As an essential problem in computer vision, salient object detection (SOD) has attracted an increasing amount of research attention over the years. Recent advances in SOD are predominantly led by deep learning-based solutions (named deep SOD). To enable in-depth understanding of deep SOD, in this paper, we provide a comprehensive survey covering various aspects, ranging from algorithm taxonomy to unsolved issues. In particular, we first review deep SOD algorithms from different perspectives, including network architecture, level of supervision, learning paradigm, and object-/instance-level detection. Following that, we summarize and analyze existing SOD datasets and evaluation metrics. Then, we benchmark a large group of representative SOD models, and provide detailed analyses of the comparison results. Moreover, we study the performance of SOD algorithms under different attribute settings, which has not been thoroughly explored previously, by constructing a novel SOD dataset with rich attribute annotations covering various salient object types, challenging factors, and scene categories. We further analyze, for the first time in the field, the robustness of SOD models to random input perturbations and adversarial attacks. We also look into the generalization and difficulty of existing SOD datasets. Finally, we discuss several open issues of SOD and outline future research directions.

Salient Object Detection in the Deep Learning Era: An In-Depth Survey

The use of RGB-D information for salient object detection (SOD) has been extensively explored in recent years. However, relatively few efforts have been put toward modeling SOD in real-world human activity scenes with RGB-D. In this article, we fill the gap by making the following contributions to RGB-D SOD: 1) we carefully collect a new S al i ent P erson (SIP) data set that consists of ~1 K high-resolution images that cover diverse real-world scenes from various viewpoints, poses, occlusions, illuminations, and background s; 2) we conduct a large-scale (and, so far, the most comprehensive) benchmark comparing contemporary methods, which has long been missing in the field and can serve as a baseline for future research, and we systematically summarize 32 popular models and evaluate 18 parts of 32 models on seven data sets containing a total of about 97k images; and 3) we propose a simple general architecture, called deep depth-depurator network (D3Net). It consists of a depth depurator unit (DDU) and a three-stream feature learning module (FLM), which performs low-quality depth map filtering and cross-modal feature learning, respectively. These components form a nested structure and are elaborately designed to be learned jointly. D3Net exceeds the performance of any prior contenders across all five metrics under consideration, thus serving as a strong model to advance research in this field. We also demonstrate that D3Net can be used to efficiently extract salient object masks from real scenes, enabling effective background-changing application with a speed of 65 frames/s on a single GPU. All the saliency maps, our new SIP data set, the D3Net model, and the evaluation tools are publicly available at https://github.com/DengPingFan/D3NetBenchmark .

Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarks

The large availability of depth sensors provides valuable complementary information for salient object detection (SOD) in RGBD images. However, due to the inherent difference between RGB and depth information, extracting features from the depth channel using ImageNet pre-trained backbone models and fusing them with RGB features directly are sub-optimal. In this paper, we utilize contrast prior, which used to be a dominant cue in none deep learning based SOD approaches, into CNNs-based architecture to enhance the depth information. The enhanced depth cues are further integrated with RGB features for SOD, using a novel fluid pyramid integration, which can make better use of multi-scale cross-modal features. Comprehensive experiments on 5 challenging benchmark datasets demonstrate the superiority of the architecture CPFP over 9 state-of-the-art alternative methods.

/pdf/contrast-prior-and-fluid-pyramid-integration-for-rgbd-13gg74o2nz.pdf

Contrast Prior and Fluid Pyramid Integration for RGBD Salient Object Detection

Salient object detection from RGB-D images aims to utilize both the depth view and RGB view to automatically localize objects of human interest in the scene. Although a few earlier efforts have been devoted to the study of this paper in recent years, two major challenges still remain: 1) how to leverage the depth view effectively to model the depth-induced saliency and 2) how to implement an optimal combination of the RGB view and depth view, which can make full use of complementary information among them. To address these two challenges, this paper proposes a novel framework based on convolutional neural networks (CNNs), which transfers the structure of the RGB-based deep neural network to be applicable for depth view and fuses the deep representations of both views automatically to obtain the final saliency map. In the proposed framework, the first challenge is modeled as a cross-view transfer problem and addressed by using the task-relevant initialization and adding deep supervision in hidden layer. The second challenge is addressed by a multiview CNN fusion model through a combination layer connecting the representation layers of RGB view and depth view. Comprehensive experiments on four benchmark datasets demonstrate the significant and consistent improvements of the proposed approach over other state-of-the-art methods.

