Good News, Bad news, and More Good News

Moving into fine acquisition, I realized that I had to fix the broken component of Coarse acquisition so that I could reuse a bit of that algorithm in fine acquisition.  As a result, coarse acquisition now happens in around 100ms, with many runs coming in even faster.

The bad news is that as distance from the target surface increases, the attached LEDs that are meant to sterilize any noisy light from the target surface have a weaker effect on the target, to the point where whites are coming in with far more color saturation than MARCO is expecting them.  I could set up auxiliary lights closer to the target, but that leaves a bad taste in my mouth: there will be no auxiliary lights in the field.  

Still, this is just a proof of concept and if I need to set up some closer lights I will.  I am certain there are ways to vastly improve my color recognition database as well using Fourier Transforms and the like to characterize the lighting environment, but if it's not blatantly obvious I am not particularly familiar with image processing as a science.

In summary, as it stands MARCO has a very short range of around 40 cm in bad light.  I've not done extensive testing in good light (lots of sun).

The other good news is that I've realized that I can combine fine and ultimate/ultra acquisition into one process.  In case I've not said so before, the coarse acq. process (which is now complete) locates the colored targets on the target surface by their color.  The fine acq. process zeroes in on the centroid of each individual target to varying degrees of precision.

The ult. acq. process previously would have aimed to determine which target is closest to MARCO (if the target surface is yawed to the left, the right-side targets would be closest).  However the algorithm I have developed for fine acq. already measures this information in some form, so with a little bit of extra work in fine acq., ult. acq can be eliminated completely.

Work on fine acq. is underway and I expect to have a rough draft working in a couple of days, after that it falls to the matrix transformations and vector projections to determine how worthwhile all of this effort was.

Comments

Post a Comment

Popular posts from this blog

The Future of MARCO

So I took some time, got a real job at NASA and I've been out traveling a bit, and I only just recently had some time to settle down and take a good look at this project from a more seasoned perspective.  For reference, when I set out to make this happen, I didn't know python, I had little experience with linux, and "computer vision" was little more than a buzzword to me.  I knew the math worked out, however I had a hard time translating the principles of MARCO from the realm of math where everything is clean and orderly to the real world where colors sometimes don't look like they should and the sun shines more brightly on some days than on others. I was not well-prepared to take on this project, and it's a good thing I started as early as I did because there's no way in hell I would have been able to achieve the fairly-positive results I got with less time. Be that as it may, I'm now in an incrementally better position to tackle this task, and I ...
Keep reading

Preliminary Results and higher-order error sources

Image
I have some test results today, and I'm quite happy with how they turned out.  Quick refresher of the parameters: range refers to the target distance in centimeters, a_ang is the rotation of the major axis of the projected ellipse, and b_ang is a measurement of the target's rotation about the major axis, both in radians. The convention when dealing with rotated ellipses is to measure the angle of rotation of the major axis from +j (beh) clockwise (BEH!) but also, since I went through the trouble of rotating these images so that they're not sideways, a_ang is measured clockwise from -i.  The elliptical fit is programmed to run along the inside edge of the larger target circle. {'range': 42.27010789888579, 'a_ang': -0.04591864992309163, 'b_ang': 0.3644755561635681} Standard up front shot, I'm impressed that the software picked up that the target is actually tilted upwards relative to the camera though I think .36 radians (20 ish degree...
Keep reading

A Working Filter Actuator

It may have taken a week and an unwieldy hardware solution, but I now have an operational filter actuator.  hooray The transistors I tried just simply could not supply enough current in series to the solenoid when biased by the 3.3V digital output of a GPIO pin, so I threw together a servo-operated switch that flicks the filters back and forth pretty reliably.  I've been testing the switch and actuator by setting the scripts that operate them on an infinite loop (see video) and after a couple of solder joint breaks and design revisions the assembly finally seems to be straightened out. In the meantime, I have continued working on the startup scripts. Of course I have scripts operating both lights and the actuator, and I am integrating them all into a sort of pre-mission check to verify functionality.  I have managed to take images using both the IR and visible light filters, and the pictures look good.  All that remains before the real hard part of this project i...
Keep reading