qlyoung's wiki
Page Tools
User Tools
    Trace:

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision		Previous revision
bird_bar [2026/02/08 00:44] – [Background] qlyoungbird_bar [2026/02/22 19:24] (current) – [Training] picture size qlyoung
Line 12: Line 12:
  
 At the start of 2021 I received a window-mount bird feeder as a secret santa gift. As a bird lover I was excited to put it up and get a close up view of some of the birds that inhabited the woods around where I lived. Within around 3 days I had birds showing up regularly. At the start of 2021 I received a window-mount bird feeder as a secret santa gift. As a bird lover I was excited to put it up and get a close up view of some of the birds that inhabited the woods around where I lived. Within around 3 days I had birds showing up regularly.
 +
 +With the floor plan of my apartment at the time, the only sensible place to put the feeder was on the kitchen window; there was a screened porch on my bedroom window, or I would have put it there. Since my work desk was in my bedroom, this meant that I couldn't watch it while I worked. If that had been an option, the rest of the project may never have materialized.
  
 Shortly after installing the feeder I had the idea to mount a camera pointing at it and stream it to Twitch, so that I could watch the birds while I was at my computer in another room. While watching I found myself wondering about a few of the species I saw and looking up pictures trying to identify them. Then it hit me - this is a textbook computer vision problem. I could build something that used realtime computer vision to identify birds as they appeared on camera. Shortly after installing the feeder I had the idea to mount a camera pointing at it and stream it to Twitch, so that I could watch the birds while I was at my computer in another room. While watching I found myself wondering about a few of the species I saw and looking up pictures trying to identify them. Then it hit me - this is a textbook computer vision problem. I could build something that used realtime computer vision to identify birds as they appeared on camera.
  
-Fast forward a few years and this has bloomed into a pretty large project. I have gone through three iterations of the project. It's definitely the most popular project I've made; my friends think it's cool.+Fast forward a few years and this has bloomed into a pretty large project, with multiple upgrades to both the hardware, software and feeder setup. It's definitely the most popular project I've made; my friends think it's cool. It's also served as a good test bed to keep up to date on advances in machine learning and accelerated computing.
  
-===== The Feeder =====+===== Feeder =====
  
 This section covers the evolution of the feeder construction & installation details. This section covers the evolution of the feeder construction & installation details.
  
-With the floor plan of my apartment, the only sensible place to put the feeder was on the kitchen window; there’s a screened porch on my bedroom window, or I would have put it there. This meant that I couldn't watch it while I worked since my desk is in another room. If that had been an option, the rest of the project may never have materialized. +==== v1 ====
- +
-Initially the feeder was mounted 'stock'. The camera was an old webcam I had lying around. Since it's mounted outside it needed to be weatherproofed. I did that with plastic wrap. Subsequent attempts greatly improved the design.+
  
-{{birdbar:feeder:feeder-with-camera.jpg?400|Bird feeder showing webcam pointed at it}} {{:feeder-with-camera-outside.jpg?200|Picture of webcam attached to the side of my apartment building}} {{:webcam-condom.jpg?200|Picture of the webcam completely wrapped in plastic wrap secured by orange duct tape sitting on my window sill}}+The first feeder was a generic acrylic bird feeder. The camera was an old webcam I had lying around. Since it's mounted outside it needed to be weatherproofed. I did that with plastic wrap. Subsequent attempts greatly improved the design.
  
-{{ :webcam-tupperware-lid.jpg?200|Picture of a tupperware lid taped over the camera as a sort of primitive rain shield}}+{{birdbar:feeder:feeder-with-camera.jpg?0x300|Bird feeder showing webcam pointed at it}} {{:feeder-with-camera-outside.jpg?0x300|Picture of webcam attached to the side of my apartment building}} {{:webcam-condom.jpg?0x300|Picture of the webcam completely wrapped in plastic wrap secured by orange duct tape sitting on my window sill}} {{:webcam-tupperware-lid.jpg?0x300|Picture of a tupperware lid taped over the camera as a sort of primitive rain shield}}
  
 Additional weatherproofing measures included a plastic tupperware lid taped over the camera as a sort of primitive precipitation shield. Additional weatherproofing measures included a plastic tupperware lid taped over the camera as a sort of primitive precipitation shield.
Line 88: Line 88:
 For the data oriented, here is the summary information for the training run of the model I ended up using: For the data oriented, here is the summary information for the training run of the model I ended up using:
  
-{{:final-training-results.png?400|Composite image with various graphs depicting various training metrics, including recall, precision, loss, and mean average precision on both training and validation sets}} {{:pr-curve.png?400|PR curve}}+{{:final-training-results.png?0x400|Composite image with various graphs depicting various training metrics, including recall, precision, loss, and mean average precision on both training and validation sets}} {{:pr-curve.png?0x400|PR curve}}
  
 These metrics are all good and show that the model trained very nicely on the dataset. These metrics are all good and show that the model trained very nicely on the dataset.
Panorama theme by desbest
bird_bar.1770511457.txt.gz · Last modified: by qlyoung
CC Attribution-Noncommercial-Share Alike 4.0 International Except where otherwise noted, content on this wiki is licensed under the following license: CC Attribution-Noncommercial-Share Alike 4.0 International