CN114533045A - 一种基于红外热传感成像与人体部位分割的儿童身体活动分级的方法 - Google Patents
一种基于红外热传感成像与人体部位分割的儿童身体活动分级的方法 Download PDFInfo
- Publication number
- CN114533045A CN114533045A CN202210159460.3A CN202210159460A CN114533045A CN 114533045 A CN114533045 A CN 114533045A CN 202210159460 A CN202210159460 A CN 202210159460A CN 114533045 A CN114533045 A CN 114533045A
- Authority
- CN
- China
- Prior art keywords
- human body
- body part
- physical activity
- segmentation
- method based
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 25
- 230000037081 physical activity Effects 0.000 title claims abstract description 21
- 230000011218 segmentation Effects 0.000 title claims abstract description 19
- 238000003384 imaging method Methods 0.000 title claims abstract description 8
- 238000010586 diagram Methods 0.000 claims abstract description 4
- 238000001931 thermography Methods 0.000 claims abstract description 4
- 238000011156 evaluation Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 description 12
- 238000013136 deep learning model Methods 0.000 description 4
- 238000003331 infrared imaging Methods 0.000 description 4
- 210000003141 lower extremity Anatomy 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 241000282412 Homo Species 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 229940079593 drug Drugs 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000002503 metabolic effect Effects 0.000 description 1
- 230000000284 resting effect Effects 0.000 description 1
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1126—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb using a particular sensing technique
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/01—Measuring temperature of body parts ; Diagnostic temperature sensing, e.g. for malignant or inflamed tissue
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Physics & Mathematics (AREA)
- Veterinary Medicine (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Public Health (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Physiology (AREA)
- Dentistry (AREA)
- Radiation Pyrometers (AREA)
Abstract
本发明专利提供了一种基于红外热传感成像与人体部位分割的儿童身体活动分级的方法，其特征在于：(1)利用热成像设备获取特定目标对象及周围的热力图；(2)利用人体部位分割算法生成对人体各个部位轮廓的分割；(3)结合上述两者信息，比较各个身体部分相较于儿童平静状态下的热力变化，计算器身体活动强度，并加以分级。
Description
一、技术领域
身体活动分级、人体部位分割、计算机视觉、人工智能
二、背景技术
2.1通用技术方法介绍
人体部位分割技术是计算机视觉物体分割技术的一种特例，其针对人体对象，并将包括头、左右上臂、左右下肢、上下半身等人体的各个部位独立分割出来的一种方法。和物体分割技术一样，人体部位分割技术已广泛采用深度学习模型实现。
2.2相似方法介绍
已有的身体活动强度方法主要基于硬件设备实现。通常这类设备包含了各类传感器，并以6轴加速度计计算不同时刻人体不同部位在三维空间上的加速度与角度转动，从而估计人的身体活动强度。
本申请的方法是一种基于红外热传感成像与人体部位分割的儿童身体活动分级的方法。本申请方法利用红外热传感成像图像并与儿童的人体部位分割结果结合，精准计算基于各个部位的在运动状态下和静止状态下的红外热传感成像图像，在时间刻度上评估身体活动的登记。
三、发明内容
本申请在融合了创新技术和已有方法的基础上，本专利实现了一种基于红外热传感成像与人体部位分割的儿童身体活动分级的方法。
针对某一时刻的儿童身体活动等级，分别获取该儿童静止时刻与当前时刻的热成像图与基于文献[1] 的人体各个部分的分割结果；以文献[1]分割出的结果的像素为一个单位，分别计算各个部位平均像素的热力差异情况，并赋值给当前时刻当前部位所对应的每一个像素。
我们将热力差异图作为深度学习模型ResNet50(见参考文献[2])的输入，并根据文献[3]的标准定义目标对象在不同活动下的代谢当量(MET值)，将MET值小于3的定义为轻强度活动，MET值在3-6之间的定义为中强度活动，MET值大于6的定义为高强度活动，并作为标签，训练基于ResNet50深度学习模型。
热力差异是对身体活动的直接反应。本方法采用每秒取一帧的做法，用以评估当前一秒的活动分级情况。最终，我们将目标对象进行一段完整活动每一秒所得出的活动强度预测结果求平均数，即为目标对象进行该活动的身体活动分级评价结果。
四、附图说明
图1是本申请的方法的架构图，该图仅针对某一时刻的身体活动强度进行评估。
本方法采用红外成像测温仪(例如，菲力尔(FLIR)TG165-X/TG167红外成像测温仪)采集人体的热成像图，同时用文献[1]方法生成身体各个部分的分割结果。接下来分别计算各个部位平均像素的热力差异情况，并赋值给当前时刻当前部位所对应的每一个像素，并作为深度学习模型ResNet50的输入，利用 softmax对身体活动强度进行分级。
五、具体实施方式
本申请通过3个步骤，本专利实现了对人的身体活动强度估计。
步骤一：计算身体各个部分的热力差异情况
采用红外成像测温仪(例如，菲力尔(FLIR)TG165-X/TG167红外成像测温仪)采集人体的热成像图，同时用文献[1]方法生成身体各个部分的分割结果。分别计算各个部位在当前时刻与静止状态下的平均像素的热力差异情况，并赋值给当前时刻当前部位所对应的每一个像素。
步骤二：当前时刻身体活动等级预测
将上一步包含身体各个部分的热力差异情况的热力图作为ResNet50的输入，并利用softmax多分类方法给出当前时刻身体活动等级的预测。
步骤三：完整运动身体活动等级评估
每秒我们仅取一帧进行前2步的预测。我们将目标对象进行一段完整活动每一秒所得出的活动强度预测结果求平均数，即为目标对象进行该活动的身体活动分级评价结果。
参考文献：
[1]Jian Zhao，Jianshu Li，Yu Cheng，Terence Sim，Shuicheng Yan，JiashiFeng：Understanding Humans in Crowded Scenes：Deep Nested Adversarial Learningand A New Benchmark for Multi-Human Parsing. ACM Multimedia 2018：792-800
[2]Kaiming He，Xiangyu Zhang，Shaoqing Ren，Jian Sun：Deep ResidualLearning for Image Recognition. CVPR 2016：770-778
[3]American College of Sports Medicine(ACSM).2006.ACSM’s guidelinesfor exercise testing and preion，7th ed.Philadelphia：Lippincott Williams；Wilkins.
