This paper describes a computer vision based model for object detection that can serve as a preliminary step in fruit prognosis, which involves the estimation of the number, diameter and yield of apple fruits. In order to overcome the recognition unreliability in uncontrolled environments caused by uneven illumination conditions, partly occluded surfaces, and similar background features, we rely on a combination of the objectćs colour, texture and 3D shape properties. In our research, we apply colour segmentation to multiple scene snapshots to separate potential regions from the background andverify them first with texture analysis and second by reconstructing them to 3D space. By analysing all three distinct features (colour, texture and 3D shape) of possible areas, we can safely conclude if they represent fruits we are looking for. Once we detect and verify all areas representing fruits, we can measure their size and model estimated fruit yield.
COBISS.SI-ID: 3078700
The research aims to demonstrate the basic system elements of a prototype automated orchard sprayer, which can deliver pesticide spray selectively withrespect to the characteristics of the targets. The contour of the apple tree canopy was detected by ultra sound sensors Prowave 400EP14D and appropriate electronics. Ultra sound signal was processed by a personal computer and fed in real-time to spraying nozzles which open and close in relation to the canopy structure. The current project focuses on developing the system components for spraying an individual tree. The evaluation was performed in field experiments by detecting deposits on leaves and water sensitive papers (WSP). The demonstrated concept of precise application of pesticide sprays supports a decrease in the amount of delivered spray, thereby reducing both costs and environmental pollution by plant protection products.
COBISS.SI-ID: 3184172
The article focuses on the development of two types of fuzzy and classical PID level control and management able to verify the modeling uncertainties in irrigation. Two-stage strategy is used to create a synthesis of classical and fuzzy logic PID controller with the process of first and second order and disorder carried out (quadratic function). Control was performed with a HP Compaq 6830s PC, the software Matlab / Simulink 2008b, FIS (Fuzzy Logic System) soft logic, input-output unit 500 Dragon Rider and ultrasonic sensors. By using a simulation program Matlab / Simulink / FIS, we simulated the operation of fuzzy logic control and classical at the level of training cycle and the comparison was made between soft and conventional control operation. Fuzzy level control can reduce energy consumption by 25 percent.
COBISS.SI-ID: 3146540