Proceedings
Authors
| Filter results4 paper(s) found. |
|---|
1. Precision Nutrient Management System Based on Ion and Crop Growth SensingAutomated sensing and variable-rate supply of nutrients in hydroponic solutions according to the status of crop growth would allow more efficient nutrient management for crop growth in closed systems. The Structure from Motion (SfM) method has risen as a new image sensing method to obtain 3D images of plants that can be used to estimate their growth, such as leaf cover area (LCA), plant height, and fresh weight. In this sense, sensor fusion technology combining ion-selective electrodes (ISEs)... W. Cho, D. Kim, C. Kang, H. Kim, J. Son, S. Chung, J. Jiang, H. Yun |
2. Open Data for Food Quality and Food Security Control: a Case Study of the Czech RepublicFood quality and food security is of a high public interest in the European Union. In the Czech Republic, food quality and food security is under control of three different public authorities: the Czech Trade Inspection Authority (CTIA) that is affiliated with the Ministry of Industry and Trade of the Czech Republic, the Czech Agriculture and Food Inspection Authority (CAFIA) that is affiliated with the Ministry of Agriculture of the Czech Republic and the regional network of hygienic stations... M. Ulman, M. Stoces, J. Jarolimek, P. Simek |
3. Robotic Arm Tomato Harvesting System and Next Best View Algorithm DevelopmentReplacing human labor with robots is a trend for future agriculture due to its efficiency and consistency. However, in automatic fruit harvesting tasks, leaf occlusion and the dynamic orientation of fruit make it difficult for robots to directly observe the picking point. To address this problem, this research focuses on tomato harvesting, and proposes a next-best-view (NBV) algorithm based on two main structures: “tomato pose prediction” and a “target-hit-gain function”.... P. Yen |
4. Null Dataset-Based Detection Enhances Robotic Vision in Greenhouse Cherry Tomato HarvestingCluttered cherry tomato greenhouse environments with visually similar distractors often trigger False Positives (FPs) in robotic vision, misguiding the robot’s motion and reducing harvesting success. We introduce a null-dataset strategy that integrates unannotated distractor images into YOLOv8l training, with their proportion tuned through loop refinement to suppress FPs while preserving precision. Optimal null proportions were identified as 12.3% for tomato detection and 8.3% for pedicel... P. Yen |