基于交叉皮质模型的单幅图像阴影检测算法

李成; 孙路; 田润澜; 毕笃彦

doi:10.3724/SP.J.1004.2014.02887

基于交叉皮质模型的单幅图像阴影检测算法

doi: 10.3724/SP.J.1004.2014.02887

李成^1, ,,
孙路²,
田润澜¹,
毕笃彦³

1.
空军航空大学长春 130022;
2.
中国人民解放军95899部队北京 100085;
3.
空军工程大学西安 710038

基金项目:

国家自然科学基金(61301233),吉林省教育厅"十二五"科学技术研究项目(吉教科合字[2014]第612号)资助

详细信息

作者简介:
孙路工程师, 硕士. 主要研究方向为智能信息处理.E-mail: eafoluke@163.com

通讯作者:
李成讲师, 博士. 主要研究方向为图像处理和视觉计算. 本文通信作者.E-mail: ecmli@163.com

计量
- 文章访问数: 1563
- HTML全文浏览量: 62
- PDF下载量: 1390
- 被引次数: 0
出版历程
- 收稿日期: 2013-11-08
- 修回日期: 2014-08-06
- 刊出日期: 2014-12-20

Single Image Shadow Detection Based on Intersecting Cortical Model

1.
Aviation University of Air Force, Changchun 130022;
2.
95899 Unit of Chinese People's Liberation Army, Beijing 100085;
3.
Air Force Engineering University, Xi'an 710038

Funds:

Supported by National Natural Science Foundation of China (61301233), the Twelfth Five Year Science and Technology Research Project of Education Department of Jilin Province (2014-612)

摘要

摘要: 图像中含有阴影区域对后续处理任务影响较大, 根据阴影特性, 提出基于交叉皮质模型(Intersecting cortical model, ICM)的单幅图像阴影检测算法. 通过在点火连接矩阵构造上考虑邻域像素值依赖关系, 融入局部二值模式(Local binary pattern, LBP)表征的纹理信息形成了Te-ICM模型. 根据阴影检测流程,利用模型迭代特性, 通过设计停止条件自动检测本影, 在本影修复后生成附着半影. 同时优化模型参数, 设计了基于分层聚类直方图划分的阈值下降策略. 仿真结果表明: 对于典型影像集, Te-ICM模型及相应参数设计可以较好地实现阴影检测, 输出阴影掩模准确度高, 为后续阴影去除提供了基础.
- 阴影检测 /
- 交叉皮质模型 /
- 局部二值模式 /
- 直方图划分
Abstract: Shadow is an integral part of many natural images, which can pose tough problems and limitations for further image processing tasks. By the analysis of shadow characteristics, a single image shadow detection method based on the intersecting cortical model (ICM) is proposed. Neurons in ICM possess dynamical spiking properties have the capability to segment the image naturally. We modify the linking matrix among neurons and combine the local texture features shown by local binary patterns (LBP) to make the Te-ICM for segment of shadow regions. The new model possesses the capability of taking adjacent pixel information into the firing matrix. The optimized parameters produced by the modified hierarchical clustering histogram partition method lead to the shadow detection sequences. We build an automatic stopping condition for umbra and penumbra iterations. Experimental results demonstrate that the output shadow mask keeps the size and shape of original objects well for typical image dataset, and that the proposed method can find wide applications to monochromatic or chromatic images containing one or more shadow regions, yielding high-quality results for further shadow removal operation.
- Shadow detection /
- intersecting cortical model (ICM) /
- local binary pattern (LBP) /
- histogram partition

HTML全文

参考文献(35)

