本文為西班牙馬德裡卡洛斯三世大學(作者:Abdulla H. Al-Kaff)的博士論文,共225頁。 本文的主要目的是為無人機提供一個魯棒的導航系統,使無人機能夠自主、實時地完成復雜的任務。所提出的算法主要是基于單目攝像機捕捉到的視覺信息來解決室外和室內環境下的導航問題。此外,本文還介紹了利用視覺傳感器作為主要數據源,或在提供有用信息方面與其他傳感器互補的優點,以提高傳感的準確性和魯棒性。 本文主要研究了基于計算機視覺技術的無人機姿態估計問題:(1)姿態估計,為無人機6D姿態估計提供了一種解決方案。該算法基于SIFT檢測器和FREAK描述子的結合,保持了特征點匹配的性能,減少了計算時間。在此基礎上,基于世界到幀和幀到幀同構圖的分解,解決了姿態估計問題。(二)障礙物探測和防撞,
本文得出結論:視覺傳感器具有重量輕、功耗低、信息可靠等優點,被認為是提高無人機自主性的有力工具。 The main objective of this dissertation isto provide Unmanned Aerial Vehicles (UAVs) with a robust navigation system; inorder to allow the UAVs to perform complex tasks autonomously and in real-time.The proposed algorithms deal with solving the navigation problem for outdoor aswell as indoor environments錛 mainly based on visual information that iscaptured by monocular cameras. In addition錛 this dissertation presents theadvantages of using the visual sensors as the main source of data錛 orcomplementing other sensors in providing useful information; in order toimprove the accuracy and the robustness of the sensing purposes. Thedissertation mainly covers several research topics based on computer visiontechniques: (I) Pose Estimation錛 to provide a solution for estimating the 6Dpose of the UAV. This algorithm is based on the combination of SIFT detectorand FREAK descriptor; which maintains the performance of the feature pointsmatching and decreases the computational time. Thereafter錛 the pose estimationproblem is solved based on the decomposition of the world-to-frame andframe-to-frame homographies. (II) Obstacle Detection and Collision Avoidance錛in which錛 the UAV is able to sense and detect the frontal obstacles that aresituated in its path. The detection algorithm mimics the human behaviors fordetecting the approaching obstacles; by analyzing the size changes of thedetected feature points錛 combined with the expansion ratios of the convex hullconstructed around the detected feature points from consecutive frames. Then錛by comparing the area ratio of the obstacle and the position of the UAV錛 themethod decides if the detected obstacle may cause a collision. Finally錛 thealgorithm extracts the collision-free zones around the obstacle錛 and combiningwith the tracked waypoints錛 the UAV performs the avoidance maneuver. (III)Navigation Guidance錛 which generates the waypoints to determine the flight pathbased on environment and the situated obstacles. Then provide a strategy tofollow the path segments and in an efficient way and perform the flightmaneuver smoothly. (IV) Visual Servoing錛 to offer different control solutions (FuzzyLogic Control (FLC) and PID)錛 based on the obtained visual information; inorder to achieve the flight stability as well as to perform the correctmaneuver; to avoid the possible collisions and track the waypoints. All theproposed algorithms have been verified with real flights in both indoor andoutdoor environments錛 taking into consideration the visual conditions; such asillumination and textures. The obtained results have been validated againstother systems; such as VICON motion capture system錛 DGPS in the case of poseestimate algorithm. In addition錛 the proposed algorithms have been comparedwith several previous works in the state of the art錛 and are results proves theimprovement in the accuracy and the robustness of the proposed algorithms.Finally錛 this dissertation concludes that the visual sensors have theadvantages of lightweight and low consumption and provide reliable information錛which is considered as a powerful tool in the navigation systems to increasethe autonomy of the UAVs for real-world applications. 1. 引言2. 最新研究進展3. 基于單目視覺的位姿估計4. 基于單目視覺的障礙物檢測5. 用于無人機的視覺伺服控制6. 結論與未來工作展望附錄A 四旋翼無人機模型附錄B 相機模型與校正更多精彩文章請關注公眾號:BioLitMine (Biological Literature Mining Tool for Human and Model Organisms)Find relationships between genes錛 MeSH terms錛 pathways錛 and people from PubMed literature.https://www.flyrnai.org/tools/biolitmine/web/The published literature encapsulates years of research about biological systems but finding the relevant literature about a gene or a biological topic is not always straightforward. BioLitMine was implemented to help scientists to quickly mine the literature. Users will able to find MeSH terms as well as the relevant literature. BioLitMine can also help scientists find the principle investigators who are working on a gene of interest or a particular signaling pathway to facilitate the scientific collaborations. Current features:Find associating MeSH terms of given gene錛 e.g. wgFind associating genes of given MeSH term錛 e.g. "lung cancer"錛 "stem cells"Find co-cited genes of input geneFind genes list of a given pathwayFind PIs with publications on a given geneFind PIs with publications associated with a given pathway,