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。
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.