MFFSODNet: Multiscale Feature Fusion Small Object Detection Network for UAV Aerial Images

目标检测 人工智能 航空影像 计算机视觉 比例(比率) 特征(语言学) 计算机科学 航空影像 特征提取 对象(语法) 遥感 图像融合 模式识别(心理学) 传感器融合 融合 图像(数学) 地图学 地理 语言学 哲学
作者
Lingjie Jiang,Baoxi Yuan,Jiawei Du,Boyu Chen,Hanfei Xie,Juan Tian,Ziqi Yuan
出处
期刊:IEEE Transactions on Instrumentation and Measurement [Institute of Electrical and Electronics Engineers]
卷期号:73: 1-14 被引量:112
标识
DOI:10.1109/tim.2024.3381272
摘要

Unmanned aerial vehicle (UAV) aerial image object detection is a valuable and challenging research field. Despite the breakthrough of deep learning-based object detection networks in natural scenes, UAV images often exhibit characteristics such as a high proportion of small objects, dense distribution, and significant variations in object scales, posing great challenges for accurate detection. To address these issues, we propose an innovative multi-scale feature fusion small object detection network (MFFSODNet). First, concerning the high proportion of small objects in UAV images, an additional tiny object prediction head is introduced instead of the large object prediction head. This approach provides a good detection accuracy of small objects and significantly reduces the parameters. Secondly, to enhance the feature extraction capability of the network for fine-grained information from small objects, a multi-scale feature extraction module (MSFEM) is designed, which could extract rich and valuable multi-scale feature information through convolution operation of different scales on multiple branches. Thirdly, to fuse the fine-grained information from shallow feature maps and the semantic information from deep feature maps, a new bidirectional dense feature pyramid network (BDFPN) is proposed. By expanding the feature pyramid network scale and introducing skip connections, BDFPN achieves efficient multi-scale information fusion. Extensive experiments on the VisDrone and UAVDT benchmark datasets demonstrate that MFFSODNet outperforms state-of-the-art object detection methods and further validate the effectiveness and generalization of MFFSODNet on photovoltaic array defect datasets (PVD).
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
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
刚刚
1秒前
吉祥如意完成签到,获得积分10
1秒前
1秒前
乐乐应助wangruize采纳,获得10
1秒前
zh发布了新的文献求助10
2秒前
3秒前
3秒前
wwx发布了新的文献求助10
3秒前
充电宝应助wow采纳,获得10
3秒前
3秒前
3秒前
务实大船发布了新的文献求助10
3秒前
XU徐发布了新的文献求助10
3秒前
Van关闭了Van文献求助
3秒前
4秒前
4秒前
星辰大海应助平常静丹采纳,获得30
4秒前
4秒前
面包小狗发布了新的文献求助10
5秒前
Russell完成签到,获得积分10
6秒前
6秒前
lgc完成签到,获得积分10
6秒前
6秒前
NexusExplorer应助耿晓平采纳,获得30
6秒前
充电宝应助Vater采纳,获得10
7秒前
自觉葵阴完成签到,获得积分10
7秒前
对对对发布了新的文献求助10
7秒前
直率的凉面完成签到,获得积分10
7秒前
7秒前
丘比特应助fuxiaobao采纳,获得10
7秒前
爆米花应助acc采纳,获得10
7秒前
7秒前
8秒前
筱灬发布了新的文献求助10
8秒前
8秒前
子凯发布了新的文献求助10
8秒前
喵喵的鱼完成签到 ,获得积分10
8秒前
幸运发布了新的文献求助10
8秒前
9秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
Handbook of pharmaceutical excipients, Ninth edition 5000
Aerospace Standards Index - 2026 ASIN2026 3000
Digital Twins of Advanced Materials Processing 2000
Polymorphism and polytypism in crystals 1000
Signals, Systems, and Signal Processing 610
Discrete-Time Signals and Systems 610
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 纳米技术 有机化学 物理 生物化学 化学工程 计算机科学 复合材料 内科学 催化作用 光电子学 物理化学 电极 冶金 遗传学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 6039374
求助须知:如何正确求助?哪些是违规求助? 7769039
关于积分的说明 16226209
捐赠科研通 5185346
什么是DOI,文献DOI怎么找? 2774958
邀请新用户注册赠送积分活动 1757774
关于科研通互助平台的介绍 1641908