SBIR TOPIC 425 PHASE I: POSTURE ANALYSIS THROUGH MACHINE LEARNING (PATHML)

SBIR 主题 425 第一阶段：通过机器学习进行姿势分析 (PATHML)

• 批准号: 10580661
• 负责人: VADIM KAGAN
• 金额: $ 5.5万
• 依托单位: SENTIMETRIX, INC.
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-09-22 至 2022-06-21
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10580661
• 关键词: Activities of Daily Living; Architecture; Automated Annotation; Behavior; Categories; Clinical Trials; Computer Vision Systems; Computer software; Data; Data Collection; Data Set; Ethnography; Goals; Health; Health behavior; Home; Hour; Human; Human Activities; Image; Individual; Interview; Learning; Location; Machine Learning; Manuals; Methodology; Monitor; Outcome; Participant; Patients; Performance; Phase; Physical activity; Positioning Attribute; Posture; Process; Protocols documentation; Rehabilitation therapy; Research; Research Personnel; Resolution; Resources; Scientist; Small Business Innovation Research Grant; Sports; Structure; Techniques; Technology; Time; Training; Walking; base; convolutional neural network; cost; functional status; human imaging; image processing; insight; interest; memory retention; neural network; open source; programs; prototype; recurrent neural network; transfer learning; walking speed; wearable device

Advances in wearable technology and the availability of low-cost video have tremendous potential to provide new insight into how physical behavior is associated with health, define clinical trial outcomes and assess functional status and activities of daily living patients within their home or a rehabilitation setting. (1-4) Cameras and/or videos can record continuously in a passive and unobtrusive manner, enabling participants to provide a detailed record of daily activity that has applications in health research, memory retention and ethnography. (5-11) However, in health research the use of image processing remains burdensome and cost prohibitive, often requiring manual annotations by trained staff. To automate annotation of images and video in recent years scientists have been using emerging machine learning technology applied to computer vision. With the help of multi-layered special purpose neural networks (Convolutional Neural Networks, Recurrent Neural Networks) researchers have been able to accurately classify still images and video frames based on what is depicted in them, recognize the position of objects of interest in an image, recognize humans in an image, and track objects (vehicles, humans) across multiple consecutive frames of a video. (12-18) To date, this technology has been applied to commercial products and sport performance, but not to quantify levels of physical activity, performance or behavior for health research. The long-term goal of this project is to develop a Commercial Off-The-Shelf (COTS) software program that can accurately classify physical activities (e.g. ’walking’, ‘sitting’ or ‘standing up”), information about behavior (e.g., location and purpose of the activity), and performance (e.g., walking speed and sit to stand transition times).

可穿戴技术的进步和低成本视频的可用性具有巨大的潜力，可以为身体行为如何与健康相关提供新的见解，定义临床试验结果，并评估患者在家中或康复环境中的日常生活功能状态和活动。(1-4)相机和/或视频可以以被动和不显眼的方式连续记录，使参与者能够提供日常活动的详细记录，这些记录在健康研究，记忆保留和人种学中有应用。（5-11）然而，在健康研究中， 仍然是繁重的并且成本过高，通常需要由受过训练的工作人员进行手动注释。为了自动化图像和视频的注释，近年来科学家们一直在使用新兴的机器学习技术应用于计算机视觉。借助多层专用神经网络（卷积神经网络，递归神经网络），研究人员已经 能够根据静态图像和视频帧中所描绘的内容对它们进行准确分类，识别图像中感兴趣对象的位置，识别图像中的人，并在视频的多个连续帧中跟踪对象（车辆，人）。（12-18）迄今为止，这项技术已应用于商业产品和运动性能，但尚未量化 用于健康研究的身体活动、表现或行为水平。该项目的长期目标是开发一种商业现成（COTS）软件程序，该软件程序可以准确地对身体活动（例如，“走路”，“坐着”或“站起来”），行为信息（例如，活动的位置和目的），以及性能（例如，步行速度和从坐到站的过渡时间）。