Please wait a minute...
浙江大学学报(工学版)
J4  2014, Vol. 48 Issue (2): 354-359    DOI: 10.3785/j.issn.1008-973X.2014.02.025
电气工程、计算机技术     
基于双目视觉的显著性区域检测
刘中, 陈伟海, 吴星明, 邹宇华, 王建华
北京航空航天大学 自动化科学与电气工程学院,北京 100191
Salient region detection based on stereo vision
LIU Zhong, CHEN Wei-hai, WU Xing-ming, ZOU Yu-hua, WANG Jian-hua
School of Automation Science and Electrical Engineering, Beihang University, Beijing 100191, China
 全文: PDF(1663 KB)  
摘要：

针对传统基于像素的显著性模型存在的边缘模糊、不适于低对比度环境等问题，提出一种基于双目视觉信息的显著性区域检测方法. 采用简单线性迭代聚类（SLIC）方法对图像进行超像素分割，将生成的超像素区域进行合并.通过计算各区域在左右视图的相对移动距离获取物体深度信息，以区域为单位分别计算颜色对比度及深度对比度，进行合成得到区域的显著性值.结果表明，生成的显著性图轮廓清晰，边缘锐利，同等条件下近处及深度变化显著的区域能够获得更高的显著性.该方法符合人类视觉感知特征，适用于移动机器人障碍物检测及场景识别.
关键词： 视觉选择性注意;  显著性图;  双目视觉;  图像分割;  视差计算    
Abstract:

Traditional pixel-based saliency model has some deficiencies, such as poorly defined borders and low performance in low contrast situation. A stereo vision based salient region detection approach was proposed. Simple linear iterative clustering (SLIC) method was adopted to perform superpixel segmentation. Superpixels were merged to construct segmentation image. Depth cue was computed by measuring the distance of region shifts in given stereo pair. For each region, color contrast and depth contrast were computed separately, and then fused to get   saliency value. Experimental result shows that saliency map has clear contour and sharp edge and regions at close range or with high depth contrast get more saliency. The proposed method is consistent with human visual perception and suitable for obstacle detection and scene recognition in mobile robot.
Key words: selective visual attention    saliency map    stereo vision    image segmentation    disparity computation
出版日期: 2014-03-03
:  TP 391  
基金资助:

国家自然科学基金资助项目（61075075, 61175108);北京市科技计划重大项目资助项目（D121104002812001).
通讯作者: 陈伟海,男,教授.     E-mail: whchenbuaa@126.com
作者简介: 刘中(1976—),男,博士生,从事计算机视觉方面的研究工作.E-mail: lzpro@126.com
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章　　

引用本文:

刘中, 陈伟海, 吴星明, 邹宇华, 王建华. 基于双目视觉的显著性区域检测[J]. J4, 2014, 48(2): 354-359.

LIU Zhong, CHEN Wei-hai, WU Xing-ming, ZOU Yu-hua, WANG Jian-hua. Salient region detection based on stereo vision. J4, 2014, 48(2): 354-359.

链接本文:

http://www.zjujournals.com/xueshu/eng/CN/10.3785/j.issn.1008-973X.2014.02.025    或    http://www.zjujournals.com/xueshu/eng/CN/Y2014/V48/I2/354

