Ansh Trivedi Misses His Parrot Friend — So Built a Raspberry Pi-Powered Bird Tracker to Find It

Product design student Ansh Trivedi was saddened when a parrot friend stopped visiting — and so did the only logical thing: built a Raspberry Pi-powered bird detection system to find it again.

"For a while, a parrot used to visit my window ledge almost every day. It didn’t scream, destroy things, or behave like a typical bird. It would just sit there and watch me work," Trivedi explains. "Quietly. Judgmentally. Like a tiny green supervisor. At some point, it started feeling oddly familiar. Almost intentional. Like some long-lost ancestor checking in to see whether I was actually doing something useful with my life.

"And then one day… it stopped coming. Days passed. Then weeks. The window ledge stayed empty.Which led to the obvious spiral of questions: is it still coming when I’m not around? Has it changed its routine? Or… worst case? Instead of overthinking it forever, I did what any reasonable designer would do. I built a system."

The system in question is designed for continuous observation of the window where the parrot would visit, so that if it was coming out-of-hours and leaving unnoticed Trivedi would know. At the heart of the bird detector is, of course, a low-cost Raspberry Pi single-board computer connected to a USB webcam, which is positioned to film the window ledge on which the bird was usually seen. "The camera watches the ledge continuously," Trivedi explains. "When the system is confident that a bird is present, it saves a frame and logs the time. No notifications. No alarms. No constant monitoring. Just… watching."

The Raspberry Pi is running a simple computer vision model trained to detect birds — which proved challenging, as changes in sunlight and shadow and blown leaves would trigger false positives, while strutting pigeons would have the camera capture hundreds of almost-identical frames needlessly. Once tweaked, the model's findings were massaged into a web interface that includes a live view, count of birds spotted, a list of the most recent captures, and the windows in time that saw the highest bird activity.

"The system worked. Beautifully," Trivedi concludes. "It detected birds reliably. Logged them. Showed patterns. Predicted visit windows. And the result? Only pigeons! So many pigeons uhhh! The parrot never showed up. Which, oddly enough, was still an answer.

"Sometimes, the most important outcome is confirming that something isn't happening (sorry parrot friend). Manifesting my dear parrot friends return. And somewhere out there, the parrot is either watching… or has moved on."

The full project write-up is available on Trivedi's website.