tui-nicr Goto Github PK

deep-orientation

Fast and robust upper body orientation estimation for mobile robotic applications

emsaformer

Efficient Multi-task Scene Analysis with Transformers

emsanet

EMSANet: Efficient Multi-Task RGB-D Scene Analysis for Indoor Environments

esanet

ESANet: Efficient RGB-D Semantic Segmentation for Indoor Scene Analysis

gandalf_detector

Gandalf - Generic ANd DistAnce-invariant Laser Features

multi-task-person-perception

Contains the code and weights to our paper "Multi-Task Deep Learning for Depth-based Person Perception in Mobile Robotics" that was published on IROS 2020.

nicr-detectron2

Detectron2-based model implementations used at NICR.

nicr-grasping

Core functionality for grasp estimation such as handling datasets.

nicr-multi-task-dataset

Dataset for patch-based person classification (person vs. non-person objects) and posture classification (standing vs. sitting vs. squatting). The data was recorded using a Kinect2 sensor and consists of labeled depth image patches of 27 persons in various postures and of various non-person objects. In total, the dataset consists of more than 235,000 samples divided into non-overlapping subsets for training, validation, and test.

nicr-multitask-scene-analysis

Provides some core functionalities for multi-task scene analysis in PyTorch.

nicr-rgb-d-orientation-data-set

A data set for upper body orientation estimation of humans with continuous ground truth labels for the angle perpendicular to the ground

nicr-scene-analysis-datasets

Code to prepare and use common datasets for scene analysis tasks

panoptic-mapping

PanopticNDT: Efficient and Robust Panoptic Mapping

rgbd-person-perception

semantic-mapping

Efficient and Robust Semantic Mapping for Indoor Environments