［1］ KOCH C, ULLMAN S. Shifts in selective visual attention: towards the underlying neural circuitry ［J］. Human Neurobiology, 1985, 4(4): 219-227.
［2］ ITTI L, KOCH C. Computational modeling of visual attention. Nature reviews ［J］. Neuroscience, 2001, 2(3): 194-203.
［3］ ACHANTA R, ESTRADA F, WILS P. et al. Salient region detection and segmentation ［C］∥ International Conference on Computer Vision Systems. Santorini: Springer Lecture Notes in Computer Science, 2008: 66-75.
［4］ MA Y F, ZHANG H J. Contrast-based image attention analysis by using fuzzy growing ［C］∥ACM International Conference on Multimedia. New York: ACM, 2003: 374-381.
［5］ BRUCE N, TSOTSOS J. Saliency, attention, and visual search: an information theoretic approach ［J］. Vision, 2009, 9(3): 124.
［6］ BRUCE N, TSOTSOS J. Saliency based on information maximization ［J］. Advances in Neural Information Processing Systems, 2009,18: 155-162.
［7］ 张国敏,殷建平,祝恩,等. 基于近似高斯金字塔的视觉注意模型快速算法［J］. 软件学报, 2009,20(12): 32413253.
ZHANG Guo-min, YIN Jian-ping, ZHU En, et al. Fast visual attention model algorithm based on approximate Gaussian pyramids ［J］. Journal of Software, 2009, 20(12): 3241-3253.
［8］ HOU X, ZHANG L. Saliency detection: a spectral residual approach ［C］∥ IEEE Conference on Computer Vision and Pattern Recognition. Minneapolis: IEEE, 2007: 18.
［9］ GUO C, ZHANG L. A novel multiresolution spatiotemporal saliency detection model and its applications in image and video compression ［J］. IEEE Trans. Image Processing, 2010,19(1): 185-198.
［10］ CHENG M M, ZHANG G, MITRA N J, et al. Global contrast based salient region detection［C］.∥ IEEE Conference on Computer Vision and Pattern Recognition. Providence: IEEE, 2011: 409-416.
［11］ 彭海,赵巨峰,冯华君,等. 基于区域显著性的双波段图像融合方法［J］. 浙江大学学报：工学版, 2012, 46(11): 2109-2115.
PENG Hai, ZHAO Ju-feng, FENG Hua-jun, et al. Dual band image fusion method based on region saliency ［J］. Journal of Zhejiang University: Engineering Science, 2012, 46(11): 2109-2115.
［12］ 曾明, 孟庆浩, 王湘晖, 等. 视觉注意机制在图像增强中的应用研究［J］.光子学报,2009, 38(5): 1283-1287.
ZENG Ming, MENG Qing-hao, WANG Xiang-hui, et al. Image enhancement based on visual attention mechanisms ［J］. Acta Photonica Sinica, 2009, 38(5): 12831287.
［13］ 刘伟,张宏,童勤业. 视觉注意计算模型及其在自然图像压缩中的应用［J］. 浙江大学学报:工学版,2007,41(4): 650-654.
LIU Wei, ZHANG Hong, TONG Qin-ye. Visual attention computational model and its application in natural image compression ［J］. Journal of Zhejiang University: Engineering Science, 2007,41(4): 650-654.
［14］ JOST T, OUERHANI N, WARTBURG R, et al. Contribution of depth to visual attention: comparison of a computer model and human ［J］. Early Cognitive Vision Workshop, 2004.
［15］ VAN E, RKELENS C. Anisotropy in werner’s binocular depth-contrast effect ［J］. Vision Research, 1996, 36: 2253-2262.
［16］ ACHANTA R, SHAJI A, SMITH K, et al. SLIC Superpixels ［R］. Lausanne: EPFL, 2010.
［17］ REN C Y, REID I. gSLIC: a real-time implementation of SLIC superpixel segmentation［R］. Oxford: University of Oxford, Department of Engineering Science, 2011.
［18］ AZIZ M Z, MERTSCHING B. Pre-Attentive detection of depth saliency using stereo vision ［C］∥Applied Imagery Pattern Recognition Workshop. Washington: IEEE, 2010: 17.
［19］ SURAL S, QIAN G, PRAMANIK S. Segmentation and histogram generation using the HSV color space for image retrieval ［C］∥Proceedings of IEEE International Conference on Image Processing. Rochester: IEEE, 2002: 589-592.
［20］ ZHANG Y X, GUO F H, ZHAO G L, et al. A comprehensive review of medical image enhancement technologies［J］. Computer Aided Drafting, Design and Manufacturing (CADDM), 2012, 22(3): 1-11.
[1] 廖苗, 赵于前, 曾业战, 黄忠朝, 张丙奎, 邹北骥. 基于支持向量机和椭圆拟合的细胞图像自动分割[J]. 浙江大学学报(工学版), 2017, 51(4): 722-728.
[2] 张建廷,张立民. 新型自适应稳健双边滤波图像分割[J]. 浙江大学学报(工学版), 2016, 50(9): 1703-1710.
[3] 胡祝华, 赵瑶池, 程杰仁, 彭金莲. 基于改进DRLSE的运动目标分割方法[J]. 浙江大学学报(工学版), 2014, 48(8): 1488-1495.
[4] 朱文峤,刁常宇,许端清,鲁东明. 基于连续对称视差计算的多视图立体匹配[J]. J4, 2014, 48(1): 85-91.
[5] 李光廷, 禹卫东. 马尔可夫随机场SAR图像分割的快速实现技术[J]. J4, 2012, 46(10): 1810-1815.
[6] 吴一全,张晓杰,吴诗婳,张生伟. 基于混沌PSO或分解的二维最小误差阈值分割[J]. J4, 2011, 45(7): 1198-1205.
[7] 谢强军, 侯迪波, 黄平捷, 张光新, 周泽魁. 基于半隐差分的单参数水平集快速分割[J]. J4, 2010, 44(8): 1496-1501.
[8] 蔡晋辉, 张光新, 才辉. 基于连通掩模的重构开算子及应用[J]. J4, 2010, 44(4): 675-680.
[9] 孔丁科, 汪国昭. 用于图像分割的边界保持局部拟合模型[J]. J4, 2010, 44(12): 2236-2240.
[10] 张赞超, 夏顺仁. 全自动尿液图像识别技术[J]. J4, 2009, 43(5): 832-838.
[11] 杨彬蔚 陆系群. 抗纹理噪声干扰的纺织印染图像分割技术[J]. , 2009, 43(4): 668-672+737.
[12] 许晓燕, 夏顺仁, LIU Tian-ming, 等. 基于Hough变换的斑马鱼胚胎图像分析技术[J]. J4, 2009, 43(11): 2034-2037.
[13] 吴洪森 冯志林 周佳男 刘小明 董金祥. 基于相位场模型的提花织物图像分割算法[J]. J4, 2008, 42(3): 444-449.
[14] 张赞超 夏顺仁 段会龙. 基于细胞神经网络的尿沉渣图像分割[J]. J4, 2008, 42(12): 2139-2144.
[15] 刁现芬 陈思平 吴佩娜 梁长虹 汪元美. 三维窄带水平集算法在内耳分割中的应用[J]. J4, 2007, 41(6): 919-924.