WA URISA Conference

Last week I attended the Washington URISA conference for the first time. Overall, I found the conference to be informative and useful and was impressed by the variety of sessions, particularly the volume and quality of open source presentations. I presented with David Howes and Gretchen Peterson on the Lone GIS Professional, a group that David started last year. It was an interesting session, in that about 1/2 the time was allotted to group discussion and David recorded audience input in real-time. The objective of the talk was to spread the word about the Lone GIS Pro group, get more people involved, and perhaps more importantly, find out what would be helpful to Lone GIS people.

It was surprising to me how many attendees of the conference are Lone GISers--either solo practitioners or the only GIS person at their business/agency/non-profit. The need for (and value of) a group like the Lone GIS Pro was reinforced in many of the sessions, based on their heavy emphasis on enterprise GIS systems with massive budgets, staff, and procedural requirements. It really is a differnet world when you're working on your own, and I'm grateful to have such an active, energetic and helpful group to turn to when I have a question or need some backup.

If you are a Lone GIS professional and are interested in joining the group, please email me--the group is invitation-only.

From Images to Data--Image Segmentation

Last year I searched for freely available image segmentation software as an alternative to eCognition. My original search was related to a project that I decided not to pursue; however, this past fall and winter I worked on a project that required image segmentation . So, after doing additional research, I was able to determine that Brazil's National Institute for Space Research (INPE) produced a freeware program called SPRING that does image segmentation. The USFWS worked with INPE to produce an English translation of the software, along with a manual available here. The software itself can be downloaded here.

After working with this software for the better part of a day, I was able to get fairly decent segments out of my imagery, but the classification was not very good. I also found the software difficult and counter-intuitive to use, and although it is ‘translated’ a lot of the menus don’t make much sense.

So I started searching again and found Berkeley Image Segmentation which is great. It is commercial software, but I was able to get the beta release for $900. The creator of the software, James Scarborough, was surprisingly accessible and extremely helpful anytime I had a question about what the software was doing. He has already integrated several of my suggestions into the most recent version, and I’m sure he’ll continue to solicit and incorporate user suggestions. The software is much, much easier to use than SPRING, and it has several classification options built in (K-means, K-nearest neighbor, and neural networks) and while they are better than SPRING they still weren’t quite good enough. James suggests in the ImageSeg manual using WEKA for segmentation classification. This is open-source data mining software, and I used the expectation maximization clustering algorithm with great success, but there are many others available.

I have sample output on the CORE GIS portfolio page, along with a brief description of one of the projects for which I’ve used it (third one from the top).