Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 28 for “"Pose Prediction"”.
-
Dynamic SLAM, object reconstruction, shape and pose prediction for 3D scene understanding
… range of computer vision competencies, including pose estimation, mapping and semantic understanding. However, many challenging research problems remain, three of which are the focus of this work.</p> <p>Firstly, the difficult task of dense mapping in dynamic environments is tackled, utilising a …
-
3M-POSE: MULTI-RESOLUTION, MULTI-PATH AND MULTI-OUTPUT NEURAL ARCHITECTURE SEARCH FOR BOTTOM-UP POSE PREDICTION
Human pose estimation is a challenging computer vision task and often hinges on carefully handcrafted architectures. This paper aims to be the first to apply Neural Architectural Search (NAS) to automatically design a bottom-up, one-stage human pose estimation model with significantly lower …
-
Improving Posing and Ranking of Molecular Docking
… a protein receptor, predict the binding mode (pose) of the ligand within the context of a receptor, (ii) screen a collection of small-molecules against a receptor and rank ligands by their likelihood of being active, and (iii) given a ligand molecule and a target receptor, predict the binding …
-
Canonical mapping as a general purpose representation
… approaches often produce task-specific predictions that are unsuitable for deformable objects or adaptation to other tasks. In this work, conducted within a USDA-funded initiative focused on automating the poultry processing industry, we propose canonical mapping as a near-universal and …
-
DEEP LEARNING MODEL UNCERTAINTY ESTIMATION USING MONTE CARLO DROPOUT TO IMPROVE UAV TARGET POSE PREDICTIONS
Target pose estimation is an important function of many relevant military applications including satellite rendezvous operations and directed energy weapons systems. This task is best left to deep learning (DL) models that can react more quickly than human operators; however, epistemic uncertainty …
-
Predicting the structure and energetics of protein-ligand interaction
… is an important tool for structure and affinity predictions of molecular association, which would lead to the mechanistic understanding of the physicochemical interactions at the atomic level. Protein-small molecule (referred to as "ligand") docking, in particular, has broad application to …
-
Take the Lead: Toward a Virtual Video Dance Partner
… on the other dance partner's movement. Human pose estimation has been applied to dance and computer vision, but many existing applications focus on a single individual or multiple individuals performing. Currently there are very few works that focus specifically on dance couples combined with …
-
Direct Visual-Inertial Odometry using Epipolar Constraints for Land Vehicles
… research efforts are being devoted to make pose predictions using fewer sensors. Currently, laser scanners, which are expensive, have been used as a primary sensor for environment perception as they measure obstacle distance with good accuracy and generate a point-cloud map of the …
-
Determination of TCR-Specific Fingerprints Through Structural Modeling
… this field, particularly regarding TCR docking pose prediction. We used molecular dynamics simulation (300 ns) to define the TCR fingerprints, which are the interaction profiles between the complementarity-determining regions (CDRs) of the TCRs and peptides. This experiment was performed for a …
-
Language Guided Out-of-Bounding Box Pose Estimation for Robust Ice Hockey Analysis
Accurate estimation of human pose and the pose of interacting objects, such as hockey sticks, is fundamental in vision-driven hockey analytics and crucial for tasks like action recognition and player assessment. Estimating 2D keypoints from monocular video is challenging, particularly in fast-paced …
-
Water-based Lead Generation
… interactions and, in some cases, improved pose prediction. Inclusion of bridging water molecules helped to enrich known actives with or without a ligand core similar to the co-crystallized compound, and the selection of ligands (for whom interactions with bridging waters are important) can …
-
Modelling the Form and Function of the Paediatric Musculoskeletal System
… equations, linear scaling, and shape model prediction. Our novel shape model prediction exhibited superior accuracy compared to alternative methods. Addressing the challenge of rapidly generating musculoskeletal geometry in a paediatric population, this thesis presents population-based shape …
-
Deep probabilistic methods for improved radar sensor modelling and pose estimation
… captured, additionally allowing uncertainty in predictions to be identified and managed. The approach is trained entirely using partial labels generated automatically from lidar, without requiring manual labelling.</p> <p>Next, a deep model is proposed for generating stochastic radar …
-
Developing novel scoring functions for protein-ligand docking using machine learning
… a diverse test set. We further investigate the predictions of a Random Forest using only ligand-based features, and find that, when a ligand has different binding affinities for multiple binding partners, this ligand-only model is predictive of the mean binding affinity of a ligand for its …
-
Solvation Thermodynamic Mapping Approaches for Computer-Aided Drug Discovery
… and develop water-based pharmacophores to aid in pose prediction and virtual screening. Our findings reveal that water does not always make full complementary interactions when the protein’s motion is restrained. This led us to investigate how solvation thermodynamics vary with protein structural …
-
Robust Real-Time Model Predictive Control for High Degree of Freedom Soft Robots
… is developed which is shown to decrease the pose prediction error at the end of a 1.5 m robot arm by about 85\%. A novel dynamic modelling approach which can be evaluated within microseconds is then formulated for continuum type soft robots. We show that deep neural networks (DNNs) can be …
-
Body Pose Predictions in Triadic Social Interactions
Human beings are social animals in that they need to socialize with each other to build companionship and thrive alongside other humans. One of the primary characteristics of social interactions is the signals used by people to communicate their thoughts effectively. These include gesturing with …
-
CATEGORY LEVEL POSE ESTIMATION VIA INSTANCE CANONICALIZATION
This thesis describes a study of pose estimation. Pose estimation is the determination of an object’s position and orientation in some coordinate frame. Pose estimation has applica- tion in robotics, augmented/virtual reality, and human-computer interaction, among others. An overview of the field …
-
Uncertainty Quantification of Tightly Integrated LiDAR/IMU Localization Algorithms
… data improves LiDAR position and orientation (pose) prediction and LiDAR limits the IMU error drift over time. In addition, LiDAR return-light intensity measurements improve landmarks recognition. As compared to using the sensors individually, tightly-coupled IMU/LiDAR not only increases pose …
Page 1 of 2