Real-time conversion of monodepth visual odometry enhanced network
This thesis work belongs to the field of self-supervised monocular depth estimation and constitutes a conversion of the work done in [1]. The purpose is to consider the computationally expensive model in [1] as the baseline model of this work and try to create a lightweight model out of it. The curr...
Main Author: | Myriokefalitakis, Panteleimon |
---|---|
Format: | Others |
Language: | English |
Published: |
KTH, Skolan för elektroteknik och datavetenskap (EECS)
2020
|
Subjects: | |
Online Access: | http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-288488 |
Similar Items
-
LjudMAP: A Visualization Tool for Exploring Audio Collections with Real-Time Concatenative Synthesis Capabilities
by: Hansjons Vegeborn, Victor
Published: (2020) -
Real-time Vision-based Fall Detection : with Motion History Images and Convolutional Neural Networks
by: Haraldsson, Truls
Published: (2018) -
Real-Time Semantic Stereo Matching
by: Dovesi, Pier Luigi
Published: (2020) -
Real-time segmentaion of feet on smartphone
by: Demborg, Axel
Published: (2018) -
Archtecture of distributed real-time systems
by: Wing Leung, Cheuk
Published: (2013)