DSpace Community:
http://hdl.handle.net/10203/175379
2024-03-29T09:04:04ZRobust visual place recognition-based localization for navigation and preclinical magnetic particle imaging
http://hdl.handle.net/10203/308020
Title: Robust visual place recognition-based localization for navigation and preclinical magnetic particle imaging
Authors: Choi, Seung-Min
Abstract: Visual place recognition is a crucial research topic that can be utilized in various ways concerning location recognition in computer vision and robotics. This dissertation deals with a novel visual place recognition (VPR) method robust to urban environments crowded with dynamic objects. Furthermore, its key components are utilized for visual localization of navigation and distortion correction research of medical tomography images.
First, we propose a robust visual place recognition method that suppresses the effect of dynamic objects by self-supervised learning in an urban environment with many dynamic things. Visual place recognition searches for images most similar to an input query image among a geo-tagged database and outputs its place. However, its accuracy is severely degraded when images include many dynamic objects that change over time, such as vehicles and pedestrians. To this end, we propose a new self-supervised de-attention mechanism that suppresses the influence of dynamic objects in images. In addition, sharpened triplet marginal loss is proposed to improve the global descriptor discrimination of the VPR, and its effectiveness is visualized. Subsequently, the re-ranking process using geometric verification based on deep local features follows. Finally, we apply the above three new approaches to the NetVLAD backbone, widely used in image-based location recognition, and train and test it with public datasets. To overcome the lack of datasets crowded with dynamic objects such as vehicles and people, we propose a clutter augmentation method that augments the density of dynamic objects in images.
Second, we employ the proposed robust visual place recognition method for the global localization of a robot in a city. Next, localization for robot navigation is also an essential research topic in robotics. Generally, expensive 3D Lidar sensors and pre-map building are used for localization instead of GNSS (Global Navigation Satellite System) with severe position errors in shaded areas and indoors. However, because astronomical costs are required to introduce public robot services at the city level with such an expensive localization method, studies on cost-effective robot localization are crucial for robot navigation. To this end, we introduce a robot camera image and free street view images into the query and database, respectively, and predict the robot’s location on a free online map. Monte Carlo localization (MCL) is utilized for global localization, and the VPR location result is introduced into its sensor model. However, suppose the domain difference between the learning and the test images is severe or similar scenes are repeated, such as a walking path or a long corridor. In that case, the reliability of the VPR is decreased. To cope with this, we define the visible region based on the predicted location
and restrict only the results within the visible region to valid sensor observations.
Lastly, we utilize the geometrical verification method of the proposed VPR for 2D tomography image registration of a novel magnetic particle imaging device. A magnetic particle imaging (MPI) system has recently attracted attention as a medical diagnosis device using a safe tracer without radiation exposure. Similar to research in the future vehicle interdisciplinary field, novel MPI development research requires extensive interdisciplinary convergence research in electricity, electronics, physics, materials, pharmacy, medicine, hospital clinical, robotics, and computer vision. Therefore, this study is possible only in a few advanced countries, such as the United States and Germany, where the technology has evenly reached the completion stage. We have successfully developed a novel point-of-care compact MPI for the first time in Korea. In this dissertation, we introduce it and employ the proposed geometric verification method of VPR for its image processing. In particular, we present a method for calibrating the distortion of 2D tomography images accumulated from the manufacturing stage by homography
estimation based on fiducial markers and restoring it in a three-dimensional (3D) MPI image.
Description: 학위논문(박사) - 한국과학기술원 : 미래자동차학제전공, 2023.2,[vii, 77 p. :]2023-01-01T00:00:00ZNew gate control technique for ripple reduction in renewable energy DC-DC converter
http://hdl.handle.net/10203/308338
Title: New gate control technique for ripple reduction in renewable energy DC-DC converter
Authors: Chae, Jongyoon
Abstract: Recently, as global warming and environmental issues have emerged, interest in renewable energy sources such as fuel cells and photovoltaics has increased. In the case of renewable energy, a DC-DC converter is required when connected to the system due to intermittent power generation. Recently, various studies have been aimed at improving the performance of DC-DC converters interconnected to renewable energy. However, in previous studies, the effect of dead time on the performance or operation of the power converter was neglected. In DC-DC converters, dead time is essential to prevent shoot-through, but due to the effect of this dead time, the converter's performance or operation might be degraded. For example, input current ripple increases in a DC-DC converter for a fuel cell system, and output voltages are unbalanced in a voltage balancer-integrated DC-DC converter for photovoltaics. In this study, the dead time effect on DC-DC converters interconnected to renewable energy is analyzed, and a new gate control technique is proposed to mitigate the dead time effect.
Description: 학위논문(석사) - 한국과학기술원 : 미래자동차학제전공, 2023.2,[iii, 35 p. :]2023-01-01T00:00:00ZStereo confidence measurement based on linearity of disparity profile for monocular depth estimation
http://hdl.handle.net/10203/308337
Title: Stereo confidence measurement based on linearity of disparity profile for monocular depth estimation
Authors: Ka, Woonghyun
Abstract: In stereo matching, one of the fundamental problems in computer vision fields, errors within occlusions, object boundaries, reflective surfaces, textureless regions, and repeated pattern regions remain critical problems to be solved. Stereo confidence estimation plays a role in mitigating the aforementioned problems by detecting unreliable pixels in disparity obtained through stereo-matching and being used to refine the results of those pixels. However, in the case of previous learning-based methods, there is a limitation in that a separate training process is needed. In this thesis, we propose a stereo confidence measurement method without extra network and training by defining an ideal disparity profile according to the disparity plane sweep based on the linearity of the disparity profile. Experimental results in self-supervised monocular depth estimation problems, where stereo confidence estimation is utilized, demonstrate the validity of the proposed method.
Description: 학위논문(석사) - 한국과학기술원 : 미래자동차학제전공, 2023.2,[iii, 18 p. :]2023-01-01T00:00:00ZPath tracking and adaptive cruise control considering vehicle mass and road gradient
http://hdl.handle.net/10203/308334
Title: Path tracking and adaptive cruise control considering vehicle mass and road gradient
Authors: Kim, Jiwoo
Abstract: For driver safety and convenience, research on autonomous driving is being actively conducted. In real driving, there exist mass uncertainty from passenger or load and the road has various road gradient. For real driving situations especially when deceleration is needed, accurate mass and road gradient information are essential and directly related to safety problems. In this study, path tracking and adaptive cruise control considering vehicle mass and road gradient are designed. Model Predictive Control(MPC) is designed for path tracking and adaptive cruise control while considering lateral and longitudinal vehicular systems. Vehicle mass and road gradient are estimated by Recursive Least Square(RLS) with multiple forgetting factors and applied to the MPC for improving the accuracy of the model and ultimately the performance of MPC. The real-time simulation was conducted before and after estimation and the improvement of the safety was verified.
Description: 학위논문(석사) - 한국과학기술원 : 미래자동차학제전공, 2023.2,[iv, 40 p. :]2023-01-01T00:00:00Z