Computer vision engineer for surfing/surfcams application

ContractFreelancePart-timeProjectRemote SurfConnect

Requirements:

  1. Know Python and OpenCV
  2. Develop computer vision algorithm to automatically evaluate surf conditions
  3. Calculate number of waves that break in subsequent frames
  4. Completed using OpenCV and Python

Project Description

I am implementing computer visions algorithms in my surfCam Startup to create a bunch of stats so surfers can better evaluate the condition.

So far, I have developed an algorithm that calculates the numbers of surfers in the line up. There is done by background subtraction and a Blob algorithm. I want to improve its performance by creating a function that will evaluate if blobs are around the same position from the last 2 calculations. If so, they are real surfers, if not disregards those blobs, they are false positives.

The function will receive a list with the coordinates of each blob as a sublist. For instance: Positions_1 = [[230,182], [554,25], [68,147]]. So in these case, there are 3 blobs. Let’s say, a next frame comes along and the blobs are: Positions_2 = [[230,182], [554,25],[857,45]]. So the official blob list is [[230,182], [554,25]]. And return that list.

The next function is to calculate the number of waves that breaks in 3 different ROIs in a frame. A wave break means there was a color change from dark to white in a certain amount of pixel(around 100 pixels in a X-axis) comparing this frame form 15 frames in the past.

To apply for this position please use the form below.

Anywhere

Upload your CV/resume or any other relevant file. Max. file size: 50 MB.

[mailpoet_form id="1"]

Our instant job notification list lets you know as soon as a new job is published. Don't miss out on a great job because you found out too late! Enter your email address in the form below to receive your instant job notifications.

[mailpoet_form id="1"]

Our instant job notification list lets you know as soon as a new job is published. Don't miss out on a great job because you found out too late! Enter your email address in the form below to receive your instant job notifications.