Improved Generalization of Heading Direction Estimation for Aerial Filming Using Semi-supervised Regression
This work addresses a domain-specific challenge in aerial filming by improving generalization for moving actors, though it is incremental as it builds on semi-supervised techniques.
The paper tackles the problem of heading direction estimation for autonomous aerial filming by proposing a semi-supervised regression algorithm that leverages temporal continuity to improve generalization with less labeled data, resulting in a significant performance increase in testing and reduced labeled data requirements.
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.