First images

I was going to quit for the day after I got the LiDAR working, then I thought, eh...

So I went ahead and built the polo component of the testing apparatus, rigged it up with IR LEDs in each of the corners and took some pictures.

Dark Tests
Visible
Yep, in a dark room looking through the visible light filter, we see nothing.  This may seem like a pointless image to be taking, but it's actually pretty important to take in context with the next picture.

Infrared

The only difference between the previous image and this one is that the filters are swapped.  The IR LEDs really shine when using the IR-pass filter, pun intended.  You will see the real value of these LEDs in the next series of picutres.
MARCO-Lit Images
Visible
In this image you can clearly see the target surface and its colored targets in each of the four corners.  These pictures are rotated ~90 degrees clockwise because of how the camera is mounted to the array surface.  It's a bit annoying, I know, but these images aren't really meant for human eyes and of course computers couldn't care less.
Infrared
As you can see, it is much, much easier to pick out the corners looking through the IR filter.  Rather than having to pick out colors against the background you just have a simple black field with white dots where the corners are.  Additionally, you can see that even just the bright IR filaments are notably easier to distinguish from the rest of the IR bloom, allowing for pixel-precise acquisition.  Of course, the disadvantage of using the IR lights is that the corners are indistinguishable from each other.  In other words, if I were to roll the polo surface some multiple of 90 degrees, this image would look exactly the same and you would not know which corner is which.

Ambient-Lit Images
Visible
Under the noisy light of multiple incandescent bulbs, the colors on the polo surface look a bit washed out compared to the cleaner LED white light on MARCO.  This highlights the importance of the machine-learning color recognition module I have planned for later in the project.
You can see that even when significant IR noise is introduced, the LEDs are still very easily distinguishable in the field of view.  In fact, the only real challenge to their brightness is the ceiling fan light reflected at us from the top of the mirror.  Hopefully you can see how the IR LEDs can play a valuable role in the process of finding the target surface in the camera's field of view.  After seeing these images, I am tempted to stick some IR reflectors on an unpowered polo surface and integrate an IR spotlight on MARCO so that we can use the IR filter for early targeting even in unpowered scenarios.

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