Fish counting application

pixelcrash · July 13, 2016, 10:57am

Hello, I client asked me if I could create a fish couting application. They installed a natural fish elevator and would like to measure the efficiency of it. It would be also great if we could figure out the type of fish.

Does anyone have experience with that?
Is a full HD thermal camera enough? or 4k?
Is this actually possible?

Thanks looking forward getting some inputs

taktik · July 13, 2016, 3:41pm

Hello Pixelcrash !

Your project sound funny.

I had a similar job for a sport retail shop that wanted to count the number of visitors, and type them (male/female/young/old). This work was doing with OpenFrameworks and a simple webcam. But it was a one week project, and need a powerful computer.

So different points for your project :

Does your system being really precise or your must have an idea of type of fish ?
Is there a place where all fish must pass ?
Your hardware must be standalone all year long ?

In my opinion, the most difficult part is to create a hardware robust solution. Maybe without computer (but a microcontroller)

HD thermal cam can be a good input. Infrared Led too. Good Luck !

pixelcrash · July 13, 2016, 5:01pm

Hi Taktik,

it is going to be a permanent installation, maybe in Winter we can dismount it, I have to ask that actually.

We should get the following data:

Amount
Size (Length)
Type of fish

The Size can be between 4 cm up to 90 cm.
There is a ramp which is like 2 meters long and 1 meter wide, where all
the fishes have to pass.

I would like to make a concept proposal and ask for state funding to produce a working prototype and afterwards a ready-to-sell product.

I will keep you updated!

pixelcrash · July 13, 2016, 5:10pm

They are pretty much doing what I want

http://www.hizkia.eu/en/passe-a-poissons/logiciels-acquisition-video-aide-comptage/

roymacdonald · July 13, 2016, 11:30pm

Hey,
there are several already implemented method for that, mostly for tracking/counting humans, but it should work for fishes.
this should work quite well out of the box
http://www.tsps.cc/

also check the following. theres a section which describes the human tracking method used.

github.com

openframeworks/ofBook/blob/master/chapters/project_eva/chapter.md

# Choreographies for Humans and Stars 

Permanent interactive outdoor installation developed by [Daily tous les jours](http://dailytouslesjours.com/) for Montreal's planetarium (2014).

Chapter by [Eva Schindling](http://evsc.net) (with help from [Pierre Thirion](http://www.21h42.fr))

!["Choreographies for Humans and Stars" in action at the Montreal's Rio Tinto Alcan Planetarium (January 2014)](images/revolutionsatplane.jpg "Project in action")

## Project Overview

[Choreographies for Humans and Stars](http://www.dailytouslesjours.com/project/choregraphies-pour-des-humains-et-des-etoiles/) is a permanent interactive outdoor installation hosted at Montreal's Rio Tinto Alcan Planetarium. The interactive projection on the building's facade invites passers-by to a series of collective dance performances inspired by the different mechanics of planets and stars.

Seven stones anchored into the ground delimit the dance area in front of the projection. A series of instructions on the screen guide participants through a set of choreographies that combine dance and astronomy. The participants use their bodies to understand celestial dynamics like eclipses, forces of attraction and combustion. A camera system tracks the movements across the dance stage and controls the images and animations on the projection. The original image material has been produced through workshops with local kids.


![The interactive projection invites passers-by to a series of collective dance performances](images/freezeatplane.jpg "Freeze!")


This chapter documents the various stages of *Choreographies for Humans and Stars* in chronological order. It talks about project logistics, prototyping processes and technological choices, before diving into some OF implementation details towards the end.

This file has been truncated. show original

A thermal camera or 4K are completely overkill. I think you will get a more suitable image using IR or even RBG rather than thermal. Computer vision usualy benefits from using lower resolutions, no only because of less data to analyze but because lower res kind of smooths out the image.
There are a lot of industrial cameras for computer vision stuff. very rugged and all proof. Check pointgray cameras https://www.ptgrey.com/

As for identifying the different fish you should implement some kind of computer learning stuff. OpenCV will cover most of your needs. Artificial Neural networks should work well. but you’ll have to train it though, which can be a bit time consuming.
best!

ikillbombs2 · July 18, 2016, 10:03pm

That’s not completely true. A while i’ve worked on a project together with an local university that could detect fish species instead of only counting. It all depends on how large the search space is and how clean the water is.

For that project, the computer had to replace a person, who counted the fish manually.