YOLO-Drone:Airborne real-time detection of dense small objects from high-altitude perspective

TL;DR

YOLO-Drone is a real-time UAV object detection algorithm that introduces novel backbone and feature aggregation modules, achieving superior accuracy and speed, especially in night conditions with special lighting.

Contribution

The paper proposes YOLO-Drone with new backbone Darknet59, MSPP-FPN module, and GIoU loss, advancing small object detection in UAV imagery under various lighting conditions.

Findings

Outperforms SOTA methods with 10.13% and 8.59% mAP improvements on UAVDT and VisDrone datasets.

Achieves 53 FPS inference speed, suitable for real-time UAV applications.

High performance under special silicon-based golden LEDs, with up to 87.71% mAP.

Abstract

Unmanned Aerial Vehicles (UAVs), specifically drones equipped with remote sensing object detection technology, have rapidly gained a broad spectrum of applications and emerged as one of the primary research focuses in the field of computer vision. Although UAV remote sensing systems have the ability to detect various objects, small-scale objects can be challenging to detect reliably due to factors such as object size, image degradation, and real-time limitations. To tackle these issues, a real-time object detection algorithm (YOLO-Drone) is proposed and applied to two new UAV platforms as well as a specific light source (silicon-based golden LED). YOLO-Drone presents several novelties: 1) including a new backbone Darknet59; 2) a new complex feature aggregation module MSPP-FPN that incorporated one spatial pyramid pooling and three atrous spatial pyramid pooling modules; 3) and the use of Generalized Intersection over Union (GIoU) as the loss function. To evaluate performance, two benchmark datasets, UAVDT and VisDrone, along with one homemade dataset acquired at night under silicon-based golden LEDs, are utilized. The experimental results show that, in both UAVDT and VisDrone, the proposed YOLO-Drone outperforms state-of-the-art (SOTA) object detection methods by improving the mAP of 10.13% and 8.59%, respectively. With regards to UAVDT, the YOLO-Drone exhibits both high real-time inference speed of 53 FPS and a maximum mAP of 34.04%. Notably, YOLO-Drone achieves high performance under the silicon-based golden LEDs, with a mAP of up to 87.71%, surpassing the performance of YOLO series under ordinary light sources. To conclude, the proposed YOLO-Drone is a highly effective solution for object detection in UAV applications, particularly for night detection tasks where silicon-based golden light LED technology exhibits significant superiority.