Search Results (2)

Leaf area index is a key structural parameter for biological and physical processes. Korea is planning to launch CAS500-4 in 2025, so in situ data is needed to validate the leaf area index. Unlike other networks (e.g., NEON and TERN), establishing an elementary sampling unit is difficult in Korea due to the complex forest structure and rugged terrain. Therefore, pixel-level correspondence between the satellite product and fisheye footprints is the best way to verify in complex terrain. In this study, we analyzed the spatial footprint of fisheye lenses in different forest types using terrestrial LiDAR data for the first time. The three-dimensional forest structure was analyzed at various viewing zenith angles, and the footprint radius was approximately 3 m at view zenith angle (VZA) 20° and approximately 10 m at VZA 90°. We also analyzed the Z-values from terrestrial laser data and the plant area index on leafless seasons to assess the impact of obstacles, such as tree trunks, under various viewing zenith angles. The analysis showed that the influence of woody components increases dramatically as the VZA exceeds 40°. Such factors influenced the increase in LAI and the decrease in the clumping index as the VZA increased. Overall, we concluded that narrowing VZA between 20° and 40° is appropriate for Korean forests with complex structures. Full article

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. Full article