Depth Enhanced Saliency Detection Method

By Yupeng Cheng, Huan Fu, Xingxing Wei, Jiangjian Xiao, Xiaochun Cao. International Conference on Internet Multimedia Computing and Service, 2014

360 citations recorded by the source corpus.

Human vision system understands the environment from 3D perception. However, most existing saliency detection algorithms detect the salient foreground based on 2D image information. In this paper, we propose a saliency detection method using the additional depth information. In our method, saliency cues are provided to follow the laws of the visually salient stimuli in both color and depth spaces. Simultaneously, the 'center bias' is also extended to 'spatial' bias to represent the nature advantage in 3D image. In addition, We build a dataset to test our method and the experiments demonstrate that the depth information is useful for extracting the salient object from the complex scenes.

Subfields: Computer Vision and Pattern Recognition, Sensory Systems

View Paper: https://www.semanticscholar.org/paper/e34c00b57feeb85de8ab85c66a047b16c45793b7

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Sensory Systems

Citations in the corpus

UC-Net: Uncertainty Inspired RGB-D Saliency Detection via Conditional Variational Autoencoders (2020, methodology): “, DES [8], and NLPR [41] datasets; or computing depth from stereo cameras, examples of such datasets are SSB [40] and NJU2K [28].”
CNNs-Based RGB-D Saliency Detection via Cross-View Transfer and Multiview Fusion (2018, methodology): “2) In terms of performance, the naïve SUM or MUL fusion rule obviously lacks an intrinsic fusion mechanism.”
Contrast Prior and Fluid Pyramid Integration for RGBD Salient Object Detection (2019, methodology): “RGBD135 [9] is also named DES which consists of seven indoor scenes and contains 135 indoor images collected by Microsoft Kinect.”
Rethinking RGB-D Salient Object Detection: Models, Data Sets, and Large-Scale Benchmarks (2019, methodology): “comparison results of 18 SOTA RGB-D based SOD models over seven datasets, namely STERE [63], LFSD [64], DES [38], NLPR [39], NJU2K [37], SSD [66], and SIP (Ours) clearly demonstrate the robustness and efficiency of our D3Net model.”
RGB-D salient object detection: A survey (2020, methodology): “A comprehensive evaluation for 24 representative RGB-D based SOD models, including LHM [51], ACSD [56], DESM [49], GP [50], LBE [57], DCMC [1], SE [2], CDCP [84], CDB [95], DF [52], PCF [92], CTMF [58], CPFP [53], TANet [99], AFNet [102], MMCI [55], DMRA [54], D3Net [3], SSF [4], A2dele [5], S2MA [6”
BBS-Net: RGB-D Salient Object Detection with a Bifurcated Backbone Strategy Network (2020, methodology): “Therefore, some algorithms propose to calculate the saliency by combining local and global information, such as global contrast [11], spatial prior [9], and background prior [53].”
JL-DCF: Joint Learning and Densely-Cooperative Fusion Framework for RGB-D Salient Object Detection (2020, methodology): “…hand-crafted features/hypotheses originally applied for RGB SOD were extended to RGB-D, such as center-surround difference [25, 34], contrast [10, 13, 44], background enclosure [20], center/boundary prior [10, 12, 36, 59], compactness [12, 13], or a combination of various saliency measures [55].”
Suppress and Balance: A Simple Gated Network for Salient Object Detection (2020, methodology): “datasets, including the DES [9], DCMC [11], CDCP [75], DF [38], CTMF [18], PCA [3], MMCI [5], TANet [4], CPFP [71] and DMRA [36].”
Progressively Complementarity-Aware Fusion Network for RGB-D Salient Object Detection (2018, methodology): “Result fusion methods include summation [35, 42], multiplication [31] and designed rules [33].”
Visual Saliency Transformer (2021, methodology): “For RGB-D SOD, we use nine widely used benchmark datasets: STERE [46] (1,000 image pairs), LFSD [33] (100 image pairs), RGBD135 [9] (135 image pairs), SSD [90] (80 image pairs), NJUD [26] (1,985 image pairs), NLPR [51] (1,000 image pairs), DUTLF-Depth [52] (1,200 image pairs), SIP [15] (929 image pa”
Depth-Induced Multi-Scale Recurrent Attention Network for Saliency Detection (2019, methodology): “We compare our method with 16 state-of-the-art ones, including 5 latest CNNs-based RGB-D methods: PCA [3], PDNet [48], MMCI [4], CTMF [18], DF [35]; 5 traditional RGB-D methods: MB [49], CDCP [50], NLPR [32], DES [8], DCMC [9]; 6 top ranking CNNs-based RGB methods: PiCANet [30], PAGRN [47], R3Net [1”
SwinNet: Swin Transformer Drives Edge-Aware RGB-D and RGB-T Salient Object Detection (2022, methodology): “DES [77] has 135 indoor images collected by Microsoft Kinect.”