[1]	Rufenacht D, Fredembach C, Susstrunk S. Automatic and accurate shadow detection using near-infrared information. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2014, 36(8): 1672-1678
[2]	Zhu Qing, Xu Sheng-Hua, Han Li-Tao. A new shadow extraction method from color aerial images based on Dempster-Shafer evidence theory. Acta Automatica Sinica, 2007, 33(6): 588-595(朱庆, 徐胜华, 韩李涛. 基于D-S证据理论的彩色航空影像阴影提取方法. 自动化学报, 2007, 33(6): 588-595)
[3]	Fang Ju-Qin, Chen Fan, He Hong-Jie, Yin Zhong-Ke. Shadow detection of remote sensing images based on local-classification level set and color feature. Acta Automatica Sinica, 2014, 40(6): 1156-1165(方菊芹, 陈帆, 和红杰, 尹忠科. 结合局部分类水平集与颜色特征的遥感影像阴影检测. 自动化学报, 2014, 40(6): 1156-1165)
[4]	Yang Q X, Tan K H, Ahuja N. Shadow removal using bilateral filtering. IEEE Transactions on Image Processing, 2012, 21(10): 4361-4368
[5]	Shahtahmassebi A, Yang N, Wang K, Moore N, Shen Z Q. Review of shadow detection and de-shadowing methods in remote sensing. Chinese Geographical Science, 2013, 23(4): 403-420
[6]	Barnard K, Finlayson G D. Shadow identification using colour ratios. In: Proceedings of the 8th Color Imaging Conference. Scottsdale, Arizona: Society for Imaging Science and Technology, 2000. 97-101
[7]	Finlayson G D, Hordley S D, Lu C, Drew M S. On the removal of shadows from images. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2006, 28(1): 59-68
[8]	Wang Ning. Study on Shadow Detection and Removal [Master dissertation], Beijing Jiaotong University, China, 2008(王宁.图像的阴影检测和去除算法研究 [硕士论文], 北京交通大学, 中国, 2008)
[9]	Liu Yan-Li, Shi Jun, Zhang Yan-Ci. Shadow removal based on single outdoor image. Journal of Software, 2012, 23(S2): 168-175(刘艳丽, 石俊, 张严辞. 一种单幅室外图像的阴影去除算法. 软件学报, 2012, 23(S2): 168-175)
[10]	Tian J D, Sun J, Tang Y D. Tricolor attenuation model for shadow detection. IEEE Transactions on Image Processing, 2009, 18(10): 2355-2363
[11]	He Kai, Zhao Hong-Ying, Liu Jing-Jing, Wang Cheng-You. Shadow removal of city's remote sensing image based on fractal and texture analysis. Journal of Tianjin University, 2008, 41(7): 800-804(何凯, 赵红颖, 刘晶晶, 王成优. 基于分形及纹理分析的城市遥感影像阴影去除. 天津大学学报, 2008, 41(7): 800-804)
[12]	Levine M D, Bhattacharyya J. Removing shadows. Pattern Recognition Letters, 2005, 26(3): 251-265
[13]	Zhu J J, Samuel K G G, Masood S Z, Tappen M F. Learning to recognize shadows in monochromatic natural images. In: Proceedings of the 2010 IEEE Conference on Computer Vision and Pattern Recognition. San Francisco, CA: IEEE, 2010. 223-230
[14]	Lalonde J F, Efros A A, Narasimhan S G. Detecting ground shadows in outdoor consumer photographs. In: Proceedings of the 2010 European Conference on Computer Vision. Berlin, Heidelberg: Springer, 2010. 322-335
[15]	Guo R Q, Dai Q Y, Hoiem D. Paired regions for shadow detection and removal. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2013, 35(12): 2956-2967
[16]	Vicente T F Y, Yu C P, Samaras D. Single image shadow detection using multiple cues in a supermodular MRF. In: Proceedings of the 2013 British Machine Vision Conference. Bristol, England: BMVA Press, 2013. 126.1-126.12
[17]	Zhang Shi-Hui, Jin Lian-Chao. Shadow detection for outdoor images based on region segmentation combining with gradient direction feature. Journal of Yanshan University, 2013, 37(2): 137-142(张世辉, 靳连超. 基于区域分割结合梯度方向特征的户外图像影子检测. 燕山大学学报, 2013, 37(2): 137-142)
