A Novel Dataset for Evaluating and Alleviating Domain Shift for Human Detection in Agricultural Fields

TL;DR

This paper introduces a new dataset for human detection in agricultural fields, evaluates domain shift effects on models, and explores annotation strategies to improve detection performance in real-world agricultural robotics applications.

Contribution

The paper presents the OpenDR Humans in Field dataset and analyzes domain shift impacts and annotation strategies for human detection in agricultural environments.

Findings

Good performance with only negative samples if training is carefully managed

Positive samples improve localization accuracy

Dataset is publicly available for research use

Abstract

In this paper we evaluate the impact of domain shift on human detection models trained on well known object detection datasets when deployed on data outside the distribution of the training set, as well as propose methods to alleviate such phenomena based on the available annotations from the target domain. Specifically, we introduce the OpenDR Humans in Field dataset, collected in the context of agricultural robotics applications, using the Robotti platform, allowing for quantitatively measuring the impact of domain shift in such applications. Furthermore, we examine the importance of manual annotation by evaluating three distinct scenarios concerning the training data: a) only negative samples, i.e., no depicted humans, b) only positive samples, i.e., only images which contain humans, and c) both negative and positive samples. Our results indicate that good performance can be achieved even when using only negative samples, if additional consideration is given to the training process. We also find that positive samples increase performance especially in terms of better localization. The dataset is publicly available for download at https://github.com/opendr-eu/datasets.