運用快速偵測法於視覺里程計

Fast detection algorithms for visual odometry

姚琮獻(Tsung-Hsien Yao)

指導教授 ： 孫崇訓

淡江大學/工學院/機械與機電工程學系碩士班/碩士(2016年)

https://doi.org/10.6846/TKU.2016.00820

摘要

本論文針對視覺里程計(Visual Odometry, VO) 運用幾個演算法對即時性進行改善。首先利用雙眼視覺系所統擷取影像，影像使用直立式加速強健特徵(Upright Speeded-Up Robust Features, U-SURF)偵測地標點。加入循序跳越式盒子濾波器(Ordinal Skip Box Filter)以減少在U-SURF中對影像迴積的次數與計算時間。之後利用參數化三點透視(Parameterized Perspective-Three-Point algorithms)演算法反推視覺系統可能位置。再者利用隨機化隨機取樣一致(Randomized Random Sample Consensus, R-RANSAC)演算法以剔除其他錯誤位置解。最後以地面基準實驗證明改善效果。

關鍵字

視覺里程計 ； 直立式加速強健特徵 ； 參數化三點透視 ； 隨機化隨機取樣一致 ； 循序跳越式盒子濾波器

並列摘要

In this paper, several algorithms are applied to improve the instantaneity of the visual odometry system. First, the binocular stereo camera is used to capture images. The upright speeded-up robust features (U-SURF) algorithm is used to detect features in the images. Ordinal skip box filter added in U-SURF can reduce convolution times and computation time. Then the possible positions of the camera can be determined by the parameterized perspective-three-point algorithm (Parameterized P3P). Next, the randomized random sample consensus (R-RANSAC) algorithm is used to eliminate other error position solutions. Finally, improvement performance is shown on the ground truth experiment.

並列關鍵字

visual odometry(VO) ； upright speeded-up robust features(U-SURF) ； parameterized perspective-three-point(parameterized P3P) ； randomized random sample consensus(R-RANSAC) ； ordinal skip box filter

參考文獻

[1] C.T. Chi, Y.T. Wang, S.T. Cheng, and C.A. Shen, “Robot Simultaneous Localization and Mapping Using a Calibrated RGB-D Sensor, ”Sensors and Materials, vol.26, no.5, pp.353-364, 2014.

[3] H. Bay, A. Ess, T. Tuytelaars, and L. Gool, “SURF: Speeded-Up Robust Features,” Computer Visio and Image Understanding, vol. 110, no.3, pp.346-359, 2008.

[4] Y.T. Wang, and G.Y. Lin, “Improvement of Speeded-Up Robust Features for Robot Visual Simultaneous Localization and Mapping,” Robotica, vol.32, no.4, pp.533-549, 2014.

[5] H. Park, H. Mitsumine, and M. Fujii, “Fast Detection of Robust Features by Reducing the Number of Box Filtering in SURF,” IEICE Transactions Information and Systems, vol. 94, no.3, pp.725-728, 2011.

[6] Y.T. Wang, C.H. Sun, and M.J. Chiou, “Detection of Moving Objects in Image Plane for Robot Navigation Using Monocular Vision,” EURASIP Journal on Advances in Signal Processing, vol.2012, pp.1-22, 2012.