Pinned Repositories
agile_flight
Developing and Comparing Vision-based Algorithms for Vision-based Agile Flight
AirSim
Open source simulator for autonomous vehicles built on Unreal Engine / Unity, from Microsoft AI & Research
AvoidBench
AvoidBench
DL-project
flightmare
An Open Flexible Quadrotor Simulator
flightmare_unity
FloorPlanGen
Simple floorplan generator in python.
moderncv
A modern curriculum vitae class for LaTeX
thesis-template
The official SERG LaTeX template for master theses.
tiago_dual_tutorials
JorisVellekoop's Repositories
JorisVellekoop/FloorPlanGen
Simple floorplan generator in python.
JorisVellekoop/AvoidBench
AvoidBench
JorisVellekoop/agile_flight
Developing and Comparing Vision-based Algorithms for Vision-based Agile Flight
JorisVellekoop/AirSim
Open source simulator for autonomous vehicles built on Unreal Engine / Unity, from Microsoft AI & Research
JorisVellekoop/DL-project
JorisVellekoop/flightmare
An Open Flexible Quadrotor Simulator
JorisVellekoop/flightmare_unity
JorisVellekoop/moderncv
A modern curriculum vitae class for LaTeX
JorisVellekoop/thesis-template
The official SERG LaTeX template for master theses.
JorisVellekoop/tiago_dual_tutorials
JorisVellekoop/TUD_ENS_MSc_Thesis_Template
TU Delft Embedded Systems Group MSc Thesis Template
JorisVellekoop/UniPose
We propose UniPose, a unified framework for human pose estimation, based on our “Waterfall” Atrous Spatial Pooling architecture, that achieves state-of-art-results on several pose estimation metrics. Current pose estimation methods utilizing standard CNN architectures heavily rely on statistical postprocessing or predefined anchor poses for joint localization. UniPose incorporates contextual seg- mentation and joint localization to estimate the human pose in a single stage, with high accuracy, without relying on statistical postprocessing methods. The Waterfall module in UniPose leverages the efficiency of progressive filter- ing in the cascade architecture, while maintaining multi- scale fields-of-view comparable to spatial pyramid config- urations. Additionally, our method is extended to UniPose- LSTM for multi-frame processing and achieves state-of-the- art results for temporal pose estimation in Video. Our re- sults on multiple datasets demonstrate that UniPose, with a ResNet backbone and Waterfall module, is a robust and efficient architecture for pose estimation obtaining state-of- the-art results in single person pose detection for both sin- gle images and videos.