摘要
针对天际线的高鲁棒性与高准确率检测问题,提出了一种多特征提取与边缘校正融合的天际线检测算法。采用Gabor纹理特征和颜色特征提取天空与非天空区域随机训练像素点的多特征值,接着采用支持向量机(SupportVector Machine,SVM)对多特征值训练得到分类器,从而检测出天际线的初始坐标位置;接着采用Canny算子对灰度化图像进行边缘检测,并利用线性五邻域搜索算法对初始坐标位置进行校正,最终得到天际线坐标位置。最后将所提算法在Web数据集和Basalt Hills数据集上进行测试,实验结果表明:提出的算法能有效地检测出较复杂图像场景中的天际线位置,在一定程度上减少了图像中相关像素点的干扰,使检测出的天际线更加平滑。
Focused on the issue of high robustness and high accuracy detection of skyline, a skyline detection algorithm based on multiple feature extraction and edge correction is proposed. The multi-eigenvalues of the training pixels randomly in sky and non-sky regions are extracted according to texture information and color information. Then, the multi-eigenvalues are used to train a classifier based on Support Vector Machine(SVM)to obtain the initial position coordinates of skyline.Next, the Canny operator method is used to detect the edge of the gray image. And the linear five neighborhood search algorithm is used to correct the position of the initial coordinate, finally skyline coordinates of original images are obtained.The proposed algorithm is tested on the Web Set and the Basalt Hills Set, the results indicate that the proposed method can effectively detect the skyline coordinates, reduce the interference of other pixels to some extent and make the skyline more smoothly.
引文
[1]de Croon G,de Wagter C,Remes B,et al.Sky segmentation approach to obstacle avoidance[C]//IEEE Aerospace Conference,2011:1-16.
[2]李寿涛,李小毛,唐延东.天际线识别在森林烟火识别中的应用[J].红外与激光工程,2006,35(s4):414-418.
[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]Tian Jing,Wu Hongmei,Zhao Shengli.Application of skyline in urban parts management[J].Geomatics&Spatial Information Technology,2013(12).
[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]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.
[7]涂兵,潘建武,吴健辉,等.区域协方差与中值校正融合的天际线检测算法研究[J].计算机科学,2017,44(3):313-317.
[8]Hung Y,Su C,Chang Y,et al.Skyline localization for mountain 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]Ahmad T,Bebis G,Regentova E,et al.A machine learning approach to horizon line detectionusing local features[C]//International Symposium on Visual Computing,2013:181-193.
[11]Kim B,Shin J,Nam H,et al.Skyline extraction using a multistage edge filtering[J].International Scholarly and Scientific Research and Innovation,2011(79):108.
[12]Liu Y J,Chiu C C,Yang J H.A robust vision-based skyline detection algorithm under different weather conditions[J].IEEE Access,2017,PP(99):1.
[13]Mcgee T G,Sengupta R,Hedrick K.Obstacle detection for small autonomous aircraft using sky segmentation[C]//IEEE International Conference on Roboties and Automation,2005.
[14]Frajberg D,Fraternali P,Torres R N.Convolutional neural network for pixel-wise skyline detection[C]//International Conference on Artificial Neural Networks.Cham:Springer,2017:12-20.
[15]丛杨,李小毛,田建东,等.基于天际线识别的无人机实时姿态角估计[J].仪器仪表学报,2009,30(5):938-943.
[16]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.
[17]吕俊伟,王成刚,周晓东,等.基于分型特征和Hough变换的海天线检测算法[J].海军航空工程学院学报,2006,21(5):545-548.
[18]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.
[19]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.
[20]Sotiris V A,Tse P W,Pecht M G.Anomaly detection through a bayesiansupport vector machine[J].IEEE Transactions on Reliability,2010,59(2):277-286.