快速攝影機移動下的視覺同步定位與建圖技術研究

A Study of Visual SLAM Techniques under Fast Camera Movements

林炫任(Shiuan-Ren Lin)

指導教授 ： 林文杰

國立交通大學/資訊學院/多媒體工程研究所/碩士(2018年)

摘要

隨著最近幾年自走式機器人、無人機、無人車、虛擬/擴增實境越來越普及，同步定位與建圖技術（simultaneous localization and mapping，SLAM）被認為是這些領域的關鍵技術之一。然而影像的模糊是目前視覺SLAM技術的一項限制。本論文觀察到在基於特徵點的視覺SLAM下，在快速移動時，特徵點取樣分佈主要影響到估測結果的好壞，藉由調整特徵點取樣分佈的情況，最佳化追蹤演算法，進而改善視覺SALM在攝影機快速移動下的運行效果。

關鍵字

同步定位與建圖技術 ； 視覺同步定位與建圖技術 ； 特徵法同步定位與建圖技術 ； 定位與建圖

並列摘要

In recent years, mobile robots, drone, driverless vehicles, VR/AR have become more and more popular. Simultaneous localization and mapping (SLAM) is considered as one of the key technologies in these fields. However, image blurring is a limitation of current visual SLAM technology. We observed that the distribution of feature points mainly influences the estimation results in the feature-based visual SLAM approaches under fast camera movements. We improve the performance of visual SALM by adjusting the distribution of the feature points under fast camera movements.

並列關鍵字

SLAM ； visual SLAM ； feature-based SLAM

參考文獻

[1] Herbert Bay, Andreas Ess, Tinne Tuytelaars, and Luc Van Gool. Speeded-Up Robust Features (SURF). European Conference on Computer Vision, pages 404–417, 2006.

[2] Michael Burri, Janosch Nikolic, Pascal Gohl, Thomas Schneider, Joern Rehder, Sammy Omari, M Achtelik, and Roland Siegwart. The EuRoC MAV datasets. The International Journal of Robotics Research (IJRR), 2015.

[3] Peter J Burt and Edward H Adelson. The Laplacian pyramid as a compact image code. Readings in Computer Vision, pages 671–679, 1987.

[4] Michael Calonder, Vincent Lepetit, Christoph Strecha, and Pascal Fua. Brief: Binary robust independent elementary features. European Conference on Computer Vision, pages 778–792, 2010.

[5] Andrew J Davison, Ian D Reid, Nicholas D Molton, and Olivier Stasse. MonoSLAM: Real-time single camera SLAM. IEEE Transactions on Pattern Analysis and Ma- chine Intelligence (TPAMI), 29(6):1052–1067, 2007.