An Anchor-Free Lightweight Deep Convolutional Network for Vehicle Detection in Aerial Images

目标检测 人工智能 计算机科学 特征提取 航空影像 计算机视觉 对象(语法) 特征(语言学) 卷积神经网络 深度学习 模式识别(心理学) 图像(数学) 语言学 哲学
作者
Jiaquan Shen,Wangcheng Zhou,Ningzhong Liu,Han Sun,Deguang Li,Yongxin Zhang
出处
期刊:IEEE Transactions on Intelligent Transportation Systems [Institute of Electrical and Electronics Engineers]
卷期号:23 (12): 24330-24342 被引量:12
标识
DOI:10.1109/tits.2022.3203715
摘要

Vehicle object detection in aerial scenes has important applications in both military and civilian fields. Recently, deep learning has shown clear advantages in object detection, and the detection performance has been continuously improved. However, these deep object detection algorithms rely on anchor-based approaches accompanied by complex convolutional operations. In this paper, we establish a lightweight aerial vehicle object detection algorithm based on the method of anchor-free. The anchor-free based object detection method effectively gets rid of the limitation of detection model capability by the size of fixed anchor box, which reduces the set of parameters and provides a more flexible solution space. In addition, the proposed lightweight object feature extraction network effectively reduces the computational cost of the model, while improving the feature extraction capability of small objects. Besides, we use channel stacking to improve the object feature extraction capability of the lightweight network, and introduce the attention mechanism in the detection model to improve the efficiency of resource utilization. We evaluate the proposed detection algorithm on both the public aerial dataset and our collected aerial dataset, and the results show that our algorithm has significant advantages over other detection algorithms in detection accuracy and efficiency. The proposed detection algorithm achieves 89.1% and 92.6% mAP on the Munich dataset and the created dataset, and the detection time for each image is 1.21s and 0.036s, respectively.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
PDF的下载单位、IP信息已删除 (2025-6-4)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
Lucas应助sln采纳,获得10
1秒前
取名真烦完成签到,获得积分10
1秒前
1秒前
苏格拉底的嘲笑完成签到,获得积分10
2秒前
2秒前
kx发布了新的文献求助10
3秒前
3秒前
3秒前
氧泡泡发布了新的文献求助10
4秒前
小丸子发布了新的文献求助10
4秒前
Edward完成签到,获得积分10
4秒前
祝我好运完成签到 ,获得积分10
4秒前
5秒前
Yilinna完成签到,获得积分10
5秒前
5秒前
gjm完成签到,获得积分10
5秒前
旅行者完成签到,获得积分10
6秒前
7秒前
dspan发布了新的文献求助10
7秒前
sci_zt发布了新的文献求助10
7秒前
8秒前
8秒前
8秒前
张才豪完成签到,获得积分10
8秒前
111完成签到,获得积分10
8秒前
9秒前
夕颜如玉发布了新的文献求助10
9秒前
赵小熊完成签到,获得积分10
9秒前
9秒前
李佳萌完成签到,获得积分10
9秒前
难过的傲南关注了科研通微信公众号
10秒前
虚幻龙猫完成签到,获得积分10
10秒前
10秒前
李晓萌完成签到 ,获得积分10
10秒前
俊逸易烟发布了新的文献求助10
10秒前
奶茶菌发布了新的文献求助10
10秒前
11秒前
11秒前
刘小雨发布了新的文献求助10
12秒前
山黛Liebe发布了新的文献求助10
12秒前
高分求助中
Picture Books with Same-sex Parented Families: Unintentional Censorship 700
ACSM’s Guidelines for Exercise Testing and Prescription, 12th edition 500
Nucleophilic substitution in azasydnone-modified dinitroanisoles 500
不知道标题是什么 500
Indomethacinのヒトにおける経皮吸収 400
Phylogenetic study of the order Polydesmida (Myriapoda: Diplopoda) 370
Effective Learning and Mental Wellbeing 300
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 遗传学 基因 物理化学 催化作用 冶金 细胞生物学 免疫学
热门帖子
关注 科研通微信公众号,转发送积分 3974712
求助须知:如何正确求助?哪些是违规求助? 3519159
关于积分的说明 11197254
捐赠科研通 3255257
什么是DOI,文献DOI怎么找? 1797724
邀请新用户注册赠送积分活动 877130
科研通“疑难数据库(出版商)”最低求助积分说明 806132