摘要
角点检测是实现跟踪注册的基础,被广泛应用于增强现实等环境复杂性实时系统.针对经典的Fast角点检测算法抗噪声及抗强光干扰性能差,而Harris角点检测算法实时性较差,均无法满足增强现实等环境复杂性实时系统需求的问题,提出一种结合灰度值星型辐射投影的角点检测算法.在提取图像边缘的基础上计算检测区域内所有像素点的星型投影值,通过投影值主峰区域和主峰间距的判定逐步剔除伪角点,最终实现鲁棒的角点检测.在自然场景、COIL-100数据集中的实验结果表明,该算法在实时性和鲁棒性2个方面取得了较好的检测结果,可适用于增强现实等环境复杂性实时系统.
Corner detection is widely used in real-time systems under complex environments, e.g., the augmented reality system, and is crucial to implement the tracking registration. The classical fast corner detection algorithm performs poorly under noise and strong light conditions, while Harris corner detection algorithm cannot work in real time. Therefore, both of them cannot well satisfy the requirement of the augmented reality system. To address these problems, a novel corner detection algorithm, the star-based grayscale projection, is proposed in this paper: the star projection value of all pixels in the detection area is computed on the basis of extracting the edge of the image, and the false corner points are eliminated gradually by judging the project value of the main peak area and the distance of the main peak. Experimental results show that the detection results of the proposed algorithm are compared to the existing algorithms in two aspects of real time and robustness. The proposed method is robust to noise and strong light, hence it is suitable for real-time systems under complex environment.
引文
[1]Bellarbi A.Toward mobile immersion in augmented reality:an approach based on robust natural feature tracking and 3D interaction[D].Paris:University of Paris-Saclay,2017
[2]Zhang Weichuan,Kong Xiangnan,Song Wen.Review of image corner detection algorithms[J].Acta Electronica Sinica,2015,43(11):2315-2321(in Chinese)(章为川,孔祥楠,宋文.图像的角点检测研究综述[J].电子学报,2015,43(11):2315-2321)
[3]Bakar S A,Hit M S,Wan N J.Improved global and local curvature properties for shape corner detection[J].Journal of Applied Sciences,2017,17(9):458-466
[4]Wang L,Fei M R,Yang T C.Circular mask and Harris corner detection on rotated images[C]//Proceedings of International Conference on Life System Modeling and Simulation,and International Conference on Intelligent Computing for Sustainable Energy and Environment..Singapore:Springer,2017:524-535
[5]Trajkovicand M,Hedley M.Fast corner detection[J].Image and Vision Computing,1998,16(2):75-87
[6]Park S,Kim G,Park J,et al.A 1.5nJ/pixel super-resolution enhanced FAST corner detection processor for high accuracy AR[C]//Proceedings of the 40th European Solid State Circuits Conference.Los Alamitos:IEEE Computer Society Press,2014:191-194
[7]Wu L F,Gao Y,Zhang J W.An improved SIFT algorithm based on FAST corner detection[C]//Proceedings of the 9th International Conference on Intelligent Information Hiding and Multimedia Signal Processing.Los Alamitos:IEEE Computer Society Press,2013:202-205
[8]Hossen M K,Deb K.Vehicle license plate detection and tilt correction based on HSI color model and SUSAN corner detector[J].Smart Compiting Review,2014,4(5):371-388
[9]Hong Lei,Ji Baojian,Ling Chao.A modified algorithm for incomplete corner identification of chess board target[J].Journal of Computer-Aided Design&Computer Graphics,2016,28(9):1521-1526(in Chinese)(洪磊,嵇保健,凌超.一种棋盘格靶标不完整角点识别的修正算法[J].计算机辅助设计与图形学学报,2016,28(9):1521-1526)
[10]Rosten E,Drummond T.Machine learning for high-speed corner detection[C]//Proceedings of the European Conference on Computer Vision.Heidelberg:Springer,2006,3951:430-443
[11]Harris C J.A combined corner and edge detector[C].Proceedings of 4th Alvey Vision Conference,1988,(3):147-151
[12]Sousa E R,Tanase A,Hannig F,et al.Accuracy and performance analysis of Harris corner computation on tightly-coupled processor arrays[C]//Proceedings of Conference on Design and Architectures for Signal and Image Processing.Los Alamitos:IEEE Computer Society Press,2013:88-95
[13]Yang Guangxue,Hu Jiawei,Kang Shouqiang,et al.A motion tracking system based on the polynomial expansion and Harris corner[J].Journal of Harbin University of Science and Technology,2017,22(3):48-53(in Chinese)(杨广学,胡嘉维,康守强,等.基于多项式展开及Harris角点的轨迹跟踪系统[J].哈尔滨理工大学学报,2017,22(3):48-53)
[14]Zhang Long,Wu Zichao,Wang Yigang.Laplacian line drawing algorithm based on difference-of-Gaussian approximation[J].Journal of Computer-Aided Design&Computer Graphics,2015,27(10):1936-1943(in Chinese)(张龙,吴子朝,王毅刚.采用高斯差分算子的拉普拉斯线绘制[J].计算机辅助设计与图形学学报,2015,27(10):1936-1943)
[15]Zhang C H,Zhong W F,Zhang C Y,et al.Simulation design of improved OPTA thinnin algorithm[C]//Proceedings of International Conference on Mechatronics and Intelligent Robotics.New York:Springer Press,2017:105-114
[16]Nene S A,Nayar S K,Murase H.Columbia object image library(COIL-100)[R].New York:Columbia University,1996
[17]Zhao Yali,Zhang Weichuan,Li Yunhong.Novel contour-based corner detection with adaptive threshold[J].Journal of Image and Graphics,2016,21(11):1502-1514(in Chinese)(赵亚利,章为川,李云红.图像边缘轮廓自适应阈值的角点检测算法[J].中国图象图形学报,2016,21(11):1502-1514)