Click on “Download PDF” for the PDF version or on the title for the HTML version.


If you are not an ASABE member or if your employer has not arranged for access to the full-text, Click here for options.

An Object-Oriented Architecture for Field Data Acquisition, Processing and Information Extraction

Published by the American Society of Agricultural and Biological Engineers, St. Joseph, Michigan www.asabe.org

Citation:  Paper number  033089,  2003 ASAE Annual Meeting . (doi: 10.13031/2013.13855) @2003
Authors:   Dev S. Shrestha, Brian L. Steward, Cory Van Wyngarden
Keywords:   Precision agriculture, machine vision, object-oriented software architecture, image processing, unified modeling language, field sensing

Software architecture was developed to automate site specific field data acquisition, processing, and geo-referenced crop plant parameters extraction. The architecture supported acquisition and processing of different data streams such as digital video for machine vision and digital serial communications of NMEA strings. The number of channels for data import could be easily expanded for multiple video, GPS, and other signal sources. The architecture was objectoriented and each component in the architecture was developed as a separate class. A key component of this architecture was a supervisor class, which communicated and coordinated the operations on all other classes. Based on this framework, early stage corn population estimation (ESCOPE) software was developed which grabs pre-recorded digital video from a vehicle-mounted camera, that was passed over corn rows, and acquires GPS strings which were modulated and recorded on the audio channel. A digital video (DV) capture class was written to acquire video using Microsofts DirectShow technology which enables camera control and video acquisition using higher level hardware functions. After completion of software development, reusability and extensibility characteristics were demonstrated by adding a class to acquire images from the hard drive and also by deriving a new image analyzer class to extract an additional feature. The architecture forms a general framework for developing reusable and extensible software for field data sensing systems.

(Download PDF)    (Export to EndNotes)