Proceedings
Authors
| Filter results4 paper(s) found. |
|---|
1. Yolo Strawberry Maturity Classification and Harvest Priority with 3d CameraAccurate harvesting timing is essential to improve crop quality and productivity, and recent advances in agricultural automation have led to the emergence of fruit maturity classification and harvest optimization algorithms for agricultural robots as major technical challenges. This study proposes a pipeline for strawberry object detection, maturity classification, distance estimation, and harvest priority. We train a YOLOv8 detector on an open RGB dataset, and estimate the camera-fruit distance... M. Yang |
2. Unsupervised Anomaly Detection of Tipburn in Leafy Vegetables Using Denoising AutoencoderTipburn, a common physiological disorder in leafy vegetables, presents as marginal necrosis but its fuzzy boundaries make annotation costly and inconsistent. We present a label-free pipeline that combines CIE Lab–based preprocessing with a chroma-only denoising autoencoder (DAE) trained solely on healthy samples for real-time, pixel-level anomaly mapping. Lettuce images were acquired under controlled lighting, segmented in CIE Lab space, and reduced to the a channel and a/b chromatic ratio... M. Yang |
3. Development of 3D Phenotypic Analysis Technology for Precision Monitoring of StrawberriesStrawberries exhibit high overall production volume but low productivity per unit area, primarily due to diseases that occur during cultivation. These yield losses can be mitigated through precision monitoring technologies based on phenotypic analysis. To enhance monitoring accuracy, 3D phenotyping techniques are essential. This study aims to automate such 3D phenotyping by constructing a 3D segmentation model capable of identifying plant organs. Strawberry plants were imaged from all angles using... M. Yang |
4. Development of Light-Normalized Crop Monitoring Framework Using RGB-D Imaging and Spatial Light RegressionTo achieve high-quality, high-yield crop production, non-destructive precision monitoring technologies combined with image-based artificial intelligence are being studied to establish finely controlled cultivation environments tailored to crop growth stages. However, variations in lighting-one of the most critical cultivation factors-can cause significant fluctuations in crop image data, limiting the accuracy of phenotype extraction. This study aims to develop a light-normalized crop monitoring... M. Yang |