This study proposes practical methods for estimating the moisture content of sludge, represented by the cake moisture, in the filter press dewatering process. Because the cake moisture and filtrate volume are difficult to measure directly, the proposed approaches utilize indirectly measurable data, including drain outlet images and the differential pressure during the compression phase. By analyzing the correlations between these parameters and the cake moisture, estimation models were developed using mathematical approximations. In the image-based approach, image processing techniques were applied to isolate the dewatered region, and the relationship between the pixel count and actual filtrate volume was analyzed to estimate the cake moisture based on the calculated filtrate volume per minute. In the pressure-based approach, two models were proposed: one that directly estimates the cake moisture from the differential pressure, and another that models the relationship among the differential pressure, filtrate volume, and cake moisture. Unlike complex machine learning techniques, the proposed methods employ simple and interpretable mathematical functions, offering both practicality and reliability. Validation using real-world operational data confirmed the accuracy and effectiveness of the proposed approaches.

Accurate and nondestructive monitoring of tomato growth is essential for large-scale greenhouse production; however, it remains challenging for small-fruited cultivars such as cherry tomatoes. Traditional 2D image analysis often fails to capture precise morphological traits, limiting its usefulness in growth modeling and yield estimation. This study proposes an automated phenotyping framework that integrates deep learning-based instance segmentation with high-resolution 3D point cloud reconstruction and ellipsoid fitting to estimate fruit size and ripeness from daily video recordings. These techniques enable accurate camera pose estimation and dense geometric reconstruction (via SfM and MVS), while Nerfacto enhances surface continuity and photorealistic fidelity, resulting in highly precise and visually consistent 3D representations. The reconstructed models are followed by CIELAB color analysis and logistic curve fitting to characterize the growth dynamics. When applied to real greenhouse conditions, the method achieved an average size estimation error of 8.01% compared to manual caliper measurements. During summer, the maximum growth rate (g_max) of size and ripeness were 24.14%, and 95.24% higher than in winter, respectively. Seasonal analysis revealed that winter-grown tomatoes matured approximately 10 days later than summer-grown fruits, highlighting environmental influences on phenological development. By enabling precise, noninvasive tracking of size and ripeness progression, this approach is a novel tool for smart and sustainable agriculture.