Abstract

An Anterior Cruciate Ligament (ACL) injury can cause a severe burden, especially for athletes participating in relatively risky sports. This risk raises a growing incentive for designing injury-prevention programs. For this purpose, for example, the analysis of the drop vertical jump test can provide a useful asset for recognizing those who are more likely to sustain knee injuries. Landing Error Score System (LESS) provides an excellent opportunity to predict the level of vulnerability for each individual who participates in the drop jump test process. Knee flexion angle plays a key role within these test scenarios. Multiple research efforts have been conducted on engaging existing technologies such as the Microsoft Kinect sensor and Motion Capture (MoCap) to investigate the connection between the lower limb angle ranges during jump tests and the injury risk associated with them. Even though these technologies provide sufficient capabilities to researchers and clinicians, they need certain levels of knowledge to enable them to utilize these facilities in an effective manner. Moreover, these systems demand special requirements and setup procedures, which make them limiting. Due to recent advances in the area of Deep Learning, numerous powerful pose estimation algorithms have been developed over the last few years. Having access to relatively reliable and accurate 3D body keypoint information can lead to the successful detection and prevention of injury.
The idea of combining temporal convolutions in video sequences with deep Convolutional Neural Networks (CNNs) offers a substantial opportunity to tackle the challenging task of accurate 3D human pose estimation. Utilizing a fast and accurate 2D pose estimation approach has also enabled us to develop a better and real-time solution for the problem of 3D knee flexion angle estimation. Using the Microsoft Kinect sensor as our ground truth, we analyzed the performance of CNN-based 3D human pose estimation and our proposed method based on a CNN-based 2D pose estimation method in everyday settings. The qualitative and quantitative results are convincing to give an incentive to pursue further improvements, especially in the task of lower extremity kinematics estimation. In addition to the performance comparison between Kinect and CNN, we have also verified the high-margin of consistency between two Kinect sensors.