Object Recognition Based on Improved Context Model

WEN Chenglin; ZHOU Guangfu; GAO Jingli; LI Hongwei; XU Xiaobin

doi:10.1049/cje.2018.03.014

Volume 27 Issue 3

Turn off MathJax

Article Contents

Article Navigation > Chinese Journal of Electronics > 2018 > 27(3): 573-581

WEN Chenglin, ZHOU Guangfu, GAO Jingli, et al., “Object Recognition Based on Improved Context Model,” Chinese Journal of Electronics, vol. 27, no. 3, pp. 573-581, 2018, doi: 10.1049/cje.2018.03.014

Citation:

WEN Chenglin, ZHOU Guangfu, GAO Jingli, et al., “Object Recognition Based on Improved Context Model,” Chinese Journal of Electronics, vol. 27, no. 3, pp. 573-581, 2018, doi: 10.1049/cje.2018.03.014

Citation:

PDF( 1893 KB)

Object Recognition Based on Improved Context Model

doi: 10.1049/cje.2018.03.014

1.
School of Automation, Hangzhou Dianzi University, Hangzhou 310018, China;
2.
College of Electrical Engineering, Zhejiang University, Hangzhou 310027, China

Funds: This work is supported by the National Natural Science Foundation of China (No.61273170, No.61271144, No.61304109, No.61503206).

Received Date: 2016-01-11
Rev Recd Date: 2016-03-24
Publish Date: 2018-05-10

Abstract

Abstract

An object recognition method is proposed in this paper by introducing the spatial location relationship of objects into the context model. The spatial-position information of the objects is first utilized to model the context model. The model parameters and dependency structure of objects can be learned by integrating the context information into the same probabilistic framework. The image recognition is accomplished by using the advantages of efficient inference of the tree structure model. The proposed method can greatly improve the object recognition rate and better keep the consistency of scenes. The effectiveness of the proposed algorithm is verified by testing and comparing with other existing algorithms in the actual dataset.
- Context model,
- Tree model,
- Co-occurrence tree,
- Spatial relationships

FullText(HTML)

References(20)

References

M.J. Choi, A. Torralba, A.S. Willsky, "A tree-based context model for object recognition", IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.34, No.2, pp.240-252, 2012.

F.S. Wang, C.L. Wang, B. Li, X.M. Ding, W.M. Hu, "Specified sensitive video recognition based on multi-context construction and linear fusion", Acta Electronica Sinica, Vol.43, No.4, pp.675-683, 2015. (in Chinese)

X.J. Yang, "Sensor selection for target tracking in wireless sensor networks based on performance bounds and quantized data", Acta Electronica Sinica, Vol.42, No.6, pp.1081-1085, 2014. (in Chinese)

F. Xu, H.Y. Zhang, J. Wang, N. Xu, Z.Y. Wang, M. Deng, "Social context-aware routing algorithms in opportunistic networks", Acta Electronica Sinica, Vol.43, No.5, pp.833-840, 2015. (in Chinese)

A. Rabinovich, A. Vedaldi, C. Galleguillos, et al., "Objects in Context", IEEE International Conference on Computer Vision, Rio de Janeiro, Brazil, pp.1-8, 2007.

A. Torralba, K.P. Murphy, W.T. Freeman, "Contextual models for object detection using boosted random fields", Advances in Neural Information Processing Systems, Vancouver, British Columbia, Canada, pp.1401-1408, 2004.

C.X. Gao, N. Sang, "Spatial pyramid model based on integrating of local features and filter characteristics", Acta Electronica Sinica, Vol.39, No.9, pp.2034-2038, 2011. (in Chinese)

R.J. Zhang, B.C. Li, F.S. Wei, "Image scene classification based on multi-scale and contextual semantic information", Acta Electronica Sinica, Vol.42, No.4, pp.646-652, 2014. (in Chinese)

L. Ladicky, C. Russell, P. Kohli, et al., "Graph cut based inference with co-occurrence statistics", European Conference on Computer Vision (ECCV), Heraklion, Greece, pp.239-253, 2010.

M.J. Choi, V.Y. Tan, A. Anandkumar, et al., "Learning latent tree graphical models", Journal of Machine Learning Research, Vol.12, No.4, pp.1771-1812, 2011.

M.I. Jordan, Y. Weiss, Graphical Models:Probabilistic Inference, MIT Press, Cambridge, MA, pp.243-266, 1999.

F. Wang, Y. Li, "Beyond physical connections:Tree models in human pose estimation", 2013 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Portland, Oregon, USA, pp.596-603, 2013.

J. Pearl, Probabilistic Reasoning in Intelligent Systems:Networks of Plausible Inference, Morgan Kaufmann, 2014.

B. Yao, F.F. Li, "Modeling mutual context of object and human pose in human-object interaction activities", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), San Francisco, California, USA, pp.17-24, 2010.

K. Nakayama, S. Shimojo, G.H. Silverman, "Stereoscopic depth:Its relation to image segmentation, grouping, and the recognition of occluded objects", Perception, Vol.18, No.1, pp.55-68, 1989.

C. Galleguillos, A. Rabinovich, S. Belongie, "Object categorization using co-occurrence, location and appearance", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Anchorage, Alaska, USA, pp.92-96, 2008.

K. Murphy, A. Torralba, W. Freeman, "Using the forest to see the trees:A graphical model relating features, objects and scenes", Advances in Neural Information Processing Systems, Vancouver, British Columbia, Canada, Vol.16, pp.1499-1506, 2003.

C. Chow, C. Liu, "Approximating discrete probability distributions with dependence trees", IEEE Transactions on Information Theory, Vol.14, No.3, pp.462-467, 1968.

J.G. Jiang, Y.L. Jin, M.B. Qi, S. Zhan, "Moving target detection in natural scene based on sparse representation of residuals", Acta Electronica Sinica, Vol.43, No.9, pp.1738-1744, 2015. (in Chinese)

J. Miao, J. Chu, G.M. Zhang, "An affine invariant line descriptor and line matching", Acta Electronica Sinica, Vol.43, No.12, pp.2505-2512, 2015. (in Chinese)

Relative Articles

Supplements(0)

Cited By

Proportional views