OVERVIEW
The course consists of 3 hands-on modules and a workshop part, where participants can work on their own data and topics.

KEYWORDS
Controlled segmentations cycles, seed Objects; spectral difference, distance calculation, context features using distance; reshaping of Objects; growing techniques

---

CONTENT
Module 1 gives insight into advanced techniques to create dynamic Rule Sets with focus on transferability. An own segmentation is developed and Object growing techniques are explained.

• Classify Seed-Objects for the Class ‘Water’
• Create a buffer of “Candidate” Objects from “Seed” Objects
• Grow initial Objects into the buffer using spectral similarities
• Use measurement techniques and variable thresholds to Increase Rule Set transferability



Module 2 concentrates on working with distances and neighborhoods. An example of a road network is used, a Rule Set to close gaps in this network is developed.

• Identify isolated road Objects using distance features and neighborhood analysis
• Create an condition based automated repetition of a process sequence
• Identify the START and END point of the growing process and set up the growing process



Module 3 focuses on methods for reshaping existing Objects. Condition based Object growing and merging are taught.

• Image Object Fusion condition based merging of Objects
• Grow Objects context based into neighborhood
• Refine Object borders

---

TIME
Rule Set Training   16 - 17 March 2010
Rule Set Training+ 18 March 2010
All days 9.00 am - 5.00 pm

PRICE
1.600,- Euro per seat for 3 days standard training with Definiens instructor

VENUE
Brock & Michelsen A/S
Blokken 76
DK - 3460 Birkerød