YOLO-Drone:A Scale-Aware Detector for Drone Vision

扫码查看

原文链接

万方数据

外文摘要：Object detection is an important task in drone vision.Since the number of objects and their scales always vary greatly in the drone-captured video,small object-oriented feature becomes the bottleneck of model perform-ance,and most existing object detectors tend to underperform in drone-vision scenes.To solve these problems,we propose a novel detector named YOLO-Drone.In the proposed detector,the backbone of YOLO is firstly replaced with ConvNeXt,which is the state-of-the-art one to extract more discriminative features.Then,a novel scale-aware attention(SAA)module is designed in detection head to solve the large disparity scale problem.A scale-sensitive loss(SSL)is also introduced to put more emphasis on object scale to enhance the discriminative ability of the proposed detector.Experimental results on the latest VisDrone 2022 test-challenge dataset(detection track)show that our detector can achieve average precision(AP)of 39.43％,which is tied with the previous state-of-the-art,meanwhile,reducing 39.8％of the computational cost.

外文关键词：

Drone visionObject detectionScale-aware attentionScale-sensitive lossVisDrone dataset

作者：

Yutong LI、Miao MA、Shichang LIU、Chao YAO、Longjiang GUO

展开 >

作者单位：

School of Computer Science,Shaanxi Normal University,Xi'an 710119,China

Key Laboratory of Modern Teaching Technology,Ministry of Education,Xi'an 710062,China

College of Computer Science,Sichuan University,Chengdu 610065,China

基金：

National Natural Science Foundation of ChinaKey Research and Development Program in Shaanxi ProvinceFunds for the Central Universities

项目编号：

U20012052023-YBGY-2411301032207

出版年：

2024

DOI：

10.23919/cje.2023.00.254

电子学报(英文)

CSTPCDEI

ISSN：1022-4653

年,卷(期)：2024.33(4)