Up until now, running any kind of computer vision system on the Raspberry Pi has been rather underwhelming, even with the addition of products such as the Movidius Neural Compute Stick. Looking to improve on the performance situation while still enjoying the benefits of the Raspberry Pi community, [Brandon] and his team have been working on Luxonis DepthAI. The project uses a carrier board to mate a Myriad X VPU and a suite of cameras to the Raspberry Pi Compute Module, and the performance gains so far have been very promising.
So how does it work? Twin grayscale cameras allow the system to perceive depth, or distance, which is used to produce a “heat map”; ideal for tasks such as obstacle avoidance. At the same time, the high-resolution color camera can be used for object detection and tracking. According to [Brandon], bypassing the Pi’s CPU and sending all processed data via USB gives a roughly 5x performance boost, enabling the full potential of the main Intel Myriad X chip to be unleashed.
For detecting standard objects like people or faces, it will be fairly easy to get up and running with software such as OpenVino, which is already quite mature on the Raspberry Pi. We’re curious about how the system will handle custom models, but no doubt [Brandon’s] team will help improve this situation for the future.
The project is very much in an active state of development, which is exactly what we’d expect for an entry into the 2019 Hackaday Prize. Right now the cameras aren’t necessarily ideal, for example the depth sensors are a bit too close together to be very effective, but the team is still fine tuning their hardware selection. Ultimately the goal is to make a device that helps bikers avoid dangerous collisions, and we’ve very interested to watch the project evolve.
The video after the break shows the stereoscopic heat map in action. The hand is displayed as a warm yellow as it’s relatively close compared to the blue background. We’ve covered the combination Raspberry Pi and the Movidius USB stick in the past, but the stereo vision performance improvements Luxonis DepthAI really takes it to another level.
Continue reading “High Performance Stereo Computer Vision For The Raspberry Pi”
Many of the early applications for the much anticipated Oculus Rift VR rig have been in gaming. But it’s interesting to see some more useful applications besides gaming, before it’s commercial release sometime this year. [JoLau] at the Institute i4Ds of FHNW School of Engineering wanted to go a step beyond rendering virtual worlds. So he built the Intuitive Rift Explorer a.k.a IRE. The IRE is a moving reality system consisting of a gimbaled stereo-vision camera rig transmitting video to the Rift, and matching head movements received from the Oculus Rift. The vision platform is mounted on a Remote-controlled robot which is completely wireless.
One of the big challenges with using VR headsets is lag, causing motion sickness in some cases. He had to tackle the problem of latency – reducing the time from moving the head to getting a matching image on the headset – Oculus Rift team specified it should be less than 20ms. The other important requirement is a high frame rate, in this case 60 frames per second. [JoLau] succeeded in overcoming most of the problems, although in conclusion he does mention a couple of enhancements that he would like to add, given more time.
[JoLau] provides a detailed description of the various sub-systems that make up IRE – the Stereo camera, audio and video transmission, media processing, servo driven gimbal for the stereo camera, and control system code. [JoLau]’s reasoning on some of the interesting hardware choices for several components used in the project makes for interesting reading. Watch a video of the IRE in action below.
Continue reading “Putting Oculus Rift On A Robot”
Culture Shock II, a robot by the Lawrence Tech team, first caught our eye due to its unique drive train. Upon further investigation we found a very well built robot with a ton of unique features.
The first thing we noticed about CultureShockII are the giant 36″ wheels. The wheel assemblies are actually unicycles modified to be driven by the geared motors on the bottom. The reason such large wheels were chosen was to keep the center of gravity well below the axle, providing a very self stabilizing robot. The robot also has two casters with a suspension system to act as dampers and stabilizers in the case of shocks and inclines. Pictured Below. Continue reading “Intelligent Ground Vehicle Competition 2010 Day Two Report”