计算机科学 ›› 2017, Vol. 44 ›› Issue (3): 313-317.doi: 10.11896/j.issn.1002-137X.2017.03.063
涂兵,潘建武,吴健辉,曾香,曹旭
TU Bing, PAN Jian-wu, WU Jian-hui, ZENG Xiang and CAO Xu
摘要： 天际线检测在视觉导航、地理图像标注中有着重要的作用。首先采用区域协方差算法对图像进行初分割,确定天际线检测的目标区域；接着根据分析数据集中的样本图片梯度值得到的最优梯度阈值,在初分割的天际线检测目标区域,提出一种循环梯度算法来检测出图像中各列的天际线位置坐标；最后采用中值滤波算法对检测的天际线各点坐标值进行校正,消除可能存在的天际线奇异点,检测出输入图像中的天际线。所提算法在内华达大学机器视觉实验室Web set和Baatz set数据集上进行了测试,实验结果表明:提出的算法能有效地检测出数据集中输入图像的天际线,不需要对图像的边缘信息进行提取,具有良好的有效性和时效性。
| [1] CROON G C H E D,REMES B D W,WASZAK C D,et al.Sky Segmentation Approach to Obstacle Avoidance[C]∥IEEE Aero-space Conference.2011:1-16. [2] ETTINGER S M,NECHYBA M C,IFJU P G,et al.Vision-guided flight stability and control for micro air vehicles[J].Advanced Robotics,2002,3(7):2134-2140. [3] MCGEE T G,SENGUPTA R,HEDRICK K.Obstacle Detection for Small Autonomous Aircraft Using Sky Segmentation[C]∥IEEE International Conference on Robotics and Automation.2005:4679-4684. [4] TODOROVIC S,NECHYBA M C,IFJU P G.Sky/ground mo-deling for autonomous MAV flight[J].IEEE International Conference on Robotics and Automation,2003,1(1):1422-1427. [5] THURROWGOOD S,SOCCOL D,MOORE R J D,et al.A vision based system for attitude estimation of UAVs[C]∥IEEE/RSJ International Conference on Intelligent Robots and Systems Thurrowgood.Saul,2009:5725-5730. [6] THURROWGOOD S,MOORE R J D,BLAND D,et al.UAVAttitude Control using the Visual Horizon[C]∥Proceedings of the 2010 Australasian Conference on Robotics and Automation(ACRA 2010). [7] BOROUJENI N S,ETEMAD S A,W HITEHEAD A.Robust Horizon Detection using Segmentation for UAV Applications[C]∥2012 Ninth Conference on Computer and Robot Vision.2012:346-352. [8] HUNG Y,SU C,CHANG Y,et al.Skyline localization formountain images[C]∥IEEE International Conference on Multimedia and Expo.2013:1-6. [9] LIE W,LIN T C I,LIN T,et al.A robust dynamic programming algorithm to extract skyline in images for navigation[J].Pattern Recognition Letters,2005,26(2):221-230. [10] VERBICKAS R,WHITEHEAD A.Sky and Ground Detection Using Convolutional Neural Networks[J].International Confe-rence on Machine Vision and Machine Learning,2014,64(4):1-10. [11] YAZDANPANAH A P,REGENTOVA E E,MANDAVA A K,et al.Sky Segmentation by Fusing Clustering with Neural Networks[J].Lecture Notes in Computer Science,2013,8034:663-672. [12] GERSHIKOV E,LIBE T,KOSOPAPOV S.Horizon Line De-tection in Marine Images:Which Method to Choose[J].International Journal on Advances in Intelligent Systems,2013,6(1/2):79-88. [13] YANG J H,LI C H,WEI D Y,et al.Sea-sky-line locating algorithm based on complicated sea-sky background row-mean curve[J].Laser and Infrared,2012,42(12):1346-1350.(in Chinese) 杨家红,李翠红,危德益,等.基于复杂海空背景行均值曲线的还天线定位算法[J].激光与红外,2012,42(12):1346-1350. [14] GUI Y,LI L C,WANG K P,et al.A new method of sea-sky-line detection based on region variance and RANSAC algorithm[J].Laser and Infrared,2008,38(4):638-641.(in Chinese) 桂阳,李立春,王鲲鹏,等,基于区域方差和RANSAC的海天线检测新方法[J].激光与红外,2008,38(4):638-641. [15] LIU S T,ZHOU X D,WANG C G.Robust sea-sky-line detection algorithm under complicated sea-sky background[J].Opto-Electronic Engineering,2006,33(8):5-10.(in Chinese) 刘松涛,周晓东,王成刚.复杂海空背景下鲁棒的海天线检测算法研究[J].光电工程,2006,33(8):5-10. [16] AHMAD T,BEBIS G,REGENTOVA E,et al.A Machine Lear-ning Approach to Horizon Line Detection Using Local Features[M].Advance in Visual Computing.Springer Berlin Heidelberg,2013:181-193. [17] FARID H.Exposing digital forgeries from JPEG ghosts[J].IEEE Trans on Information Forensics and Security,2009,4(1):154-160. [18] NI L,GONG Q,CAO L,et al.Two-dimensional Otsu image segmentation algorithm based on adaptive weighted median filter[J].Application Research of Computers,2013,30(2):588-590.(in Chinese) 倪麟,龚劬,曹莉,等.基于自适应加权中值滤波的二维Otsu图像分割算法[J].计算机应用研究,2013,30(2):588-590. [19] CHEN M X,ZHOU Y L,ZHANG Q Z.Directional weighted filter with 12 directions to remove random valued impulse noise[J].Application Research of Computers,2014,31(5):1584-1587.(in Chinese) 陈明轩,周亚丽,张奇志.基于12个方向的方向加权滤波算法去除随机值脉冲噪声[J].计算机应用研究,2014,31(5):1584-1587. [20] ZHAO Z G,WU X,ZHANG W Z,et al.Palmprint recognition algorithm of integrating horizontal gradient and local information intensity[J].Computer Science,2015,42(6):317-321.(in Chinese) 赵志刚,吴鑫,张维忠,等.融合水平梯度与局部信息强度的掌纹识别算法[J].计算机科学,2015,42(6):317-321. |
| No related articles found! |
|
||
首页