Salient Objects In Videos Research Articles

Flow-Edge-Net: Video Saliency Detection Based on Optical Flow and Edge-Weighted Balance Loss

Optical flow networks have been widely utilized for video saliency detection (VSD) due to their effective performance in capturing the motion of objects. However, the use of optical flow blurs the edges of salient objects and leads to the problems of poorly defined object boundaries. To address this issue, we propose an optical flow-based edge-weighted loss function, to train a network called Flow-Edge-Net, which can balance the weights of the foreground and background information at the edges of video frames. It has achieved superior performance in detecting salient boundaries. Specifically, we propose two complementary encoding and decoding networks based on the concept of decoupling. That is, the optical flow network focuses on moving objects, while the edge network, based on the encoder-decoder structure, focuses on edge information. As the two networks output features of the same dimension and are from the same input, our proposed self-designed adaptive weighted feature fusion module can compare and integrate the edge information and location information from the two networks through adaptive weighting. The proposed method has been evaluated on five widely used databases. Experiment results demonstrate the superior performance of the proposed Flow-Edge-Net in locating salient objects, with accurate and refined edges. The proposed method achieves superior performance over the state-of-the-art methods in detecting salient objects in videos.

STI-Net: Spatiotemporal integration network for video saliency detection

Image saliency detection, to which much effort has been devoted in recent years, has advanced significantly. In contrast, the community has paid little attention to video saliency detection. Especially, existing video saliency models are very likely to fail in videos with difficult scenarios such as fast motion, dynamic background, and nonrigid deformation. Furthermore, performing video saliency detection directly using image saliency models that ignore video temporal information is inappropriate. To alleviate this issue, this study proposes a novel end-to-end spatiotemporal integration network (STI-Net) for detecting salient objects in videos. Specifically, our method is made up of three key steps: feature aggregation, saliency prediction, and saliency fusion, which are used sequentially to generate spatiotemporal deep feature maps, coarse saliency predictions, and the final saliency map. The key advantage of our model lies in the comprehensive exploration of spatial and temporal information across the entire network, where the two features interact with each other in the feature aggregation step, are used to construct boundary cue in the saliency prediction step, and also serve as the original information in the saliency fusion step. As a result, the generated spatiotemporal deep feature maps can precisely and completely characterize the salient objects, and the coarse saliency predictions have well-defined boundaries, effectively improving the final saliency map's quality. Furthermore, “shortcut connections” are introduced into our model to make the proposed network easy to train and obtain accurate results when the network is deep. Extensive experimental results on two publicly available challenging video datasets demonstrate the effectiveness of the proposed model, which achieves comparable performance to state-of-the-art saliency models.

Self-Sufficient Feature Enhancing Networks for Video Salient Object Detection

Detecting salient objects in videos is a very challenging task. Current state-of-the-art methods are dominated by motion based deep neural networks, among which optical flow is often leveraged as motion representation. Though with robust performance, these optical flow-based video salient object detection methods face at least two problems that may hinder their generalization and application. First, computing optical flow as a pre-processing step does not support direct end-to-end learning; second, little attention has been given to the quality of visual features due to high computational cost of spatiotemporal feature encoding. In this paper we propose a novel self-sufficient feature enhancing network (SFENet) for video salient object detection, which leverages optical flow estimation as an auxiliary task while being end-to-end trainable. With a joint training scheme of both salient object detection and optical flow estimation, its multi-task architecture can be totally self-sufficient for achieving good performance without any pre-processing. Furthermore, for improving feature quality, we design four lightweight modules in spatial and temporal domains, including cross-layer fusion, multi-level warping, spatial-channel attention and boundary-aware refinement. The proposed method is evaluated through extensive experiments on five video salient object detection datasets. Experimental results show that our SFENet can be easily trained with fast convergence speed. It significantly outperforms previous methods in terms of various evaluation metrics. Moreover, with optical flow estimation and unsupervised video object segmentation as example applications, our method also yields state-of-the-art results on standard datasets.

