Video Exposure Assessment of Hand Activity Level

描述（由申请人提供）：本探索性研究调查了使用数字视频处理自动评估美国政府工业卫生学家会议（ACGIH）手部活动水平（HAL）的可行性。我们正在开发特征提取算法，用于使用集中在上肢的传统数字视频实时量化HAL。这项研究是重要的，因为目前还没有一个实用的工具，客观，不显眼，有效地测量重复运动暴露，以评估在工作场所的肌肉骨骼损伤的风险。目前的方法包括使用附在工人手上或手臂上的仪器进行直接测量，或间接观察。仪器和观察方法大多仅限于研究，对行业从业者来说非常不切实际。所提出的方法是创新的，因为它使用数字视频处理来测量重复运动曝光，因为它利用了大量的视频数据库和相关的曝光数据已经通过与加州大学伯克利分校（UCB）的合作手动分析。UCB正在提供四个行业工人的320个视频，以及他们的相关分析。概念验证算法已经过测试。我们首先建议进一步开发和完善视频处理算法，用于从集中在上肢的标准数字视频记录中自动和连续地测量HAL。然后，通过比较重复频率，占空比和HAL，我们的算法从执行节奏重复任务的实验室受试者或实际的工业工人的视频剪辑，对人类分析师进行手动逐帧多媒体视频任务分析获得的类似结果，来评估视频算法。最终，这项转化研究可能会导致一个基于视频的直接阅读接触评估工具，广泛应用于职业健康和安全。

DESCRIPTION (provided by applicant): This exploratory research investigates the feasibility of automatically evaluating the American Conference of Government Industrial Hygienists (ACGIH) Hand Activity Level (HAL) using digital video processing. We are developing feature extraction algorithms for quantifying HAL in real-time using conventional digital videos focused on the upper extremities. This research is significant because there is currently no practical instrument for objectively, unobtrusively, and efficiently measuring repetitive motion exposure for evaluating the risk of musculoskeletal injuries in the workplace. Current methods involve either direct measurements using instruments attached to a worker's hands or arms, or indirect observations. Both instrument and observation methods are mostly limited to research studies and are highly impractical for industry practitioners. The proposed approach is innovative because it uses digital video processing to measure repetitive motion exposure and because it leverages a vast data base of videos and associated exposure data already analyzed manually through collaboration with the University of California-Berkeley (UCB). UCB is making available 320 videos of workers in four industries, and their associated, analyses for this initial study. A proof-of-concept algorithm has already been tested. We first propose to further develop and refine video processing algorithms for automatically and continuously measuring HAL from standard digital video recordings focused on the upper extremities. The video algorithms will then be evaluated by comparing repetition frequency, duty cycle and HAL derived by our algorithm from video clips of laboratory subjects performing paced repetitive tasks or actual industrial workers, against similar outcomes obtained by a human analyst conducting a manual frame-by-frame multimedia video task analysis. Ultimately this translational research might lead to a video-based direct reading exposure assessment instrument with broad applications for occupational health and safety.