Claims (1)
1.本发明专利提供了一种基于红外热传感成像与人体部位分割的儿童身体活动分级的方法，其特征在于如下步骤：(1)利用热成像设备获取特定目标对象及周围的热力图；(2)利用人体部位分割算法生成对人体各个部位轮廓的分割；(3)结合上述两者信息，比较各个身体部分相较于儿童平静状态下的热力变化，计算器身体活动强度，并给出身体的量化分级评价。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210159460.3A CN114533045A (zh) | 2022-02-21 | 2022-02-21 | 一种基于红外热传感成像与人体部位分割的儿童身体活动分级的方法 |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210159460.3A CN114533045A (zh) | 2022-02-21 | 2022-02-21 | 一种基于红外热传感成像与人体部位分割的儿童身体活动分级的方法 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114533045A true CN114533045A (zh) | 2022-05-27 |
Family
ID=81678211
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210159460.3A Pending CN114533045A (zh) | 2022-02-21 | 2022-02-21 | 一种基于红外热传感成像与人体部位分割的儿童身体活动分级的方法 |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114533045A (zh) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110639191A (zh) * | 2018-06-27 | 2020-01-03 | 北京东方兴企食品工业技术有限公司 | 用于评估机体运动能力的系统及其应用 |
| CN111111111A (zh) * | 2020-01-14 | 2020-05-08 | 广东技术师范大学 | 一种健身实时监测系统及方法 |
| CN112741601A (zh) * | 2019-10-31 | 2021-05-04 | 华为技术有限公司 | 一种评估热身效果的方法及装置 |
| CN113749618A (zh) * | 2021-09-10 | 2021-12-07 | 匠影(上海)智能科技有限公司 | 运动损伤评估方法、系统、介质及终端 |
-
2022
- 2022-02-21 CN CN202210159460.3A patent/CN114533045A/zh active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110639191A (zh) * | 2018-06-27 | 2020-01-03 | 北京东方兴企食品工业技术有限公司 | 用于评估机体运动能力的系统及其应用 |
| CN112741601A (zh) * | 2019-10-31 | 2021-05-04 | 华为技术有限公司 | 一种评估热身效果的方法及装置 |
| CN111111111A (zh) * | 2020-01-14 | 2020-05-08 | 广东技术师范大学 | 一种健身实时监测系统及方法 |
| CN113749618A (zh) * | 2021-09-10 | 2021-12-07 | 匠影(上海)智能科技有限公司 | 运动损伤评估方法、系统、介质及终端 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hesse et al. | Computer vision for medical infant motion analysis: State of the art and rgb-d data set | |
| Rohan et al. | Human pose estimation-based real-time gait analysis using convolutional neural network | |
| Yoo et al. | Automated markerless analysis of human gait motion for recognition and classification | |
| Rabhi et al. | Intelligent control wheelchair using a new visual joystick | |
| US10445930B1 (en) | Markerless motion capture using machine learning and training with biomechanical data | |
| McCay et al. | Establishing pose based features using histograms for the detection of abnormal infant movements | |
| CN111144207B (zh) | 一种基于多模态信息感知的人体检测和跟踪方法 | |
| CN110807364A (zh) | 三维人脸与眼球运动的建模与捕获方法及系统 | |
| Nieto-Hidalgo et al. | Vision based extraction of dynamic gait features focused on feet movement using RGB camera | |
| CN113378649A (zh) | 身份、位置和动作识别方法、系统、电子设备及存储介质 | |
| Bhargavas et al. | Human identification using gait recognition | |
| Rezaee et al. | Modeling abnormal walking of the elderly to predict risk of the falls using Kalman filter and motion estimation approach | |
| Nandy et al. | A new paradigm of human gait analysis with Kinect | |
| CN114533045A (zh) | 一种基于红外热传感成像与人体部位分割的儿童身体活动分级的方法 | |
| US20230040650A1 (en) | Real-time, fine-resolution human intra-gait pattern recognition based on deep learning models | |
| Raja et al. | Design and implementation of facial recognition system for visually impaired using image processing | |
| Taher et al. | An extended eye movement tracker system for an electric wheelchair movement control | |
| CN113361333B (zh) | 一种非接触式骑行运动状态监测方法及其系统 | |
| Wong et al. | Enhanced classification of abnormal gait using BSN and depth | |
| Campomanes-Álvarez et al. | Automatic facial expression recognition for the interaction of individuals with multiple disabilities | |
| Ferlinghetti et al. | Algorithm development for contact identification during wheelchair tennis propulsion using marker-less vision system | |
| Gruendig et al. | 3d head pose estimation with symmetry based illumination model in low resolution video | |
| Posada-Gómez et al. | Development of a motion analysis system and human-machine interaction through digital image processing and virtual reality | |
| Hansen et al. | A data-based parametric biomechanical | |
| Qie et al. | Automatic posture capture of sports movement based on sensor information fusion |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20220527 |