We’re on a sort of vacation in Tanzania at the moment and staying in a modest hotel away from the tourist and government district. It’s a district of small shops selling the same things and guys repairing washing machines out on the sidewalk. The guys repairing washing machines are more than happy to talk. Everybody’s amazingly friendly here, the hotel guy grilled us for an hour about our home state. But I really didn’t expect to end up in a conversation about computer vision.
In search of some yogurt and maybe something cooler to wear, we went on a little walk away from the hotel. With incredible luck we found a robotics shop a few blocks away. Mecktonix is a shop about two meters each way, stuffed full of Arduinos, robots, electronics components, servos, and random computer gear, overseen by [Yohanna “Joe” Harembo]. Nearby is another space with a laser engraver and 3D printer. The tiny space doesn’t stop them from being busy. A constant stream of automotive tech students from the nearby National Institute of Transport shuffle in for advice and parts for class assigned projects.
In between students, Joe demos an autonomous car he’s working on. In classic hacker fashion, he first has to reattach the motor driver board and various sensors, but then he demos the car and its problem – the video frame rate is very slow. We dive in with him and try to get some profiling using time.monotonic_ns()
. He’s never done profiling before, so this is a big eye opener. He’s only processing one video frame every 4.3 seconds, using YOLO on a Pi 3, and yup, that’s the problem. I suggest he change to gamut detection or a Pi 4. Continue reading “The Dar Es Salaam Hacker Scene And Gamut Detection”