A thorough analysis of unsupervised depth and ego-motion estimation

Download
2020-8
Sarı, Alp Eren
Recent years have shown unprecedented success in depth estimation by jointly solving unsupervised depth estimation and pose estimation. In this study, we perform a thorough analysis for such an approach. Initially, pose estimation performances of classical techniques, such as COLMAP, are compared against recent unsupervised learning-based techniques. Simulation results indicate the superiority of Bundle Adjustment step in classical techniques. Next, the effect of the number of input frames to the pose estimator network is investigated in detail. The experiments performed at this step revealed that the state-of-the-art can be improved by providing extra frames to the pose estimator network. Finally, the semantic labels of objects in the scene are utilized individually during pose and depth estimation stages. For this purpose, pre-trained semantic segmentation networks are utilized. The effect of computing losses from different regions of the scene and averaging different pose estimations with learnable weights are investigated. The poses and losses corresponding to different semantic classes are summed with learnable weights yielding comparable results against state-of-the-art methods.

Suggestions

A CRITIQUE ON FATIGUE CRACK-GROWTH LIFE ESTIMATION METHODOLOGIES
AKYUREK, T; BILIR, OG (Elsevier BV, 1992-01-01)
In this study, three fatigue crack growth life estimation methodologies are reviewed and sample calculations are made using these methodologies. Comparison of the results with respect to the methodologies are made. Three computer codes which represent these methodologies, CRACKS IV, FASTRAN and FATIGUE are selected for the analyses. The estimations are also correlated to the test results found in the literature. FALSTAFF spectra are used in the analyses.
A SURVEY OF FATIGUE CRACK-GROWTH LIFE ESTIMATION METHODOLOGIES
AKYUREK, T; BILIR, OG (Elsevier BV, 1992-07-01)
In this study, three fatigue crack growth life estimation methodologies are reviewed and sample calculations are made using these methodologies. Comparisons of the results with respect to the methodologies are made. Three computer codes which represent these methodologies, CRACKS IV, FAST and FATIGUE, are selected for the analyses. The estimations are also correlated to the test results.
Development of synthetic and real-world pose estimation dataset to be used in human tracking system
Ersoy, Mustafa; Koku, Ahmet Buğra; Department of Mechanical Engineering (2022-4-29)
In this study, we propose an extendable, synthetic human pose estimation dataset named “Metupose”. Pose estimation aims to determine the pose of a person by detecting joints in an image or video. Dataset was created in Blender 3D software and with varying human objects and environment. It is also used to enhance the accuracy of pose estimation models in the literature. Metupose dataset contains 178000 images. Images have 1 to 4 people in it, where there is a total of 402000 people exist in these images. Whe...
An analysis of stereo depth estimation utilizing attention mechanisms, self-supervised pose estimators & temporal predictions
Oğuzman, Utku; Alatan, Abdullah Aydın; Department of Electrical and Electronics Engineering (2022-5-18)
By the recent success of deep learning, real-world applications of stereo depth estimation algorithms attracted the interest of many researchers. Using the available datasets, synthetic or real-world, the researchers begin analyzing their ideas for practical applications. In this thesis, a thorough analysis is performed of such an aim. The state-of-the-art stereo depth estimation algorithms are tried to be improved by incorporating attention mechanisms to the current networks and better initialization strat...
HPRNet: Hierarchical point regression for whole-body human pose estimation
SAMET, NERMİN; Akbaş, Emre (2021-11-01)
In this paper, we present a new bottom-up one-stage method for whole-body pose estimation, which we call “hierarchical point regression,” or HPRNet for short. In standard body pose estimation, the locations of ~17 major joints on the human body are estimated. Differently, in whole-body pose estimation, the locations of fine-grained keypoints (68 on face, 21 on each hand and 3 on each foot) are estimated as well, which creates a scale variance problem that needs to be addressed. To handle the scale variance ...
Citation Formats
A. E. Sarı, “A thorough analysis of unsupervised depth and ego-motion estimation,” M.S. - Master of Science, Middle East Technical University, 2020.