Calculating distance with an Axis Camera 206

[Chris_Elston]

With any vision system, you could fill in the area of the "square" target that is found with the "edge detection". This way you get a solid square.

Once you have a soild square, now run an "area detection" of the square.

This will get you a size. The bigger the area, the closer you are. The smaller the area, the further away you are.

[Alan Anderson]

Originally Posted by Chris_Elston

The bigger the area, the closer you are. The smaller the area, the further away you are.

A smaller area could also mean you are just farther away from the line perpendicular to the target, even if you are the same distance from the target itself.

Citrus, what algorithm are you using to compute distance?

[MysterE]

Originally Posted by Chris_Elston

This will get you a size. The bigger the area, the closer you are. The smaller the area, the further away you are.

Would it be more accurate to use the ratio of size of the rectangle in comparison to the overall picture (ie. The smaller the rectangle in pixels, the farther away you are moving from it) and then using the length and width of the sides to calculate for angle?

And I'm one of those NEMs (Non-engineering Mentors) so the math escapes me completely here.

[cjlane1138]

Can someone please post the documentation for detecting the squares and tracking them? I can't seem to find the PDF's or tutorials.

Thanks,
Eagle Engineering 1138

[JewishDan18]

Originally Posted by MysterE

Would it be more accurate to use the ratio of size of the rectangle in comparison to the overall picture (ie. The smaller the rectangle in pixels, the farther away you are moving from it) and then using the length and width of the sides to calculate for angle?

And I'm one of those NEMs (Non-engineering Mentors) so the math escapes me completely here.

Basically, yes. Involves a fair amount of trig, but this is how I am doing it, and it works well.

[Citrus]

We are using the height of the target and comparing it to the height of the camera image.

[dellagd]

Originally Posted by JewishDan18

Basically, yes. Involves a fair amount of trig, but this is how I am doing it, and it works well.

Correct me if im wrong, but cant you use a exponential regression for the correlation from height of rectangle to distance away (at least it seems a exponential regression is the right way to go)

[ganchara]

Does OpenCV have a program that will spit out code for you similar to what the NI Vision Assistant program does? It seems like using OpenCV will be easier for my team to implement our rectangle tracking with if it does, as we are having some trouble understanding the code that is spit out by Vision Assistant.

[caseydech]

my team uses the axis camera to identify blobs (yes its the technical term for the... blobs that the camera picks up) And then finds the distance based on the pixel distance between top square and bottom square, angle uses trig and distance from side targets, labview can calculate the rest

[Derschatten]

I have seen a lot of people over look this in past year. Make sure you are converting it to foot and inches or whatever you desire as 1' would be 1.2 as a double.

[JewishDan18]

Originally Posted by dellagd

Correct me if im wrong, but cant you use a exponential regression for the correlation from height of rectangle to distance away (at least it seems a exponential regression is the right way to go)

Sure you can, but you need to get a baseline to start from, which can be found by going through the trig for one image, or going to a field and finding it through measurements there.

Originally Posted by caseydech

my team uses the axis camera to identify blobs (yes its the technical term for the... blobs that the camera picks up) And then finds the distance based on the pixel distance between top square and bottom square, angle uses trig and distance from side targets, labview can calculate the rest

Yeah, this is what I hope to do, since the error is much less than using a single target. But, if one target is not found, you will need to do the math without it, which makes things very interesting (and a whole lot of if-else, unless I find a more elegant way to do it)