-level spatial saliency map, which is generated based on global contrast and spatial sparsity of superpixels, to generate the pixel-level spatiotemporal saliency map with reasonable quality. Experimental results on two public video datasets demonstrate that the proposed model outperforms the state-of-the-art spatiotemporal saliency models on saliency detection performance.

Spatiotemporal saliency detection for video sequences based on random walk with restart.

A novel saliency detection algorithm for video sequences based on the random walk with restart (RWR) is proposed in this paper. We adopt RWR to detect spatially and temporally salient regions. More specifically, we first find a temporal saliency distribution using the features of motion distinctiveness, temporal consistency, and abrupt change. Among them, the motion distinctiveness is derived by comparing the motion profiles of image patches. Then, we employ the temporal saliency distribution as a restarting distribution of the random walker. In addition, we design the transition probability matrix for the walker using the spatial features of intensity, color, and compactness. Finally, we estimate the spatiotemporal saliency distribution by finding the steady-state distribution of the walker. The proposed algorithm detects foreground salient objects faithfully, while suppressing cluttered backgrounds effectively, by incorporating the spatial transition matrix and the temporal restarting distribution systematically. Experimental results on various video sequences demonstrate that the proposed algorithm outperforms conventional saliency detection algorithms qualitatively and quantitatively.

Kernel regression in mixed feature spaces for spatio-temporal saliency detection

Spatio-temporal saliency detection has attracted lots of research interests due to its competitive performance on wide multimedia applications. For spatio-temporal saliency detection, existing bottom-up algorithms often over-simplify the fusion strategy, which results in the inferior performance than the human vision system. In this paper, a novel bottom-up spatio-temporal saliency model is proposed to improve the accuracy of attentional region estimation in videos through fully exploiting the merit of fusion. In order to represent the space constructed by several types of features such as location, appearance and temporal cues extracted from video, kernel regression in mixed feature spaces (KR-MFS) including three approximation entity-models is proposed. Using KR-MFS, a hybrid fusion strategy which considers the combination of spatial and temporal saliency of each individual unit and incorporates the impacts from the neighboring units is presented and embedded into the spatio-temporal saliency model. The proposed model has been evaluated on the publicly available dataset. Experimental results show that the proposed spatio-temporal saliency model can achieve better performance than the state-of-the-art approaches.

Spatiotemporal Saliency Detection Using Textural Contrast and Its Applications

Saliency detection has been extensively studied due to its promising contributions for various computer vision applications. However, most existing methods are easily biased toward edges or corners, which are statistically significant, but not necessarily relevant. Moreover, they often fail to find salient regions in complex scenes due to ambiguities between salient regions and highly textured backgrounds. In this paper, we present a novel unified framework for spatiotemporal saliency detection based on textural contrast. Our method is simple and robust, yet biologically plausible; thus, it can be easily extended to various applications, such as image retargeting, object segmentation, and video surveillance. Based on various datasets, we conduct comparative evaluations of 12 representative saliency detection models presented in the literature, and the results show that the proposed scheme outperforms other previously developed methods in detecting salient regions of the static and dynamic scenes.

Regularized Feature Reconstruction for Spatio-Temporal Saliency Detection

Multimedia applications such as image or video retrieval, copy detection, and so forth can benefit from saliency detection, which is essentially a method to identify areas in images and videos that capture the attention of the human visual system. In this paper, we propose a new spatio-temporal saliency detection framework on the basis of regularized feature reconstruction. Specifically, for video saliency detection, both the temporal and spatial saliency detection are considered. For temporal saliency, we model the movement of the target patch as a reconstruction process using the patches in neighboring frames. A Laplacian smoothing term is introduced to model the coherent motion trajectories. With psychological findings that abrupt stimulus could cause a rapid and involuntary deployment of attention, our temporal model combines the reconstruction error, regularizer, and local trajectory contrast to measure the temporal saliency. For spatial saliency, a similar sparse reconstruction process is adopted to capture the regions with high center-surround contrast. Finally, the temporal saliency and spatial saliency are combined together to favor salient regions with high confidence for video saliency detection. We also apply the spatial saliency part of the spatio-temporal model to image saliency detection. Experimental results on a human fixation video dataset and an image saliency detection dataset show that our method achieves the best performance over several state-of-the-art approaches.