|Teaching method||Contact hours|
|Course coordinator(s)||dr. GW Kootstra|
|Lecturer(s)||prof. dr. ir. EJ van Henten|
|PhD R Raja|
|dr. GW Kootstra|
|dr. X Wang|
|Examiner(s)||dr. GW Kootstra|
|prof. dr. ir. EJ van Henten|
Language of instruction:
FTE-32806 Automation for Bioproduction.
In this course, you will learn how to use sensors and process their data in order to measure or detect objects and quantities in the environment. A main part of the course will be dedicated to Machine Vision.
The main activities used in this course are tutorials and practicals. The tutorials are interactive lectures where new theories are presented in small chunks, alternated with programming and pen-and-paper exercises to process the information. In the practicals, you will work on project assignments by combining the previously learned methods into an integrated solution for a given agricultural problem.
Starting with a simple 1D distance sensor, you will explore concepts of measurement error and noise in week 1. You will learn how to deal with them through calibration and signal processing and see how low-pass and high-pass filters can be applied and how time-series can be analysed. In week 2-5, we will focus on 2D imaging sensors – colour cameras – and the processing of digital images, a field know as machine vision. You will learn about cameras, lenses and image acquisition. We will discuss the fundamentals of digital images and you will learn how to use methods for processing of grey-scale and colour images. Methods for image segmentation, image features and object detection will be introduced, and we will look at time-series of images – videos. In week 6, we will move to 3D depth cameras and explore some methods to process 3D point clouds.
After successful completion of this course students are expected to be able to:
- install and calibrate a sensor and acquire data with it;
- explain key theories and methods in signal processing and machine vision;
- apply these methods to real-world agricultural problems using a programming language;
- examine the signal-to-noise ratio of a sensor;
- analyse an agricultural problem and conclude which sensors and processing methods to apply;
- create a perception algorithm to solve an agricultural problem and evaluate its performance.
The final grade will be determined based on the project grade (40%) and the written-exam grade (60%). For both, a minimum grade of 5.5 is required. The project grade is a weighted average over a predefined set of project assignments. These assignments will be graded based on a demonstration and a written report. For the other assignments a simple pass/fail based on a demonstration applies.
To be announced.
|Compulsory for:||BAT||Biosystems Engineering||BSc||6MO|