Abstract
Object detection is an important and challenging vision task. It is a critical part in many applications such as image search, robot navigation, and scene understanding. In this paper, we propose a novel objectness measure method, which uses both saliency segmentation and superpixels clustering together. First, we use the single skeleton refinement and fuzzy C-means method to segment the image. Then, the candidate regions are selected by combining the saliency map. At the same time, we used the superpixels clustering and straddling method to filter the windows. The final candidate object windows are obtained based on a fusion of the two results. The experimental results from PASCAL VOC 2007 validate the efficacy of the proposed method, and we get a result of 40.1% on mean average precision which was the best of the tested methods.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part-based models. IEEE Trans. Pattern Anal. Mach. Intell. 1627–1645 (2010)
Harzallah, H., Jurie, F., Schmid, C.: Combining efficient object localization and image classification. In: IEEE 12th International Conference on Computer Vision, pp. 237–244 (2009)
Endres, I., Hoiem, D.: Category-independent object proposals with diverse ranking. IEEE Trans. Pattern Anal. Mach. Intell. 222–234 (2014)
Uijlings, J.R., Van De Sande, K.E., Gevers, T., Smeulders, A.W.: Selective search for object recognition. Int. J. Comput. Vis. 154–171 (2013)
Girshick, R.: Fast R-CNN. In: IEEE International Conference on Computer Vision (ICCV), pp. 1440–1448 (2015)
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. Adv. Neural Inf. Process. Syst. 91–99 (2015)
Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 779–788 (2016)
Niu, J., Bu, X., Qian, K.: Exploiting contrast cues for salient region detection. Multimed. Tools Appl. 10427–10441 (2017)
Xu, L., Lu, C., Xu, Y., Jia, J.: Image smoothing via L0 gradient minimization. ACM Trans. Gr. (TOG) 174–186 (2011)
Jie, N., Xiongzhu, B., Kun, Q.: Touching corn kernels based on skeleton features information. Trans. Chin. Soc. Agric. Mach. 280–285 (2014)
Achanta, R., Shaji, A., Smith, K., Lucchi, A., Fua, P., Süsstrunk, S.: SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Trans. Pattern Anal. Mach. Intell. 2274–2282 (2012)
Kriegel, H.P., Kröger, P., Sander, J., Zimek, A.: Density-based clustering. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, pp. 231–240 (2011)
Van de Sande, K.E., Uijlings, J.R., Gevers, T., Smeulders, A.W.: Segmentation as selective search for object recognition. In: IEEE International Conference on Computer Vision (ICCV), pp. 1879–1886 (2011)
Szegedy, C., Toshev, A., Erhan, D.: Deep neural networks for object detection. Adv. Neural Inf. Process. Syst. 2553–2561 (2013)
Bolei, Z., Khosla, A., Lapedriza, A., Oliva, A., Torralba, A.: Object detectors emerge in deep scene CNNs, pp. 1–12 (2015)
Bilen, H., Vedaldi, A.: Weakly supervised deep detection networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2846–2854 (2016)
Acknowledgements
This work is supported by the Natural Science Foundation of Higher Education Institutions of Jiangsu Province (16KJB520048); Chang Zhou Applied Basic Research Planned Project (CJ20180010); “QingLan” Project of Jiangsu Province; Key Laboratory of Industrial IoT (KYPT201803Z); the Natural Science Foundation of CCIT (CXZK201705Z).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Niu, J., Jiang, YW., Huang, L., Xue, HW. (2019). A Novel Approach for Objectness Estimation Based on Saliency Segmentation and Superpixels Clustering. In: Pan, JS., Lin, JW., Sui, B., Tseng, SP. (eds) Genetic and Evolutionary Computing. ICGEC 2018. Advances in Intelligent Systems and Computing, vol 834. Springer, Singapore. https://doi.org/10.1007/978-981-13-5841-8_63
Download citation
DOI: https://doi.org/10.1007/978-981-13-5841-8_63
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-5840-1
Online ISBN: 978-981-13-5841-8
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)