Transformer-Based Person Detection in Paired RGB-T Aerial Images With VTSaR Dataset

人工智能 计算机科学 计算机视觉 RGB颜色模型 变压器 模式识别(心理学) 工程类 电压 电气工程
作者
Xiangqing Zhang,Yan Feng,Nan Wang,Guohua Lü,Shaohui Mei
出处
期刊:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing [Institute of Electrical and Electronics Engineers]
卷期号:18: 5082-5099 被引量:9
标识
DOI:10.1109/jstars.2025.3526995
摘要

Aerial-based person detection poses a significant challenge, yet it is crucial for real-world applications like air-ground linkage search and all-weather intelligent corescuing. However, existing person detection models designed for aerial images heavily rely on numerous labeled instances and exhibit limited tolerance towards complex lighting conditions commonly encountered in search and rescue (SaR) scenarios. This article presents the visible-thermal from SaR scenarios for person detection network (VTSaRNet) to address the challenge of detecting persons situated sparsely in SaR scenes marked by intricate illumination conditions and restricted accessibility. VTSaRNet integrates the instance segmentation for copy–paste mechanism (ISCP) using a Union Transformer Network that functions in both Visible (V) and Thermal (T) bimodalities. Specifically, This study employs synthetic samples obtained through offline Mosaic augmentation by oversampling the local area of bulk images. Then, it utilizes the ISCP module to extract accurate boundaries of personnel instances from complex backgrounds. VTSaRNet cross-integrates the global features and encodes the correlations between two modalities through the multihead attention module. It also adaptively recalibrates the channel responses of partial feature maps for fusion operations with the transformer module in conjunction with anchor-based detectors. Moreover, the adaptation scheme is constructed with multiple strategies to effectively handle various scenarios involving persons, and the entire network is trained end-to-end. Extensive experiments conducted on the Heridal and VTSaR datasets demonstrate the effectiveness of light-weighted VTSaRNet in achieving impressive metrics precision of 98.3%, recall of 96.78%, mAP@0.5 of 98.73%, and mAP@0.5:0.95 of 73.98% under self-built VTSaR dataset, respectively). This performance sets a new benchmark in person detection from aerial imagery.
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
在水一方的应助被蛋卷儿采纳,获得10
1秒前
feng完成签到,获得积分10
1秒前
华清如完成签到,获得积分10
2秒前
Lucy小影完成签到,获得积分10
2秒前
我是老大的应助被美好的易文采纳,获得10
2秒前
星河完成签到,获得积分10
2秒前
风吹麦浪发布了新的文献求助10
2秒前
2秒前
2秒前
jie完成签到,获得积分10
2秒前
3秒前
HuBasya发布了新的文献求助10
3秒前
HH完成签到,获得积分10
3秒前
超越俗尘完成签到,获得积分10
3秒前
3秒前
3秒前
圣斗士完成签到,获得积分10
4秒前
爱听歌的沛凝完成签到,获得积分10
4秒前
yyf完成签到 ,获得积分10
5秒前
泥蝶完成签到 ,获得积分10
6秒前
海盐奶盖完成签到,获得积分20
6秒前
心中的楠楠完成签到 ,获得积分10
6秒前
阔达海雪完成签到,获得积分10
6秒前
侯伯军完成签到,获得积分10
6秒前
听话的八宝粥完成签到 ,获得积分10
7秒前
ARNAMO完成签到,获得积分10
7秒前
姣妹崽完成签到,获得积分10
7秒前
zzzz完成签到,获得积分10
8秒前
赤练仙子发布了新的文献求助10
8秒前
Jack_hao完成签到,获得积分10
8秒前
Kane完成签到,获得积分10
8秒前
8秒前
wjn完成签到,获得积分10
9秒前
等待昊强发布了新的文献求助10
9秒前
爱教育的张月亮完成签到,获得积分10
9秒前
超级冬瓜完成签到,获得积分10
9秒前
xuz发布了新的文献求助10
10秒前
汉堡包的应助被will采纳,获得10
10秒前
周少完成签到,获得积分0
10秒前
aajhajkahna的应助被guan采纳,获得10
10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
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
奈特基础组织学:配套组织病理学(第4版)(Netter's Essential Histology With Correlated Histopathology) 800
John McDowells Bildungstheorie 800
Social Psychology in the Real World 600
八旗制度の研究 600
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8180275
求助须知:如何正确求助?哪些是违规求助? 9570366
关于积分的说明 21810725
捐赠科研通 7776380
什么是DOI,文献DOI怎么找? 3433277
关于科研通互助平台的介绍 2557483
邀请新用户注册赠送积分活动 2479042