From coarse to fine: Quickly and accurately obtaining indoor image-based localization under various illuminations.

摘要

The focus of this dissertation is on improving accuracy and efficiency for indoor image- or video-based localization under different situations. I introduce the 3D Structure-from-Motion (SfM) reconstruction model into the indoor localization framework. In order to make features more discriminant for building 2D-to-3D correspondences, I learn a projection matrix and project features to a more discriminant space. I then change the distance computation method from Euclidean distance to Hellinger distance to improve the localization accuracy.;In a crowded environment, the captured images in an indoor environment usually contain people, which often leads to an inaccurate camera pose estimation. In my approach, people are segmented out in the videos by means of an optical flow technique and background is completed. The correspondence selection method is through graph matching to enhance both image registration speed and camera pose estimation accuracy. In addition to SfM-based methods, I propose another multi-view, image-based localization framework. I perform image retrieval to roughly obtain the image location. I regard each view direction as a task and perform image retrieval in a multi-task learning framework. By performing the multi-view image retrieval, the image location and orientation are achieved at the same time.;To cope with dark environment, I implement a localization method based on thermal imaging which captures the object surface temperature instead of light. To overcome the limitation of few thermal image samples available, I apply transfer learning to enhance the training of the thermal image classification. To select the most informative samples used in the learning process, I combine active learning with transfer learning to make the classification model more accurate.;To better explore scene geometric attributes, I further use a 3D model reconstructed by a short video as the query to realize 3D-to-3D localization under a multi-task, point-retrieval framework. First, the use of a 3D model as the query enables efficient selection of location candidates. Furthermore, by exploring shared information (matching features during SfM) across multiple related tasks (images of the same scene captured from different views) through multi-task learning, the visual feature's view-invariance property can be improved to achieve higher point-retrieval accuracy.