An Innovative Salient Object Detection Using Center-Dark Channel Prior

Zhu, Changan; Li, Ge; Wang, Wenmin; Wang, Ronggang

doi:10.1109/iccvw.2017.178

Cited by 148 publications

(106 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…There have been many attempts to boost the performance of RGB methods [23,29,[37][38][39]. Depth contains structural information and 3D layout information, which have been introduced to SOD [8,10,26,32,34,44,45]. Decent progress has been made by RGB-D saliency detection methods, especially in complex scenes.…”

Section: Related Workmentioning

confidence: 99%

“…We compare our method with 14 state-of-the-art RGB-D salient object detection methods, including 9 latest CNNs-based methods: A2dele [28], DMRA [27], CPFP [41], PDNet [43], PCA [4], CTM-F [15], MMCI [6], DF [31], TANet [5]; and 5 traditional methods: DES [8], NLPR [26], DCMC [10], MB [44], CDCP [45]. For fair comparisons, We implement those methods with the released code and their default parameters.…”

Section: Comparison With State-of-the-artsmentioning

confidence: 99%

“…This fundamental task plays an important role in various computer vision applications, including image segmentation [24], object tracking [2,16] and pose estimation [9]. Earlier saliency detection methods mainly focus on extracting hand-crafted features [26,30,36,45]. Based on limited knowledge which lacks high-level contexts representation, these methods may have less robustness in di erent scenes.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Feature Reintegration over Differential Treatment: A Top-down and Adaptive Fusion Network for RGB-D Salient Object Detection

Zhang

Piao

et al. 2020

Proceedings of the 28th ACM International Conference on Multimedia

View full text Add to dashboard Cite

Most methods for RGB-D salient object detection (SOD) utilize the same fusion strategy to explore the cross-modal complementary information at each level. However, this may ignore di erent feature contributions from two modalities on di erent levels towards prediction. In this paper, we propose a novel top-down multi-level fusion structure where di erent fusion strategies are utilized to e ectively explore the low-level and high-level features. This is achieved by designing the interweave fusion module (IFM) to effectively integrate the global information and designing the gated select fusion module (GSFM) to discriminatively select useful local information by ltering out the unnecessary one from RGB and depth data. Moreover, we propose an adaptive fusion module (AFM) to reintegrate the fused cross-modal features of each level to predict a more accurate result. Comprehensive experiments on 7 challenging benchmark datasets demonstrate that our method achieves the competitive performance over 14 state-of-the-art RGB-D alternative methods. CCS CONCEPTS • Computing methodologies → Interest point and salient region detections.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Comparison With State-of-the-artsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Feature Reintegration over Differential Treatment: A Top-down and Adaptive Fusion Network for RGB-D Salient Object Detection

Zhang

Piao

et al. 2020

Proceedings of the 28th ACM International Conference on Multimedia

View full text Add to dashboard Cite

show abstract

“…In [10], Jiang uses the supervised learning approach based on multi-level image segmentation to map the regional feature vector to a saliency score, and finally fuses the saliency scores across multiple levels to yield the saliency map. Zhu [11] proposes to generate initial saliency map based on color and depth saliency map, and center-dark channel map based on center saliency prior and dark channel prior, respectively. Then these saliency maps are fused to generate the final saliency map.…”

Section: Introductionmentioning

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

“…Recently, advances in 3D data acquisition techniques have motivated the adoption of structural features, improving the discrimination between different objects with the similar appearance. some algorithms [19,15,5,6,44,40] adopt depth cue to deal with the challenging scenarios. In [19], Zhu et al propose a framework based on cognitive neuroscience, and use depth cue to represent the depth of real field.…”

mentioning

confidence: 99%

A multilayer backpropagation saliency detection algorithm and its applications

Zhu

2018

Multimed Tools Appl

Self Cite

View full text Add to dashboard Cite

Saliency detection is an active topic in the multimedia field. Most previous works on saliency detection focus on 2D images. However, these methods are not robust against complex scenes which contain multiple objects or complex backgrounds. Recently, depth information supplies a powerful cue for saliency detection. In this paper, we propose a multilayer backpropagation saliency detection algorithm based on depth mining by which we exploit depth cue from three different layers of images. The proposed algorithm shows a good performance and maintains the robustness in complex situations. Experiments results show that the proposed framework is superior to other existing saliency approaches. Besides, we give two innovative applications by this algorithm, such as scene reconstruction from multiple images and small target object detection in video.

show abstract

An Innovative Salient Object Detection Using Center-Dark Channel Prior

Cited by 148 publications

References 13 publications

Feature Reintegration over Differential Treatment: A Top-down and Adaptive Fusion Network for RGB-D Salient Object Detection

Feature Reintegration over Differential Treatment: A Top-down and Adaptive Fusion Network for RGB-D Salient Object Detection

Video smoke detection based on deep saliency network

A multilayer backpropagation saliency detection algorithm and its applications

Contact Info

Product

Resources

About