Sökning: "projection error"
Visar resultat 1 - 5 av 20 uppsatser innehållade orden projection error.
1. Hardware Accelerator of Bundle Adjustment Algorithm
Master-uppsats, Lunds universitet/Institutionen för elektro- och informationsteknikSammanfattning : With the popularization and development of CV technology, the SLAM algorithm is widely used in scenarios such as self-driving cars and autonomous navigation robots. As a key step in the SLAM system, the BA algorithm is responsible for optimizing camera parameters and 3D point coordinates. LÄS MER
2. FAULT DETECTION OF PROJECTION ON CURVED SURFACE
Master-uppsats, Mälardalens universitet/Akademin för innovation, design och teknikSammanfattning : In this thesis a system that evaluates projection systems is designed and tested. The type of projection systems of concern feature display surfaces that are curved in two axes. The system uses a calibration image featuring evenly spaced circles. This image is projected onto the display surface. LÄS MER
3. Single image scene-depth estimation based on self-supervised deep learning : For perception in autonomous heavy duty vehicles
Uppsats för yrkesexamina på avancerad nivå, Uppsala universitet/Avdelningen för visuell information och interaktionSammanfattning : Depth information is a vital component for perception of the 3D structure of vehicle's surroundings in the autonomous scenario. Ubiquity and relatively low cost of camera equipment make image-based depth estimation very attractive compared to employment of the specialised sensors. LÄS MER
4. Damaged starch and dietary fibre content in Swedish wheat flour : PLS-modelling to predict baking volume
Master-uppsats, SLU/Department of Molecular SciencesSammanfattning : SDmatic, SRC-CHOPIN 2 and Alveolab are used to evaluate flour, but not widely used in Sweden. This study aimed to evaluate the machines and see if they could be used to predict baking volume for bread baked on Swedish wheat flour. PLS-models were built with baking volume as the Y-variable. LÄS MER
5. Random projections in a distributed environment for privacy-preserved deep learning
Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)Sammanfattning : The field of Deep Learning (DL) only over the last decade has proven useful for increasingly more complex Machine Learning tasks and data, a notable milestone being generative models achieving facial synthesis indistinguishable from real faces. With the increased complexity in DL architecture and training data, follows a steep increase in time and hardware resources required for the training task. LÄS MER