Abstract
With the advent of stereo camera saliency object detection for RGB-D image is attracting more and more interest. Most existing algorithms treat RGB-D image as one RGB image and one depth map, then measure saliency map independently, and last fuse them. They disregard the fact that human visual system operates in real 3D environments. The paper proposed saliency object detection for RGB-D image from 3D perspective. It regards object as three dimensional structures, and redefines boundary conception in RGB-D image, and regards space boundary including top, down, left, right, front, back plane in real 3D environment as background. It incorporates 3D compactness feature, in which salient objects typically have 3D compact spatial distributions, into color and depth feature to express similarity among supervoxels and applies manifold ranking by six boundary planes to generate six saliency maps, and then integrates them to get the RGB-D saliency map from background view. In the end it refines saliency map by high confident salient seeds from foreground view. Experiment results show that six planes of RGB-D image are superior to four sides of RGB image as background seeds and 3D compactness plays an important role in saliency measurement. Our approach outperforms other state-of-the-art algorithms on NLPR RGBD 1000 benchmark.
Similar content being viewed by others
References
Achanta R, Shaji A, Smith K et al (2012) SLIC superpixels compared to state-of-the-art superpixel methods [J]. IEEE Trans Pattern Anal Mach Intell 34(11):2274–2282
Ahmad J, Sajjad M, Mehmood I et al (2015) Saliency-weighted graphs for efficient visual content description and their applications in real-time image retrieval systems[J]. J Real-Time Image Proc 13(3):431–447
Chaib S, Gu Y, Yao H et al (2016) A VHR scene classification method integrating sparse PCA and saliency computing[C]. Geoscience and Remote Sensing Symposium (IGARSS). 2016 IEEE International, pp 2742–2745
Cheng Y, Fu H, Wei X et al (2014) Depth enhanced saliency detection method[C]. Proceedings of international conference on internet multimedia computing and service. ACM, pp 23
Desingh K, Madhava K K, Rajan D et al (2013) Depth really matters: improving visual salient region detection with depth[C]. British machine vision conference (BMVC), pp 98.1–98.11
Feng D, Barnes N, You S et al (2016) Local background enclosure for RGB-D salient object detection[C]. Computer Vision and Pattern Recognition (CVPR), 2016 IEEE Conference on. IEEE, pp 2343–2350
Guo J, Ren T, Bei J et al (2015) Salient object detection in RGB-D image based on saliency fusion and propagation[C]. Proceedings of the 7th international conference on internet multimedia computing and service. ACM, pp 59
Hong S, You T, Kwak S et al (2015) Online tracking by learning discriminative saliency map with convolutional neural network[C]. International Conference on Machine Learning (ICML), pp 597–606
Hussain CA, Rao DV, Masthani SA (2016) Robust pre-processing technique based on saliency detection for content based image retrieval systems[J]. Procedia Computer Science 85:571–580
Hussain CA, Rao DV, Masthani SA (2016) Image retrieval using saliency content[C]. Electrical, electronics, and optimization techniques (ICEEOT), international conference on. IEEE, pp 840–844
Jiang L, Koch A, Zell A (2015) Salient regions detection for indoor robots using RGB-D data[C]. 2015 IEEE International conference on robotics and automation (ICRA). IEEE, pp 1323–1328
Ju R, Ge L, Geng W et al (2014) Depth saliency based on anisotropic center-surround difference[C]. 2014 IEEE international conference on image processing (ICIP). IEEE, pp 1115–1119
Ju R, Liu Y, Ren T et al (2015) Depth-aware salient object detection using anisotropic center-surround difference[J]. Signal Process Image Commun 38:115–126
Khanna MT, Rai K, Chaudhury S et al (2015) Perceptual depth preserving saliency based image compression[C]. Proceedings of the 2nd international conference on perception and machine intelligence. ACM, pp 218–223
Krause EA, Zillich M, Williams TE et al (2014) Learning to recognize novel objects in one shot through human-robot interactions in natural language dialogues[C]. AAAI, pp 2796–2802
Lang C, Nguyen T V, Katti H et al (2012) Depth matters: influence of depth cues on visual saliency[M]. Computer Vision–ECCV 2012. Springer Berlin Heidelberg, pp 101–115
Li Z, Liu G, Zhang D et al (2016) Robust single-object image segmentation based on salient transition region[J]. Pattern Recogn 52:317–331
Liu GH, Yang JY, Li ZY (2015) Content-based image retrieval using computational visual attention model[J]. Pattern Recogn 48(8):2554–2566
