Improved Generalization of Heading Direction Estimation for Aerial Filming Using Semi-supervised Regression

TL;DR

This paper introduces a semi-supervised method for heading direction estimation in aerial filming, improving generalization and reducing labeled data needs by leveraging temporal continuity as an unsupervised signal.

Contribution

The paper presents a novel semi-supervised algorithm that enhances heading direction estimation for aerial filming, effectively utilizing unlabeled data to improve performance and generalization.

Findings

Significant performance improvement with semi-supervised learning.

Reduced need for labeled data in heading estimation.

Robust heading predictions across different actor types.

Abstract

In the task of Autonomous aerial filming of a moving actor (e.g. a person or a vehicle), it is crucial to have a good heading direction estimation for the actor from the visual input. However, the models obtained in other similar tasks, such as pedestrian collision risk analysis and human-robot interaction, are very difficult to generalize to the aerial filming task, because of the difference in data distributions. Towards improving generalization with less amount of labeled data, this paper presents a semi-supervised algorithm for heading direction estimation problem. We utilize temporal continuity as the unsupervised signal to regularize the model and achieve better generalization ability. This semi-supervised algorithm is applied to both training and testing phases, which increases the testing performance by a large margin. We show that by leveraging unlabeled sequences, the amount of labeled data required can be significantly reduced. We also discuss several important details on improving the performance by balancing labeled and unlabeled loss, and making good combinations. Experimental results show that our approach robustly outputs the heading direction for different types of actor. The aesthetic value of the video is also improved in the aerial filming task.