RGBD Salient Object Detection via Deep Fusion

Qu, Liangqiong; He, Shengfeng; Zhang, Jiawei; Tian, Jinshou; Tang, Yandong; Yang, Qingxiong

doi:10.1109/tip.2017.2682981

Cited by 370 publications

(226 citation statements)

References 55 publications

(224 reference statements)

Supporting

Mentioning

226

Contrasting

Order By: Relevance

“…More recently, [177] proposed to use a CNN for RGB-D saliency prediction. However, their approach is not endto-end trainable as they first extract several hand-crafted features and fuse them together followed by an off-line smoothing and saliency prediction stage with in a CNN.…”

Section: Methods Overviewmentioning

confidence: 99%

Indoor Scene Understanding in 2.5/3D for Autonomous Agents: A Survey

2019

View full text Add to dashboard Cite

With the availability of low-cost and compact 2.5/3D visual sensing devices, computer vision community is experiencing a growing interest in visual scene understanding of indoor environments. This survey paper provides a comprehensive background to this research topic. We begin with a historical perspective, followed by popular 3D data representations and a comparative analysis of available datasets. Before delving into the application specific details, this survey provides a succinct introduction to the core technologies that are the underlying methods extensively used in the literature. Afterwards, we review the developed techniques according to a taxonomy based on the scene understanding tasks. This covers holistic indoor scene understanding as well as subtasks such as scene classification, object detection, pose estimation, semantic segmentation, 3D reconstruction, saliency detection, physics-based reasoning and affordance prediction. Later on, we summarize the performance metrics used for evaluation in different tasks and a quantitative comparison among the recent state-of-the-art techniques. We conclude this review with the current challenges and an outlook towards the open research problems requiring further investigation.

show abstract

Section: Methods Overviewmentioning

confidence: 99%

Indoor Scene Understanding in 2.5/3D for Autonomous Agents: A Survey

2019

View full text Add to dashboard Cite

show abstract

“…However, there are still some wrongly detected backgrounds, such as the white object in the second image of the last group. Combining the depth cue and deep learning, the DF [40] method suppresses the background effectively, but it ignores the completeness of salient objects, such as the third image in the green cartoon group. For the RGB co-saliency detection methods (CCS [49] and SCS [47]), some foregrounds (such as the third image in the green cartoon group) are wrongly suppressed by the CCS method, and some backgrounds (such as the white board in the red flashlight group) are also inaccurately highlighted by the SCS method.…”

Section: B Comparison With State-of-the-art Methodsmentioning

confidence: 99%

HSCS: Hierarchical Sparsity Based Co-saliency Detection for RGBD Images

Cong

Lei

et al. 2019

IEEE Trans. Multimedia

View full text Add to dashboard Cite

Co-saliency detection aims to discover common and salient objects in an image group containing more than two relevant images. Moreover, depth information has been demonstrated to be effective for many computer vision tasks. In this paper, we propose a novel co-saliency detection method for RGBD images based on hierarchical sparsity reconstruction and energy function refinement. With the assistance of the intra saliency map, the inter-image correspondence is formulated as a hierarchical sparsity reconstruction framework. The global sparsity reconstruction model with a ranking scheme focuses on capturing the global characteristics among the whole image group through a common foreground dictionary. The pairwise sparsity reconstruction model aims to explore the corresponding relationship between pairwise images through a set of pairwise dictionaries. In order to improve the intra-image smoothness and inter-image consistency, an energy function refinement model is proposed, which includes the unary data term, spatial smooth term, and holistic consistency term. Experiments on two RGBD co-saliency detection benchmarks demonstrate that the proposed method outperforms the state-of-the-art algorithms both qualitatively and quantitatively.

show abstract

“…There are some technologies of spatial coherence refinement for the post-processing approaches, such as CRF [19,22,24] , clustering [12,21] using superpixel, graph Laplacian regularized nonlinear regression [15,20]. Zhao [13] outputs the occupation ratio of salient softmax value, while the general saliency network output sigmoid of probability of saliency.…”

Section: Related Workmentioning

confidence: 99%

Video smoke detection based on deep saliency network

Zhang

et al. 2019

Fire Safety Journal

View full text Add to dashboard Cite

Video smoke detection is a promising fire detection method especially in open or large spaces and outdoor environments. Traditional video smoke detection methods usually consist of candidate region extraction and classification, but lack powerful characterization for smoke. In this paper, we propose a novel video smoke detection method based on deep saliency network. Visual saliency detection aims to highlight the most important object regions in an image. The pixel-level and object-level salient convolutional neural networks are combined to extract the informative smoke saliency map. An end-to-end framework for salient smoke detection and existence prediction of smoke is proposed for application in video smoke detection. The deep feature map is combined with the saliency map to predict the existence of smoke in an image. Initial and augmented dataset are built to measure the performance of frameworks with different design strategies.Qualitative and quantitative analysis at frame-level and pixel-level demonstrate the excellent performance of the ultimate framework.

show abstract

RGBD Salient Object Detection via Deep Fusion

Cited by 370 publications

References 55 publications

Indoor Scene Understanding in 2.5/3D for Autonomous Agents: A Survey

Indoor Scene Understanding in 2.5/3D for Autonomous Agents: A Survey

HSCS: Hierarchical Sparsity Based Co-saliency Detection for RGBD Images

Video smoke detection based on deep saliency network

Contact Info

Product

Resources

About