[18]	Johnson J L, Padgett M L. PCNN models and applications. IEEE Transactions on Neural Networks, 1999, 10(3): 480-498
[19]	Gu X D, Yu D H, Zhang L M. Image shadow removal using pulse coupled neural network. IEEE Transactions on Neural Networks, 2005, 16(3): 692-698
[20]	Nielsen M, Madsen C B. Graph cut based segmentation of soft shadows for seamless removal and augmentation. In: Proceedings of the 15th Scandinavian Conference. Berlin, Heidelberg: Springer, 2007. 918-927
[21]	Wu T P, Tang C K, Brown M S, Shum H Y. Natural shadow matting. ACM Transactions on Graphics, 2007, 26(2): Article No.8
[22]	Kwatra V, Han M, Dai S Y. Shadow removal for aerial imagery by information theoretic intrinsic image analysis. In: Proceedings of the 2012 IEEE International Conference on Computational Photography. Seattle, WA: IEEE, 2012. 1-8
[23]	Lindblad T, Kinser J M. Image Processing Using Pulse-Coupled Neural Networks (2nd Edition). Germany: Springer-Verlag, 2005. 24-26
[24]	Wang Z B, Ma Y D, Cheng F Y, Yang L Z. Review of pulse-coupled neural networks. Image and Vision Computing, 2010, 28(1): 5-13
[25]	Ojala T, Pietikainen M, Maenpaa T. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(7): 971-987
[26]	Jin H L, Liu Q S, Lu H Q. Face detection using improved LBP under Bayesian framework. In: Proceedings of the 2004 IEEE First Symposium on Multi-agent Security and Survivability. Hong Kong, China: IEEE, 2004. 306-309
[27]	Arbel E. A Novel Approach for Shadow Removal Based on Intensity Surface Approximation [Ph.D. dissertation], University of Haifa, Israel, 2009
[28]	Liu Song-Tao, Wang Wei, Yin Fu-Liang. Infrared image enhancement method based on dynamic and generalized histogram equalization. Journal of Systems Engineering and Electronics, 2010, 32(7): 1411-1414(刘松涛, 王维, 殷福亮. 基于动态广义直方图均衡的红外图像增强方法. 系统工程与电子技术, 2010, 32(7): 1411-1414)
[29]	Ju Ming, Li Cheng, Gao Shan, Mu Ju-Guo, Bi Du-Yan. Non-uniform-lighting image enhancement based on centripetal-autowave intersecting cortical model. Acta Automatica Sinica, 2011, 37(7): 800-810(鞠明, 李成, 高山, 穆举国, 毕笃彦. 基于向心自动波交叉皮质模型的非均匀光照图像增强. 自动化学报, 2011, 37(7): 800-810)
[30]	Qiu G P, Duan J. Novel histogram processing for colour image enhancement. In: Proceedings of the 2004 IEEE First Symposium on Multi-Agent Security and Survivability. Hong Kong, China: IEEE, 2004. 55-58
[31]	Finlayson G D, Drew M S, Lu C. Entropy minimization for shadow removal. International Journal of Computer Vision, 2009, 85(1): 35-57
[32]	Shor Y, Lischinski D. The shadow meets the mask: pyramid-based shadow removal. Computer Graphics Forum, 2008, 27(2): 577-586
[33]	Yao J, Zhang Z F. Hierarchical shadow detection for color aerial images. Computer Vision and Image Understanding, 2006, 102(1): 60-69
[34]	Salvador E, Cavallaro A, Ebrahimi T. Shadow identification and classification using invariant color models. In: Proceedings of the 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Salt Lake City, UT: IEEE, 2001. 1545-1548
[35]	Dare P M. Shadow analysis in high-resolution satellite imagery of urban areas. Photogrammetric Engineering and Remote Sensing, 2005, 71(2): 169-177