基于回测光流法的室内结构线端点跟踪
|
摘要
时间序列图像的特征跟踪技术有着巨大的潜在应用,然而传统的光流法跟踪算法由于其精度不高而影响了其实用性。针对这一问题提出一种基于回测光流法的结构线端点跟踪方法。将图像上的建筑结构线的端点作为目标特征,在序列图像的当前参考帧进行特征检测,利用光流跟踪法得到特征在下一帧图像上的对应位置;进一步将跟踪到的特征位置点用于回测跟踪,将回测跟踪的结果与参考帧原始检测到的特征位置进行比较,排除掉误差大的特征点,最终获得有效特征检测结果。将改进后的光流法应用于视觉里程计,实验结果表明,结构线端点特征稳定,回测光流跟踪精度较高,视觉里程计的计算轨迹精度比应用传统光流法有明显提高。
Tracking features on image time series have huge potential for many applications, but the popular optical flow tracking algorithm is less practical because of its less accuracy. To tackle this problem, this paper proposes a method of tracking endpoints of indoor structure lines based on backprobing of optical flow. The endpoints of the building structure lines indoor are used as target features to be detected on the reference frame of image series, then the features are tracked using the optical flow algorithm to obtain the corresponding positions on the next frame of images; The idea is backprobing which means tracking the corresponding positions back to the reference frame to get the backprobing positions, and comparison is made between the original feature positions and the backprobing positions which should be no difference ideally on the reference frame; The effective features are finally selected by eliminating the ones with large differences. This improved optical flow tracking algorithm is applied to the visual odometry, and the experiment results show that the image features of structure-line-endpoints are stable, and the backprobing optical flow tracking method has a high accuracy, and the final trajectory of the visual odometry is significantly improved compared with the traditional optical flow algorithm.
Tracking features on image time series have huge potential for many applications, but the popular optical flow tracking algorithm is less practical because of its less accuracy. To tackle this problem, this paper proposes a method of tracking endpoints of indoor structure lines based on backprobing of optical flow. The endpoints of the building structure lines indoor are used as target features to be detected on the reference frame of image series, then the features are tracked using the optical flow algorithm to obtain the corresponding positions on the next frame of images; The idea is backprobing which means tracking the corresponding positions back to the reference frame to get the backprobing positions, and comparison is made between the original feature positions and the backprobing positions which should be no difference ideally on the reference frame; The effective features are finally selected by eliminating the ones with large differences. This improved optical flow tracking algorithm is applied to the visual odometry, and the experiment results show that the image features of structure-line-endpoints are stable, and the backprobing optical flow tracking method has a high accuracy, and the final trajectory of the visual odometry is significantly improved compared with the traditional optical flow algorithm.
引文
[1]郑慧君,陈俞强.基于改进蚁群的路径导航算法[J].控制工程,2016,23(4):608-612.Zheng H J,Chen Y Q.Improved ACO-based Path Navigation Algorithm[J].Control Engineering of China,2016,23(4):608-612.
[2]Fraundorfer F,Scaramuzza D.Visual Odometry:Part II:Matching,Robustness,Optimization,and Applications[J].IEEE Robotics&Amp Amp Automation Magazine,2012,19(2):78-90.
[3]Gibson,James J.The perception of the visual world.[J].American Journal of Psychology,1951,64(3):121-130.
[4]Horn B,Schunck B.Determing optical flow[J].Artificial Intelligence,1981,17(1):185-203.
[5]Lucas B D,Kanade T.An iterative image registration technique with an application to stereo vision[C]//International Joint Conference on Artificial Intelligence.Morgan Kaufmann Publishers Inc.1981:285-289.
[6]Bouguet J Y.Pyramidal implementation of the Lucas Kanade feature tracker description of the algorithm[J].Intel Corporation Microprocessor Research Labs Tech Rep,2000,22(2):363-381.
[7]Baker S,Roth S,Scharstein D,et al.A database and evaluation methodology for optical flow[C]//In Proceedings of the IEEEInternational Conference on Computer Vision.2007:1-8.
[8]柳士俊,张蕾.光流法及其在气象领域里的应用[J].气象科技进展,2015,5(4):16-21.Liu S J,Zhang L.Optical flow tracking algorithm and its application in meteorological field[J].Advances in Meteorological Science and Technology,2015,5(4):16-21.