CNNs-Based RGB-D Saliency Detection via Cross-View Transfer and Multiview Fusion

In this work, we propose a novel depth-induced multi-scale recurrent attention network for saliency detection. It achieves dramatic performance especially in complex scenarios. There are three main contributions of our network that are experimentally demonstrated to have significant practical merits. First, we design an effective depth refinement block using residual connections to fully extract and fuse multi-level paired complementary cues from RGB and depth streams. Second, depth cues with abundant spatial information are innovatively combined with multi-scale context features for accurately locating salient objects. Third, we boost our model's performance by a novel recurrent attention module inspired by Internal Generative Mechanism of human brain. This module can generate more accurate saliency results via comprehensively learning the internal semantic relation of the fused feature and progressively optimizing local details with memory-oriented scene understanding. In addition, we create a large scale RGB-D dataset containing more complex scenarios, which can contribute to comprehensively evaluating saliency models. Extensive experiments on six public datasets and ours demonstrate that our method can accurately identify salient objects and achieve consistently superior performance over 16 state-of-the-art RGB and RGB-D approaches.

/pdf/depth-induced-multi-scale-recurrent-attention-network-for-oc6xzw6o8r.pdf

Depth-Induced Multi-Scale Recurrent Attention Network for Saliency Detection

Most previous works on saliency detection are dedicated to 2D images. Recently it has been shown that 3D visual information supplies a powerful cue for saliency analysis. In this paper, we propose a novel saliency method that works on depth images based on anisotropic center-surround difference. Instead of depending on absolute depth, we measure the saliency of a point by how much it outstands from surroundings, which takes the global depth structure into consideration. Besides, two common priors based on depth and location are used for refinement. The proposed method works within a complexity of O(N) and the evaluation on a dataset of over 1000 stereo images shows that our method outperforms state-of-the-art.

Depth saliency based on anisotropic center-surround difference

Most previous works on salient object detection concentrate on 2D images. In this paper, we propose to explore the power of depth cue for predicting salient regions. Our basic assumption is that a salient object tends to stand out from its surroundings in 3D space. To measure the object-to-surrounding contrast, we propose a novel depth feature which works on a single depth map. Besides, we integrate the 3D spatial prior into our method for saliency refinement. By sparse sampling and representing the image using superpixels, our method works very fast, whose complexity is linear to the image resolution. To segment the salient object, we also develop a saliency based method using adaptive thresholding and GrabCut. The proposed method is evaluated on two large datasets designed for depth-aware salient object detection. The results compared with several state-of-the-art 2D and depth-aware methods show that our method has the most satisfactory overall performance. HighlightsWe proposed a new depth feature for salient region detection.Spatial prior is integrated for saliency refinement.A saliency-based object segmentation method is presented.We built the largest dataset for depth-aware salient object detection evaluation.

Depth-aware salient object detection using anisotropic center-surround difference

In this paper, we propose a novel interactive image segmentation method for RGB-D images using hierarchical Graph Cut. Considering the characteristics of RGB channels and depth channel in RGB-D image, we utilize Euclidean distance on RGB space and geodesic distance on 3D space to measure how likely a pixel belongs to foreground or background in color and depth respectively, and integrate the color cue and depth cue into a unified Graph Cut framework to obtain the optimal segmentation result. Moreover, to overcome the low efficiency problem of Graph Cut in handling high resolution images, we accelerate the proposed method with hierarchical strategy. The experimental results show that our method outperforms the state-of-the-art methods with high efficiency.

https://mcg.nju.edu.cn/publication/2015/pcm15-gel.pdf

Interactive RGB-D Image Segmentation Using Hierarchical Graph Cut and Geodesic Distance

The goal of objectness estimation is to predict a moderate number of proposals of all possible objects in a given image with high efficiency. Most existing works solve this problem solely in conventional 2D color images. In this paper, we demonstrate that the depth information could benefit the estimation as a complementary cue to color information. After detailed analysis of depth characteristics, we present an adaptively integrated description for generic objects, which could take full advantages of both depth and color. With the proposed objectness description, the ambiguous area, especially the highly textured regions in original color maps, can be effectively discriminated. Meanwhile, the object boundary areas could be further emphasized, which leads to a more powerful objectness description. To evaluate the performance of the proposed approach, we conduct the experiments on two challenging datasets. The experimental results show that our proposed objectness description is more powerful and effective than state-of-the-art alternatives.

Adaptive integration of depth and color for objectness estimation

In military applications, the motion of high-speed objects usually causes motion blur in images, which makes it difficult to detect objects. We propose an image restoration method based on the line features and the degradation process of motion-blurred images. By analysing these features, we can estimate the motion state of the target and restore the images. The images processed by this method can get better performance in tasks like object detection and object tracking.

https://iopscience.iop.org/article/10.1088/1742-6596/2478/6/062004/pdf

Ling Ge

Papers

Depth saliency based on anisotropic center-surround difference

Depth-aware salient object detection using anisotropic center-surround difference

Interactive RGB-D Image Segmentation Using Hierarchical Graph Cut and Geodesic Distance

Adaptive integration of depth and color for objectness estimation

An image restoration method for motion-blurred objects