Margolin R, Zelnik-Manor L, Tal A (2014) How to evaluate foreground maps?[C]. Proceedings of the IEEE conference on computer vision and pattern recognition, pp 248–255
Oh SJ, Benenson R, Khoreva A et al (2017) Exploiting saliency for object segmentation from image level labels[C]. Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4410–4419
Otsu N (1979) A threshold selection method from gray-level histograms[J]. IEEE Trans Syst Man Cybern 9(1):62–66
Papushoy A, Bors AG (2015) Image retrieval based on query by saliency content[J]. Digital Signal Processing 36:156–173
Peng H, Li B, Xiong W et al (2014) Rgbd salient object detection: a benchmark and algorithms[C]. European conference on computer vision. Springer, Cham, pp 92–109
Qi M, Wang Y (2016) DEEP-CSSR: scene classification using category-specific salient region with deep features[C]. 2016 IEEE international conference on image processing (ICIP). IEEE, pp 1047-1051
Quo J, Ren T, Bei J (2016) Salient object detection for RGB-D image via saliency evolution[C]. 2016 IEEE international conference on multimedia and expo (ICME). IEEE, pp 1–6
Ren J, Gong X, Yu L et al (2015) Exploiting global priors for RGB-D saliency detection[C]. 2015 IEEE conference on computer vision and pattern recognition workshops (CVPRW). IEEE, pp 25–32
Song H, Liu Z, Du H et al (2015) Saliency detection for RGBD images[C]. Proceedings of the 7th international conference on internet multimedia computing and service. ACM, pp 72
Srivastava S, Mukherjee P, Lall B (2016) Adaptive image compression using saliency and KAZE features[C]. International conference on signal processing and communications, pp:1–5
Sun J, Wu J, Yu H et al (2016) Boosting image retrieval framework with salient objects[C]. Audio, language and image processing (ICALIP), 2016 international conference on. IEEE, pp 241–245
Tamura Y, Akashi T, Yano S et al (2016) Human visual attention model based on analysis of magic for smooth human–robot interaction[J]. Int J Soc Robot 8(5):685–694
Tang Y, Tong R, Tang M et al (2016) Depth incorporating with color improves salient object detection[J]. Vis Comput 32(1):111–121
Wu P, Duan L, Kong L (2015) RGB-D salient object detection via feature fusion and multi-scale enhancement[C]. CCF Chinese Conference on Computer vision. Springer Berlin Heidelberg, pp 359–368
Xue H, Gu Y, Li Y et al (2015) RGB-D saliency detection via mutual guided manifold ranking[C]. Image Processing (ICIP), 2015 IEEE international conference on. IEEE, pp 666–670
Yang C, Zhang L, Lu H et al (2013) Saliency detection via graph-based manifold ranking[C]. Computer vision and pattern recognition (CVPR), 2013 IEEE Conference on. IEEE, pp 3166–3173
Zhang X, Chen X (2016) Robust sketch-based image retrieval by saliency detection[C]. International conference on multimedia modeling. Springer, Cham, pp 515–526
Zhang F, Du B, Zhang L (2015) Saliency-guided unsupervised feature learning for scene classification[J]. IEEE Transactions on Geoscience and Remote Sensing 53(4):2175–2184
Zhang L, Chen J, Qiu B (2016) Region-of-interest coding based on saliency detection and directional wavelet for remote sensing images[J]. IEEE Geosci Remote Sens Lett 14(1):23–27
Zhou D, Weston J, Gretton A et al (2004) Ranking on data manifolds[C]. Adv Neural Inf Proces Syst 16:169–176
Zhou L, Yang Z, Yuan Q et al (2015) Salient region detection via integrating diffusion-based compactness and local contrast[J]. IEEE Trans Image Process 24(11):3308–3320
Zhu S, Bo Y, He L (2016) Robust multi-feature visual tracking with a saliency-based target descriptor[C]. Control conference (CCC), 2016 35th Chinese. IEEE, pp 5008–5013
Zhu G, Wang J, Wu Y et al (2016) MC-HOG correlation tracking with saliency proposal[C]. Thirtieth AAAI Conference on Artificial Intelligence. AAAI Press, pp 3690–3696
Zhu W, Liang S, Wei Y et al Saliency optimization from robust background detection[C]. Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2814–2821
Acknowledgements
We thank Prof. Jianguo Wu from Anhui University for helping with acquisition of funding. We also thank all anonymous reviewers for their valuable comments. This research is supported by National Key Technology Research and Development Program of the Ministry of Science and Technology of China (2015BAK24B01), Key Program of Natural Science Project of Educational Commission of Anhui Province, China (KJ2015A009), Open issues on Co-Innovation Center for Information Supply & Assurance Technology, Anhui University (ADXXBZ201610).
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Liu, Z., Song, T. & Xie, F. RGB-D image saliency detection from 3D perspective. Multimed Tools Appl 78, 6787–6804 (2019). https://doi.org/10.1007/s11042-018-6319-4
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-018-6319-4