[9]郑驰,项志宇,刘济林.融合光流与特征点匹配的单目视觉里程计[J].浙江大学学报(工学版),2014,42(2):279-284.Zheng C,Xiang Z Y,Liu J L.Monocular vision odometry based on the fusion of optical flow and feature points matching[J].Journal of Zhejiang University(Engineering Science),2014,42(2):279-284.
[10]Kalal Z,Mikolajczyk K,Matas J.Forward-Backward Error:Automatic Detection of Tracking Failures[C]//International Conference on Pattern Recognition.IEEE,2010:2756-2759.
[11]Hough P V C.Method and means for recognizing complex patterns[J].1962.
[12]Rosten E,Drummond T.Machine Learning for High-Speed Corner Detection[C]//European Conference on Computer Vision.Springer-Verlag,2006:430-443.
[13]Harris C G,Pike J M.3D positional integration from image sequences[J].Image&Vision Computing,1988,6(2):87-90.
[14]Lowe D G,Lowe D G.Distinctive Image Features from Scale-Invariant Keypoints[J].International Journal of Computer Vision,2004,60(2):91-110.
[15]Bay H,Tuytelaars T,Gool L V.SURF:Speeded Up Robust Features[J].Computer Vision&Image Understanding,2006,110(3):404-417.
[16]Rublee E,Rabaud V,Konolige K,et al.ORB:An efficient alternative to SIFT or SURF[C]//IEEE International Conference on Computer Vision.IEEE,2011:2564-2571.
[17]Nist D.An Efficient Solution to the Five-Point Relative Pose Problem[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2003,26(6):756-7.
[2]Fraundorfer F,Scaramuzza D.Visual Odometry:Part II:Matching,Robustness,Optimization,and Applications[J].IEEE Robotics&Amp Amp Automation Magazine,2012,19(2):78-90.
[3]Gibson,James J.The perception of the visual world.[J].American Journal of Psychology,1951,64(3):121-130.
[4]Horn B,Schunck B.Determing optical flow[J].Artificial Intelligence,1981,17(1):185-203.
[5]Lucas B D,Kanade T.An iterative image registration technique with an application to stereo vision[C]//International Joint Conference on Artificial Intelligence.Morgan Kaufmann Publishers Inc.1981:285-289.
[6]Bouguet J Y.Pyramidal implementation of the Lucas Kanade feature tracker description of the algorithm[J].Intel Corporation Microprocessor Research Labs Tech Rep,2000,22(2):363-381.
[7]Baker S,Roth S,Scharstein D,et al.A database and evaluation methodology for optical flow[C]//In Proceedings of the IEEEInternational Conference on Computer Vision.2007:1-8.
[8]柳士俊,张蕾.光流法及其在气象领域里的应用[J].气象科技进展,2015,5(4):16-21.Liu S J,Zhang L.Optical flow tracking algorithm and its application in meteorological field[J].Advances in Meteorological Science and Technology,2015,5(4):16-21.
[9]郑驰,项志宇,刘济林.融合光流与特征点匹配的单目视觉里程计[J].浙江大学学报(工学版),2014,42(2):279-284.Zheng C,Xiang Z Y,Liu J L.Monocular vision odometry based on the fusion of optical flow and feature points matching[J].Journal of Zhejiang University(Engineering Science),2014,42(2):279-284.
[10]Kalal Z,Mikolajczyk K,Matas J.Forward-Backward Error:Automatic Detection of Tracking Failures[C]//International Conference on Pattern Recognition.IEEE,2010:2756-2759.
[11]Hough P V C.Method and means for recognizing complex patterns[J].1962.
[12]Rosten E,Drummond T.Machine Learning for High-Speed Corner Detection[C]//European Conference on Computer Vision.Springer-Verlag,2006:430-443.
[13]Harris C G,Pike J M.3D positional integration from image sequences[J].Image&Vision Computing,1988,6(2):87-90.
[14]Lowe D G,Lowe D G.Distinctive Image Features from Scale-Invariant Keypoints[J].International Journal of Computer Vision,2004,60(2):91-110.
[15]Bay H,Tuytelaars T,Gool L V.SURF:Speeded Up Robust Features[J].Computer Vision&Image Understanding,2006,110(3):404-417.
[16]Rublee E,Rabaud V,Konolige K,et al.ORB:An efficient alternative to SIFT or SURF[C]//IEEE International Conference on Computer Vision.IEEE,2011:2564-2571.
[17]Nist D.An Efficient Solution to the Five-Point Relative Pose Problem[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,2003,26(6):756-7.