StereoPi v2

by StereoPi

The open-source stereoscopic camera based on Raspberry Pi with Wi-Fi, Bluetooth, and an advanced powering system

View all updates Mar 12, 2021

Stereoscopic Vision, Neural Networks, and Laser Beams

by Eugene Pomazov

Sounds like fun, right? Today, we’ll share with you a couple of projects that are using this set of technologies to solve real problems.

Fighting Weeds

Laser weed control

As a human, you can easily distinguish and then neutralize weeds from cultivated plants, like tomatoes. A hardware solution to this problem needs to perform a bunch of complex tasks:

  • Distinguish weeds from tomatoes
  • Determine the exact coordinates of the weeds
  • Precisely aim the laser at the weeds
  • Set the laser power and exposure time to harm the weeds, but not the tomatoes

All these tasks were solved by Ildar Rakhmatulin and Christian Andreasen in their project, A Concept of a Compact and Inexpensive Device for Controlling Weeds with Laser Beams.

Laser weed control setup

The prototype was developed and tested on couch grass (Elytrigia repens (L.) Desv. ex Nevski) mixed with tomatoes. Three types of lasers were used: 0.3 W, 1 W, and 5 W. A neural network was trained to identify the weeds, and a laser guidance system estimates the coordinates of the weeds. The energy required to damage a plant depends on the diameter of the plant, which is related to the plant’s length.

For more details about the hardware and software tricks used in this set up, read the full article (PDF). One of the project authors, Ildar, contacted us with a question for the stereoscopic part of the solution. We hope to see StereoPi v2 in the next version of the device!

Hunting Mosquitoes!

Laser mosquito hunter setup

The title kind of says it all! This small insect is one of humans’ most dangerous enemies. Every year, more than 700,000 human deaths worldwide are attributed to mosquito-borne diseases. So, Ildar had another set of challenges:

  • Detect the mosquito
  • Determine the mosquito's location
  • Aim and fire the laser
  • Check that the mosquito was neutralized
  • Do all the above in a real time

Laser mosquito hunter

Mosquitos are tiny - from 1 to 5 mm. Ultrasonic detection won’t work here. Mosquitos are cold-blooded, so thermal cameras won’t help. Instead, an approach using optical cameras was chosen. A neural network was used to detect the mosquito, and stereoscopic vision was used for 3D localization.

There are a huge number of challenges here - the size and speed of the mosquito, laser tracking system latency, and so on. A lot of these challenges are detailed in this article (direct link to PDF version). To summarize, their system works, albeit under a lot of constraints and with plenty of room for improvement. For example, you might ask how this robotic mosquito safari system ensures that only mosquitos are targeted and other animals, including people, or not harmed. Well, that’s another story, and a great topic for experiments, investigation, and making!


Neural networks and stereoscopic vision are good friends! And, with the StereoPi v2, based on Raspberry Pi Compute Module 4, you can get both at up to 2.5 times faster than on Raspberry Pi 3. For the heavy NN load you can use USB accelerators like Google Coral or Intel Movidus.

What are your plans for neural-network-backed stereoscopic vision? Share your ideas with us in Twitter or in our forum!

About the Author

Eugene Pomazov

StereoPi  ·  Realizator  ·   St. Petersburg

$83,850 raised

of $35,000 goal

239% Funded! Order Below

Product Choices


StereoPi v2 Slim

Perfect for DIY ninjas and those wanting to embed StereoPi in a tight space. This board is the same as the standard edition, but without all the bulky connectors - the Ethernet RJ45 jack, GPIO header, and dual USB Type-A connector have not been populated. To use this board, you will need your own Raspberry Pi Compute Module, cameras, and camera ribbon cables. Two short power cables and three jumpers already included.


StereoPi v2 Standard

The world of stereoscopic video awaits! This board is the ultimate interface between two cameras and a Raspberry Pi Compute Module. It comes with all the bells and whistles, including Ethernet, dual USB ports, GPIO header, microSD slot, HDMI output, and more. To use this board, you will need your own Raspberry Pi Compute Module, cameras, and camera ribbon cables. Two short power cables and three jumpers already included.


StereoPi v2 Camera Kit

Everything you need to assemble your camera! Includes StereoPi Standard, CM4 + external antenna, 2 cameras (IMX219, 160 FOV), a TFT screen, a shot button, camera-mount plates, nuts & bolts, 3 jumpers, a 15 cm tripod, and 2 microSD cards with pre-written SLP and OpenCV images!


StereoPi PoE HAT

This board adds Power over Ethernet option to your StereoPi


StereoPi HQ Metal Housing

Metal housing for a couple of HQ cameras with advanced adjustments features. Includes StereoPi HQ housing base + carriages, 2 x HOYA CM500 filters (8.9 x 8.9 x 1 mm), a set of nuts/bolts/washers for assembly, and a tripod. To use this kit you need a couple of HQ cameras and a couple of C or CS lenses.



We are a small team of geeks who have been making remote-controlled things with livestreaming video since 2010. We've done everything from boats and planes, to robots, copters, and VR helmets. If we can't find the right tools for our projects, we build them ourselves.


Sergey Serov



Full-service Manufacturer

See Also

Subscribe to the Crowd Supply newsletter, highlighting the latest creators and projects: