ExoNet Database: Wearable Camera Images of Human Locomotion Environments

Citation Author(s):
Brokoslaw
Laschowski
University of Waterloo
William
McNally
University of Waterloo
Alexander
Wong
University of Waterloo
John
McPhee
University of Waterloo
Submitted by:
Brokoslaw Laschowski
Last updated:
Mon, 05/31/2021 - 05:46
DOI:
Links:
License:
0
0 ratings - Please login to submit your rating.

Abstract 

Abstract: Advances in computer vision and deep learning are allowing researchers to develop environment recognition systems for robotic leg prostheses and exoskeletons. However, small-scale and private training datasets have impeded the development and dissemination of image classification algorithms for classifying human walking environments. To address these limitations, we developed ExoNet - the first open-source, large-scale hierarchical database of high-resolution wearable camera images of human locomotion environments. Unparalleled in scale and diversity, ExoNet contains over 5.6 million RGB images of indoor and outdoor real-world walking environments, which were collected using a lightweight wearable camera system during the summer, fall, and winter seasons. Approximately 923,000 images in ExoNet were human-annotated using a 12-class hierarchical labelling architecture. Available publicly through IEEE DataPort, ExoNet offers an unprecedented shared platform to train, develop, and compare next-generation image classification algorithms for human locomotion environment recognition. Besides the control of exoskeletons and prostheses, applications of ExoNet could extend to humanoids and autonomous legged robots.

References:

1) Laschowski B, McNally W, Wong A, and McPhee J. (2020). ExoNet Database: Wearable Camera Images of Human Locomotion Environments. Frontiers in Robotics and AI, 7, 562061. DOI: 10.3389/frobt.2020.562061.

2) Laschowski B, McNally W, Wong A, and McPhee J. (2021). Computer Vision and Deep Learning for Environment-Adaptive Control of Robotic Lower-Limb Exoskeletons. bioRxiv. DOI: 10.1101/2021.04.02.438126. 

Instructions: 

*Details on the ExoNet database are provided in the references above. Please email Brokoslaw Laschowski (blaschow@uwaterloo.ca) for any additional questions and/or technical assistance. 

Comments

I need to access this dataset for academic reasons.

Submitted by Shanshan Lao on Sat, 01/30/2021 - 20:14

I need to access this dataset for academic reasons.

Submitted by Jiangpeng Ni on Mon, 03/15/2021 - 03:44