2026-09-18T19:16:20Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/115799 2023-07-11 col_2142_5131 col_2142_8888 com_2142_5130 com_2142_8887 com_2142_234

Driggs-Campbell, Katherine Rose 2022-05 application/pdf en text Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2022-11-11 without embargo terms The student, Weihang Liang, accepted the attached license on 2022-04-28 at 16:22. The student, Weihang Liang, submitted this Thesis for approval on 2022-04-28 at 16:35. This Thesis was approved for publication on 2022-04-29 at 08:08. DSpace SAF Submission Ingestion Package generated from Vireo submission #17999 on 2022-11-11 at 17:54:09 Geometry-based video prediction with camera motion for mobile robotics Liang, Weihang 2022-04-29 Video Prediction Computer Vision Robotics Machine Learning Video prediction is one of the fundamental research problems in computer vision, and it has a wide range of applications in planning and control for robotics. Recent learning-based approaches show promising results on various video datasets, and some have seen successful applications in planning robot arm motion. However, predicting future observations in a sequence given a set of past images remains a challenging task in mobile robotics, especially when the camera is in motion. Early works in this area use deterministic approaches, which often yield visually unintuitive results due to the intrinsic variability of motion in the future. More recent works have adopted stochastic models to generate sharper future frames. However, most methods do not account for camera motion and perform poorly in scenarios with moving cameras when they are deployed on vehicles and mobile robots. To solve the challenging task of video prediction on mobile platforms, we propose a geometry-based prediction framework that combines visual odometry prediction and view synthesis. Based on a sequence of observed frames, our method first predicts future camera poses and extracts the 3D geometry of the world, which are then jointly used to generate predicted future frames. Specifically, we train a recurrent visual odometry prediction model conditioned on raw RGB images with ground-truth pose labels. In addition, we train SynSin, a view synthesis method to generate 2D images from novel viewpoints using a 3D world representation. By combining these approaches, we demonstrate that our hierarchical deterministic approach outperforms previous stochastic works on the KITTI dataset. Thesis eng https://hdl.handle.net/2142/115799 Copyright 2022 Weihang Liang M.S. Thesis Electrical & Computer Engr University of Illinois at Urbana-Champaign Electrical & Computer Eng