Jump to main content
Professur Digital- und Schaltungstechnik
Digital Signal Processing and Circuit Technology
Professur Digital- und Schaltungstechnik 

OmniLab


News

Sample images of each action in OmniLab

Sample images of each action in OmniLab

Image 1
brooming
Image 2
cleaning windows
Image 3
down and get up
Image 4
drinking
Image 5
fall on face
Image 6
inchair stand up
Image 7
pull object
Image 8
push object
Image 9
rugpull
Image 10
turn left
Image 11
turn right
Image 12
upbend from knees
Image 13
upbend from waist
Image 14
up from ground
Image 15
walk
Image 16
walk-oldman

Abstract

Please download and sign the dataset release agreement, and send it to Jingrui Yu for access of the dataset. The dataset is for non-commercial usage only.

In order to evaluate the effectiveness of NToP in real-world scenarios, we collect a new dataset OmniLab with a top-view omnidirectional camera, mounted on the ceiling of two different rooms (bedroom, living room) at 2.5 m height. Five actors (3 males, 2 females) perform 15 actions from CMU-MoCap database (brooming, cleaning windows, down and get up, drinking, fall-on-face, in chair and stand up, pull object, push object, rugpull, turn left, turn right, upbend from knees, upbend from waist, up from ground, walk, walk-old-man) in two rooms with varying clothes. The recorded action length is 2.5 s, which results in 60 images for each scene at a frame rate of 24 FPS. The position of the camera is fixed and the resolution of the images is 1200 by 1200 pixels. A total of 4800 frames are collected. All annotations of 17 keypoints conforming to COCO conventions are estimated through a keypoint detector and subsequently refined by four different humans in two loops to ensure high annotation quality. Bottom figure shows a few examples from OmniLab with person bounding boxes and keypoint annotations.

Paper

Code

BibTeX

If you use the data set in your work, please don't forget to cite:

@misc{yu2024ntop,
      title={NToP: NeRF-Powered Large-scale Dataset Generation for 2D and 3D Human Pose Estimation in Top-View Fisheye Images}, 
      author={Jingrui Yu and Dipankar Nandi and Roman Seidel and Gangolf Hirtz},
      year={2024},
      eprint={2402.18196},
      archivePrefix={arXiv},
      primaryClass={cs.CV},
      url={https://arxiv.org/abs/2402.18196}, 
}