Abstract:

: In precision agriculture, unmanned aerial vehicles (UAVs) are playing an increasingly important role in farmland information acquisition and fine management. However, discrete obstacles in the farmland environment, such as trees and power lines, pose serious threats to the flight safety of UAVs. Real-time detection of the attributes of obstacles is urgently needed to ensure their flight safety. In the wake of rapid development of deep learning, object detection algorithms based on convolutional neural networks (CNN) and transformer architectures have achieved remarkable results. Detection Transformer (DETR) and Deformable DETR combine CNN and transformer to achieve end-to-end object detection. The goal of this work is to use Deformable DETR for the task of farmland obstacle detection from the perspective of UAVs. However, limited by local receptive fields and local self-attention mechanisms, Deformable DETR lacks the ability to capture long-range dependencies to some extent. Inspired by non-local neural networks, we introduce the global modeling capability to the front-end ResNet to further improve the overall performance of Deformable DETR. We refer to the improved version as Non-local Deformable DETR. We evaluate the performance of Non-local Deformable DETR for farmland obstacle detection through comparative experiments on our proposed dataset. The results show that, compared with the original Deformable DETR network, the mAP value of the Non-local Deformable DETR is increased from 71.3% to 78.0%. Additionally, Non-local Deformable DETR also presents great performance for detecting small and slender objects. We hope this work can provide a solution to the flight safety problems encountered by UAVs in unstructured farmland environments.

Keywords: