YOLO-RTUAV: Towards Real-Time Vehicle Detection through Aerial Images with Low-Cost Edge Devices

Abstract

Object detection in aerial images has been an active research area thanks to the vast availability of unmanned aerial vehicles (UAVs). Along with the increase of computational power, deep learning algorithms are commonly used for object detection tasks. However, aerial images have large variations, and the object sizes are usually small, rendering lower detection accuracy. Besides, real-time inferencing on low-cost edge devices remains an open-ended question. In this work, we explored the usage of state-of-the-art deep learning object detection on low-cost edge hardware. We propose YOLO-RTUAV, an improved version of YOLOv4-Tiny, as the solution. We benchmarked our proposed models with various state-of-the-art models on the VAID and COWC datasets. Our proposed model can achieve higher mean average precision (mAP) and frames per second (FPS) than other state-of-the-art tiny YOLO models, especially on a low-cost edge device such as the Jetson Nano 2 GB. It was observed that the Jetson Nano 2 GB can achieve up to 12.8 FPS with a model size of only 5.5 MB.

Mutual Guidance Meets Supervised Contrastive Learning: Vehicle Detection in Remote Sensing Images

“…Our YOLOX backbone with CMG strategy outperforms on the VEDAI datasets and on par with YOLO-fine on xView. From qualitative results in Figure 8 and Figure 9, respectively for the VEDAI and xView, it can be seen that although the xView dataset contains extremely small objects, our method, without deliberate operations for tiny object detection, can approach the state-of-the-art method specifically designed for small vehicle detection [29]. A breakdown performance for each class of VEDAI is shown in Table 6.…”

“…In [28,29], YOLOv3 and YOLOv4 were modified and adapted to tackle small vehicle detection from both Unmanned Aerial Vehicle (UAV) and satellite images with the objective of providing a real-time operational context. In the proposed YOLO-fine [28] and YOLO-RTUAV [29] models, the authors attempted to remove unnecessary network layers from the backbones of YOLOv3 and YOLOv4-tiny, respectively, while adding some others to focus on small object searching. In [23], the Tiramisu segmentation model as well as the YOLOv3 detector were experimented and compared for their capacity to detect very small vehicles from 50-cm Pleiades satellite images.…”

YOLO-UAV: Object Detection Method of Unmanned Aerial Vehicle Imagery Based on Efficient Multi-Scale Feature Fusion

“…Koay et al [21] introduced the YOLO-RTUAV model. YOLO-RTUAV builds upon YOLOv4-Tiny and reduces suppression errors using DIoU-NMS, reducing missed detections.…”

ComS-YOLO: a combinational and sparse network for detecting vehicles in aerial thermal infrared images

“…Although vehicle detection techniques in aerial images have been extensively researched, a large proportion of the previous studies have focused on aerial visible images 1 – 3 Unfortunately, visible images are sensitive to lighting conditions, such as darkness, occlusion, and rain, which adversely affects vehicle detection. By contrast, aerial thermal infrared images require a lower illumination intensity.…”