The HDIN Dataset: A Real-World Indoor UAV Dataset with Multi-Task Labels for Visual-Based Navigation

Abstract

Supervised learning for Unmanned Aerial Vehicle (UAVs) visual-based navigation raises the need for reliable datasets with multi-task labels (e.g., classification and regression labels). However, current public datasets have limitations: (a) Outdoor datasets have limited generalization capability when being used to train indoor navigation models; (b) The range of multi-task labels, especially for regression tasks, are in different units which require additional transformation. In this paper, we present a Hull Drone Indoor Navigation (HDIN) dataset to improve the generalization capability for indoor visual-based navigation. Data were collected from the onboard sensors of a UAV. The scaling factor labeling method with three label types has been proposed to overcome the data jitters during collection and unidentical units of regression labels simultaneously. An open-source Convolutional Neural Network (i.e., DroNet) was employed as a baseline algorithm to retrain the proposed HDIN dataset, and compared with DroNet’s pretrained results on its original dataset since we have a similar data format and structure to the DroNet dataset. The results show that the labels in our dataset are reliable and consistent with the image samples.

Keywords

• supervised learning
• indoor visual-based navigation
• real-world UAV dataset
• multi-task labels
• convolutional neural network (CNN)
• scaling factor labeling