DS-Net: Dynamic spatiotemporal network for video salient object detection

As moving objects always draw more attention of human eyes, the temporal motion information is always exploited complementarily with spatial information to detect salient objects in videos. Although efficient tools such as optical flow have been proposed to extract temporal motion information, it often encounters difficulties when used for saliency detection due to the movement of camera or the partial movement of salient objects. In this paper, we investigate the complementary roles of spatial and temporal information and propose a novel dynamic spatiotemporal network (DS-Net) for more effective fusion of spatiotemporal information. We construct a symmetric two-bypass network to explicitly extract spatial and temporal features. A dynamic weight generator (DWG) is designed to automatically learn the reliability of corresponding saliency branch. And a top-down cross attentive aggregation (CAA) procedure is designed to facilitate dynamic complementary aggregation of spatiotemporal features. Finally, the features are modified by spatial attention with the guidance of coarse saliency map and then go through decoder part for final saliency map. Experimental results on five benchmarks VOS, DAVIS, FBMS, SegV2, and ViSal demonstrate that the proposed method achieves superior performance than state-of-the-art algorithms. The source code is available at https://github.com/TJUMMG/DS-Net.

Video Captioning with Object-Aware Spatio-Temporal Correlation and Aggregation.

Video captioning is a significant challenging task in computer vision and natural language processing, aiming to automatically describe video content by natural language sentences. Comprehensive understanding of video is the key for accurate video captioning, which needs to not only capture the global content and salient objects in video, but also understand the spatio-temporal relations of objects, including their temporal trajectories and spatial relationships. Thus, it is important for video captioning to capture the objects' relationships both within and across frames. Therefore, in this paper, we propose an object-aware spatio-temporal graph (OSTG) approach for video captioning. It constructs spatio-temporal graphs to depict objects with their relations, where the temporal graphs represent objects' inter-frame dynamics, and the spatial graphs represent objects' intra-frame interactive relationships. The main novelties and advantages are: (1) Bidirectional temporal alignment: Bidirectional temporal graph is constructed along and reversely along the temporal order to perform bidirectional temporal alignment for objects across different frames, which provides complementary clues to capture the inter-frame temporal trajectories for each salient object. (2) Graph based spatial relation learning: Spatial relation graph is constructed among objects in each frame by considering their relative spatial locations and semantic correlations, which is exploited to learn relation features that encode intra-frame relationships for salient objects. (3) Object-aware feature aggregation: Trainable VLAD (vector of locally aggregated descriptors) models are deployed to perform object-aware feature aggregation on objects' local features, which learn discriminative aggregated representations for better video captioning. A hierarchical attention mechanism is also developed to distinguish contributions of different object instances. Experiments on two widely-used datasets, MSR-VTT and MSVD, demonstrate our proposed approach achieves state-of-the-art performances in terms of BLEU@4, METEOR and CIDEr metrics.

A cellular automata based approach to track salient objects in videos

In this paper we present an algorithm to track the motion of a salient object using Cellular Automata (CA). The overall work, taking inspiration from recent research on insect sensory motor system, investigates the application of non conventional computer vision approaches to evaluate their effectiveness in fulfilling this task. The proposed system employs the Sobel operator to individual frames, performing further elaborations through a CA, with the aim of detecting and characterizing moving entities within the field of view to support collision avoidance from the perspective of the viewer. The paper formally describes the adopted approach as well as its experimentation videos representing plausible situations.

Video Saliency Detection via Sparsity-Based Reconstruction and Propagation.

Video saliency detection aims to continuously discover the motion-related salient objects from the video sequences. Since it needs to consider the spatial and temporal constraints jointly, video saliency detection is more challenging than image saliency detection. In this paper, we propose a new method to detect the salient objects in video based on sparse reconstruction and propagation. With the assistance of novel static and motion priors, a single-frame saliency model is first designed to represent the spatial saliency in each individual frame via the sparsity-based reconstruction. Then, through a progressive sparsity-based propagation, the sequential correspondence in the temporal space is captured to produce the inter-frame saliency map. Finally, these two maps are incorporated into a global optimization model to achieve spatio-temporal smoothness and global consistency of the salient object in the whole video. The experiments on three large-scale video saliency datasets demonstrate that the proposed method outperforms the state-of-the-art algorithms both qualitatively and quantitatively.

