Friday, March 6, 2009

The Elements of Image Interpretation

There are generally five accepted elements of image interpretation: color, texture, pattern, shape, size, and location. From my readings, it appears that these principals were first documented the 1940s. Makes perfect sense as World War II and the subsequent Cold War resulted in the rapid development of military remote sensing capabilities. Coupled with this increase in capabilities was the need to thoroughly understand what principals should guide a photointerpreter. If remote sensing is considered to be both an art and a science, the trade craft employed by the military photointerpreters during these early days was certainly an art form.
I would like to put forth the argument that the advent of digital image processing techniques caused some sectors of the remote sensing community to focus too much on science of remote sensing, and less on the art form. In short, the trade craft was lost. No where was this more evident than the widespread use of pixel-based classifiers, such as the unsupervised and supervised routines that were commonly employed to extract land cover information from digital imagery.

When one considers the elements of image interpretation, it is clear that techniques that rely solely on the spectral (color) values associated with individual pixels violate the very principals of image interpretation. Perhaps much of this was due to the limitations of the technology at the time. After all, it was not until Definiens introduced their object-oriented software a decade ago that the shift towards object-based image analysis (OBIA) techniques that better replicated the human cognitive process, began. Nevertheless, when examining the literature over the past decades in which pixel-based classifiers where used, rarely do I see a disclaimer along the lines of "these techniques violate the very principals of image interpretation, but they are the best tools we have."

OBIA requires one to understand the elements of image interpretation. Perhaps the "art" is back in remote sensing.

7 comments:

Colin said...

This is probably the classic article on this:
Olson, C. E., Jr. 1960. Elements of photographic interpretation common to several sensors. Photogrammetric Engineering, Vol. 26(4):651-656.

Full disclosure: I happen to work with Dr. Olson and I've read his elements of image interpretation citations from the 1960s & 1970s a few times!

Jarlath O'Neil-Dunne said...

Thanks Colin! A quick search revealed this manual. Olson does a fantastic job in this manual covering both the art and the science.

mentaer said...

actually "OBIA" got changed to "GEOBIA" : GEographic Object-Based Image Analysis.

see: http://wiki.ucalgary.ca/page/GEOBIA for more infos

Jarlath O'Neil-Dunne said...

I would contend that it didn't change, it was simply rebranded as GEOBIA in some circles. The elements of image interpretation, along with the tools and techniques employed in OBIA extend well beyond the geospatial community. OBIA software is used in the medical sciences, for facial pattern recognition, and in the life sciences among others. I find following the OBIA advances in these other fields incredibly valuable to contributing to my understanding of OBIA.

Jarlath O'Neil-Dunne said...

Let me add that whether or not we call it OBIA or GEOBIA I think we will need a new term soon. The increasing using of vector data in OBIA workflows to inform the classification process combined with the fact that object-based analysis of LiDAR point clouds will likely be possible means that we are no longer working with just images. Perhaps GEBOA - geographic object based analysis? Sounds terrible!

Mike Galvin said...
This comment has been removed by the author.
Mike Galvin said...

This was extremely helpful. Fred, using color and texture, always struggled with this and discounted the art of the exercise as he could not valid it statistically; he knew that once he applied it he had a more accurate product but could not bring himself to trust it (!)
Thanks for bringing a wider view of both the elements of image interpretation and the balance between the accuracy of the tool and the skill of the one that wields it.