Presentation
A Video-Based Lifting Action Recognition Method Using Rank-Altered Kinematic Feature Pairs
SessionOE3: Tools and Analysis
DescriptionLow-back musculoskeletal disorders (MSDs) are the primary work-related injuries among manual material handling (MMH) workers, who are frequently exposed to repetitive lifting. To prevent low-back MSDs in the workplace, we present a video-based lifting action recognition method using rank-altered kinematic feature pairs, called top-scoring pairs (TSPs). We derive kinematic TSPs from a video dataset containing lifting and other activities commonly seen in MMH. These TSPs collectively classify each frame as lifting and non-lifting. We use the classification results to count the number of lifts performed in videos. The validation process involves evaluating classification performance and comparing the estimated frequencies with the actual count. The proposed method minimizes computational and memory requirements while achieving performance comparable to methods using wearable sensors and/or deep neural networks. This makes it suitable for embedded systems with limited hardware resources, thereby providing extensive feasibility across a variety of MMH environments to improve workplace safety.
Event Type
Lecture
TimeTuesday, September 10th4:55pm - 5:15pm MST
LocationFLW Salon H
Occupational Ergonomics