Video Salient Object Detection Using Spatiotemporal Deep Features.

This paper presents a method for detecting salient objects in videos, where temporal information in addition to spatial information is fully taken into account. Following recent reports on the advantage of deep features over conventional handcrafted features, we propose a new set of spatiotemporal deep (STD) features that utilize local and global contexts over frames. We also propose new spatiotemporal conditional random field (STCRF) to compute saliency from STD features. STCRF is our extension of CRF to the temporal domain and describes the relationships among neighboring regions both in a frame and over frames. STCRF leads to temporally consistent saliency maps over frames, contributing to accurate detection of salient objects' boundaries and noise reduction during detection. Our proposed method first segments an input video into multiple scales and then computes a saliency map at each scale level using STD features with STCRF. The final saliency map is computed by fusing saliency maps at different scale levels. Our experiments, using publicly available benchmark datasets, confirm that the proposed method significantly outperforms the state-of-the-art methods. We also applied our saliency computation to the video object segmentation task, showing that our method outperforms existing video object segmentation methods.

Fusing disparate object signatures for salient object detection in video

We present a novel spatiotemporal saliency model for object detection in videos. In contrast to previous methods focusing on exploiting or incorporating different saliency cues, the proposed method aims to use object signatures which can be identified by any kinds of object segmentation methods. We integrate two distinctive saliency maps, which are respectively computed from object proposals of an appearance-dominated method and a motion-dominated algorithm, to obtain a refined spatiotemporal saliency maps. This enables the method to achieve good robustness and precision in identifying salient objects in videos under various challenging conditions. First, an improved appearance-based and a modified motion-based segmentation approaches are separately utilized to extract two kinds of candidate foreground objects. Second, with these captured object signatures, we design a new approach to filter the extracted noisy object pixels and label foreground superpixels in each object signature channel. Third, we introduce a foreground connectivity saliency measure to compute two types of saliency maps, from which an adaptive fusion strategy is exploited to obtain the final spatiotemporal saliency maps for salient object detection in a video. Both quantitative and qualitative experiments on several challenging video benchmarks demonstrate that the proposed method outperforms existing state-of-the-art approaches.

Video-based salient object detection via spatio-temporal difference and coherence

Salient object detection aims to extract the attractive objects in images and videos. It can support various robotics tasks and multimedia applications, such as object detection, action recognition and scene analysis. However, efficient detection of salient objects in videos still faces many challenges as compared to that in still images. In this paper, we propose a novel video-based salient object detection method by exploring spatio-temporal characteristics of video content, i.e., spatial-temporal difference and spatial-temporal coherence. First, we initialize the saliency map for each keyframe by deriving spatial-temporal difference from color cue and motion cue. Next, we generate the saliency maps of other frames by propagating the saliency intra and inter frames with the constraint of spatio-temporal coherence. Finally, the saliency maps of both keyframes and non-keyframes are refined in the saliency propagation. In this way, we can detect salient objects in videos efficiently by exploring their spatio-temporal characteristics. We evaluate the proposed method on two public datasets, named SegTrackV2 and UVSD. The experimental results show that our method outperforms the state-of-the-art methods when taking account of both effectiveness and efficiency.

Coherency Based Spatio-Temporal Saliency Detection for Video Object Segmentation

Extracting moving and salient objects from videos is important for many applications like surveillance and video retargeting. In this paper we use spatial and temporal coherency information to segment salient objects in videos. While many methods use motion information from videos, they do not exploit coherency information which has the potential to give more accurate saliency maps. Spatial coherency maps identify regions belonging to regular objects, while temporal coherency maps identify regions with high coherent motion. The two coherency maps are combined to obtain the final spatio-temporal map identifying salient regions. Experimental results on public datasets show that our method outperforms two competing methods in segmenting moving objects from videos.