In the wake of COVID-19, the digital fitness market combining health equipment and ICT technologies is experiencing unexpected high growth. A smart trampoline fitness system is a new representative home exercise equipment for muscle strengthening and rehabilitation exercises. Recognizing the motions of the user and evaluating user activity is critical for implementing its self-guided exercising system. This study aimed to estimate the three-dimensional positions of the user’s foot using deep learning-based image processing algorithms for footprint shadow images acquired from the system. The proposed system comprises a jumping fitness trampoline; an upward-looking camera with a wide-angle and fish-eye lens; and an embedded board to process deep learning algorithms. Compared with our previous approach, which suffered from a geometric calibration process, a camera calibration method for highly distorted images, and algorithmic sensitivity to environmental changes such as illumination conditions, the proposed deep learning algorithm utilizes end-to-end learning without calibration. The network is configured with a modified Fast-RCNN based on ResNet-50, where the region proposal network is modified to process location regression different from box regression. To verify the effectiveness and accuracy of the proposed algorithm, a series of experiments are performed using a prototype system with a robotic manipulator to handle a foot mockup. The three root mean square errors corresponding to X, Y, and Z directions were revealed to be 8.32, 15.14, and 4.05 mm, respectively. Thus, the system can be utilized for motion recognition and performance evaluation of jumping exercises.

To evaluate the dynamic characteristics at all positions of the main spindle of a machine tool, an experimental point was selected using a full factorial design, and a vibration test was conducted. Based on the measurement position, the resonant frequency was distributed from approximately 236 to 242 Hz. The approximation model was evaluated based on its resonant frequencies and dynamic stiffness using regression and interpolation methods. The accuracy of the resonant frequency demonstrated by the kriging method was approximately 89%, whereas the highest accuracy of the dynamic stiffness demonstrated by the polynomial regression method was 81%. To further verify the approximation model, its dynamic characteristics were measured and verified at additional experimental points. The maximum errors yielded by the model, in terms of the resonant frequency and dynamic stiffness, were 1.6% and 7.1%, respectively.