Redirigiendo al acceso original de articulo en 18 segundos...
Inicio  /  Drones  /  Vol: 6 Par: 5 (2022)  /  Artículo
ARTÍCULO
TITULO

Lightweight Detection Network for Arbitrary-Oriented Vehicles in UAV Imagery via Global Attentive Relation and Multi-Path Fusion

Jiangfan Feng and Chengjie Yi    

Resumen

Recent advances in unmanned aerial vehicles (UAVs) have increased altitude capability in road-traffic monitoring. However, state-of-the-art vehicle detection methods still lack accurate abilities and lightweight structures in the UAV platform due to the background uncertainties, scales, densities, shapes, and directions of objects resulting from the UAV imagery?s shooting angle. We propose a lightweight solution to detect arbitrary-oriented vehicles under uncertain backgrounds, varied resolutions, and illumination conditions. We first present a cross-stage partial bottleneck transformer (CSP BoT) module to exploit the global spatial relationship captured by multi-head self-attention, validating its implication in recessive dependencies. We then propose an angle classification prediction branch in the YOLO head network to detect arbitrarily oriented vehicles in UAV images and employ a circular smooth label (CSL) to reduce the classification loss. We further improve the multi-scale feature maps by combining the prediction head network with the adaptive spatial feature fusion block (ASFF-Head), which adapts the spatial variation of prediction uncertainties. Our method features a compact, lightweight design that automatically recognizes key geometric factors in the UAV images. It demonstrates superior performance under environmental changes while it is also easy to train and highly generalizable. This remarkable learning ability makes the proposed method applicable to geometric structure and uncertainty estimates. Extensive experiments on the UAV vehicle dataset UAV-ROD and remote sensing dataset UACS-AOD demonstrate the superiority and cost-effectiveness of the proposed method, making it practical for urban traffic and public security.

 Artículos similares

       
 
Duc-Minh Ngo, Dominic Lightbody, Andriy Temko, Cuong Pham-Quoc, Ngoc-Thinh Tran, Colin C. Murphy and Emanuel Popovici    
This study proposes a heterogeneous hardware-based framework for network intrusion detection using lightweight artificial neural network models. With the increase in the volume of exchanged data, IoT networks? security has become a crucial issue. Anomaly... ver más
Revista: Future Internet

 
Jiulin Li, Qingquan Li, Qingzhou Mao and Hao Xu    
Steel structures that benefit from having lightweight, ductility, and seismic behaviors are capable of improving the overall performance of civil engineering in environmental protection, project quality, process management, and ease of construction, maki... ver más
Revista: Buildings

 
Wendou Yan, Xiuying Wang and Shoubiao Tan    
This paper proposes the You Only Look Once (YOLO) dependency fusing attention network (DFAN) detection algorithm, improved based on the lightweight network YOLOv4-tiny. It combines the advantages of fast speed of traditional lightweight networks and high... ver más
Revista: Future Internet

 
Liming Zhou, Xiaohan Rao, Yahui Li, Xianyu Zuo, Baojun Qiao and Yinghao Lin    
In recent years, significant progress has been obtained in object detection using Convolutional Neural Networks (CNNs). However, owing to the particularity of Remote Sensing Images (RSIs), common object detection methods are not well suited for RSIs. Aim... ver más

 
Weiwei Zhang, Xin Ma, Yuzhao Zhang, Ming Ji and Chenghui Zhen    
Due to the arbitrariness of the drone?s shooting angle of view and camera movement and the limited computing power of the drone platform, pedestrian detection in the drone scene poses a greater challenge. This paper proposes a new convolutional neural ne... ver más
Revista: Future Internet