Application of object prediction theory in object localization

Yang, Kai, Xie, Liming, Gao, Xiaorong, Peng, Jianping

Publication in Journal of Optical Technology

For Russian citation (Opticheskii Zhurnal):

Kai Yang, Liming Xie, Xiaorong Gao, Jianping Peng Application of object prediction theory in object localization (Применение теории предсказания в задаче локализации объектов) [на англ. яз.] // Оптический журнал. 2017. Т. 84. № 6. С. 30–36.

Kai Yang, Liming Xie, Xiaorong Gao, Jianping Peng Application of object prediction theory in object localization (Применение теории предсказания в задаче локализации объектов) [in English] // Opticheskii Zhurnal. 2017. V. 84. № 6. P. 30–36.

For citation (Journal of Optical Technology):

Kai Yang, Liming Xie, Xiaorong Gao, and Jianping Peng, "Application of object prediction theory in object localization," Journal of Optical Technology. 84(6), 384-389 (2017). https://doi.org/10.1364/JOT.84.000384

Abstract:

In this paper, an object localization method based on prediction theory was proposed. Prediction theory was employed to construct the network in the approach. Besides, the proposed work was applied to key component localization on a running gear. Its performance was compared with a sift based object localization. The proposed network was designed to represent the structure of objects, and the recognition of objects is to be accomplished after a training of the network. The experiment demonstrates that the proposed method can accurately localize objects in a big image through using a small size of training data.

Keywords:

running gear; prediction theory; objects localization

OCIS codes: 150.0150; 150.3040

References:

1. Viola P.A., Jones M.J. Robust real-time face detection // IJCV. 2004. V. 57. № 2. P. 137–154.
2. Dalal N., Triggs B. Histograms of oriented gradients for human detection // CVPR. 2005. V. 1. P. 886–893.
3. Lampert C.H., Blaschko M.B., Hofmann T. Efficient subwindow search: a branch and bound framework for object localization // PAMI. 2009. V. 31. № 12. P. 2129–2142.

4. Felzenszwalb P.F., Girshick R.B., McAllester D.A., Ramanan D. Object detection with d iscriminatively trained partbased models // PAMI. 2010. V. 32. № 9. P. 1627–1645.
5. Cinbis R.G., Verbeek J.J., Schmid C. Segmentation driven object detection with fisher vectors // ICCV. 2013. P. 2968–2975.
6. Galleguillos C., Babenko B., Rabinovich A., Belongie S.J. Weakly supervised object localization with stable segmentations // ECCV. 2008. V. 5302. P. 193–207.
7. Siva P., Xiang T. Weakly supervised object detector learning with model drift detection // ICCV. 2011. P. 343–350.
8. Deselaers T., Alexe B., Ferrari V. Weakly supervised localization and learning with generic knowledge // IJCV. 2012. V. 100. № 3. P. 275–293.
9. Nguyen M.H., Torresani, L., la Torre F.D., Rother C. Learning discriminative localization from weakly labeled data // Pattern Recognition. 2014. V. 47. № 3. P. 1523–1534.
10. Cinbis R.G., Verbeek J.J., Schmid C. Multifold MIL training for weakly supervised object localization // CVPR. 2014. P. 2409–2416.
11. Munder S., Gavrila D.M. An experimental study on pedestrian classification // PAMI. 2006. V. 28. № 11. P. 1863–1868.
12. Hawkins J., Blakeslee S. On Intelligence. New York: Henry Holt, 2004. 98 p.
13. George D. How the brain might work: A hierarchical and temporal model for learning and recognition // PhD Thesis. USA. Stanford: Stanford University, 2008. 191 p.