A self-supervised spatio-temporal attention network for video-based 3D infant pose estimation

人工智能 姿势 计算机科学 估计 计算机视觉 模式识别(心理学) 机器学习 经济 管理
作者
Wang Yin,Linxi Chen,Xinrui Huang,Chunling Huang,Zhaohong Wang,Yang Bian,You Wan,Yuan Zhou,Tongyan Han,Ming Yi
出处
期刊:Medical Image Analysis [Elsevier BV]
卷期号:96: 103208-103208 被引量:20
标识
DOI:10.1016/j.media.2024.103208
摘要

General movement and pose assessment of infants is crucial for the early detection of cerebral palsy (CP). Nevertheless, most human pose estimation methods, in 2D or 3D, focus on adults due to the lack of large datasets and pose annotations on infants. To solve these problems, here we present a model known as YOLO-infantPose, which has been fine-tuned, for infant pose estimation in 2D. We further propose a self-supervised model called STAPose3D for 3D infant pose estimation based on videos. We employ multi-view video data during the training process as a strategy to address the challenge posed by the absence of 3D pose annotations. STAPose3D combines temporal convolution, temporal attention, and graph attention to jointly learn spatio-temporal features of infant pose. Our methods are summarized into two stages: applying YOLO-infantPose on input videos, followed by lifting these 2D poses along with respective confidences for every joint to 3D. The employment of the best-performing 2D detector in the first stage significantly improves the precision of 3D pose estimation. We reveal that fine-tuned YOLO-infantPose outperforms other models tested on our clinical dataset as well as two public datasets MINI-RGBD and YouTube-Infant dataset. Results from our infant movement video dataset demonstrate that STAPose3D effectively comprehends the spatio-temporal features among different views and significantly improves the performance of 3D infant pose estimation in videos. Finally, we explore the clinical application of our method for general movement assessment (GMA) in a clinical dataset annotated as normal writhing movements or abnormal monotonic movements according to the GMA standards. We show that the 3D pose estimation results produced by our STAPose3D model significantly boost the GMA prediction performance than 2D pose estimation. Our code is available at .
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
W_J_J发布了新的文献求助10
刚刚
1秒前
1秒前
孙士淼完成签到 ,获得积分10
2秒前
molihuakai的应助被刘欣宇采纳,获得10
2秒前
2秒前
2秒前
科研通AI65的应助被萧小五采纳,获得10
2秒前
烟花的应助被科研助理795采纳,获得10
3秒前
丘比特的应助被不想上班采纳,获得10
3秒前
3秒前
xingyueli完成签到,获得积分10
3秒前
TGM_Hedwig完成签到,获得积分10
4秒前
4秒前
脑洞疼的应助被DADA采纳,获得10
4秒前
kinji完成签到,获得积分10
4秒前
蒋博芳发布了新的文献求助10
4秒前
Smile发布了新的文献求助20
6秒前
Luka完成签到,获得积分10
6秒前
Owen的应助被WN采纳,获得10
7秒前
xingyueli发布了新的文献求助10
7秒前
所所的应助被积极的黑猫采纳,获得10
7秒前
啊啊啊啊发布了新的文献求助10
7秒前
任性小凡完成签到,获得积分10
7秒前
8秒前
9秒前
gq100520发布了新的文献求助10
10秒前
永无完成签到,获得积分10
10秒前
墨白发布了新的文献求助10
11秒前
11秒前
11秒前
陶醉若云完成签到,获得积分10
12秒前
13秒前
YAN0221完成签到,获得积分10
13秒前
我是谁的应助被枫丶采纳,获得20
13秒前
13秒前
14秒前
momi发布了新的文献求助10
14秒前
火星上奇迹完成签到,获得积分20
14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 2000
Handbook of Sport Coaching Research 1000
Orthognathic Surgery - 2 Volume Set 500
高分子基功能界面水蒸发材料与应用研究 500
外场增强的水汽发电研究 500
基于结构调控的功能化水诱导发电材料与器件研究 500
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 8193425
求助须知:如何正确求助?哪些是违规求助? 9579620
关于积分的说明 21866505
捐赠科研通 7793025
什么是DOI,文献DOI怎么找? 3437297
关于科研通互助平台的介绍 2560718
邀请新用户注册赠送积分活动 2484128