ReSCan — Automated Resistor Identification!

resistor id

Need a quick and easy way to sort through a few hundred random resistors? You could do them one at a time by reading the color codes yourself… or you could get a machine to do it for you!

When [Robert] was faced with a pile of unsorted resistors he quickly decided he did not have the patience to sort them manually. So, he started by writing an Android app using OpenCV to detect and identify resistor color codes. The problem is, most phones have trouble focusing at short distances — and since resistors are so small, holding the phone farther back results in color rings only being a few pixels wide — not the greatest for image recognition!

So, he started again on his computer, using a cheap LED-lit webcam instead. He wrote the app in java so he could re-use parts of the code from the Android app. It seems to work pretty well — check it out in the following video! This would be perfect to pair up with your illuminated storage bin hack.

[Read more...]

Using A Computer To Read Braille

braille

[Matthiew] needed to create a system that would allow a computer to read braille. An electromechanical system would be annoying to develop and would require many hardware iterations as the system [Matthew] is developing evolves. Instead, he came up with a much better solution using a webcam and OpenCV that still gets 100% accuracy.

Instead of using a camera to look for raised or lowered pins in this mechanical braille display, [Matthiew] is using OpenCV to detect the shadows. This requires calibrating the camera to the correct angle, or in OpenCV terms, pose.

After looking at the OpenCV tutorials, [Matthiew] found a demo that undistorts an image of a chess board. Using this same technique, he used fiducials from the ARTag project to correctly calibrate an image of his mechanical braille pins.

As for why [Matthiew] went through all the trouble to get a computer to read braille – something that doesn’t make a whole lot of sense if you think about it – he’s building a braille eBook reader, something that just screams awesome mechanical design. We’d be interested in seeing some more info on that project as well.

The Beginning of a DIY Vehicle Night Vision System

night vision car

[Stephen] has just shared with us the current progress of his night vision vehicle system, and it’s looking quite promising!

The idea of the project is to provide the driver with a high contrast image of the road, pedestrians and any other obstacles that may not be immediately visible with headlights. It’s actually becoming a feature on many luxury cars including BMW, Audi, GM and Honda. This is what inspired [Stephen] to try making his own.

The current system consists of an infrared camera, two powerful IR light spot lights, and a dashboard LCD screen to view it. It may be considered “not a hack” by some of our more exuberant readers, but [Stephen] does such a great job explaining his future plans for it, which include object recognition using OpenCV, so we felt it was more than worth a share, even at this point.

You see, the idea of vehicle night vision is not to constantly watch a little screen instead of the road — it’s designed to be there when you need it — and to let you know when you need it, [Stephen's] planning on adding a Raspberry Pi to the mix running OpenCV to detect any anomalies on the road that could be of concern. We shudder at the amount of  training a system like that might need — well, depending on the complexity of this image recognition.

Anyway, stick around after the break to hear [Stephen] explain it himself — it is a long video, but if you want to skip to the action there are clips of it on the road at 1:53 and 26:52.

[Read more...]

2D Room Mapping With a Laser and a Webcam

2014-01-29-21-02-40

[Shane Ormonde] recently learned how to measure distance using just a webcam, a laser, and everyone’s favorite math — trigonometry. Since then he’s thrown the device onto a stepper motor, and now has a clever 2D room mapping machine.

He learned how to create the webcam laser range finder from [Todd Danko], a project we featured 7 years ago! It’s a pretty simple concept. The camera and laser are placed parallel to each other at a known distance, axis-to-axis. On the computer, a python script (using the OpenCV library) searches the image for the brightest point (the laser). The closer the brightest point is to the center of the image, the farther the object. Counting pixels from the center of the image to the laser point allows you to calculate an angle, which can then be used to calculate the distance to the object — of course, this needs to be calibrated to be at all accurate. [Shane] does a great job explaining all of this in one of his past posts, building the webcam laser rangefinder.

From there it was just a matter of slapping the rangefinder onto a stepper motor, driving it with a small PIC, and running the calculations on the fly! His results are fairly impressive.

[Read more...]

S.A.M. The Safety Attention Monitor

Capture

Last term’s project at Chico State University hopes to reduce driver distraction by alerting you when it notices you aren’t paying attention (to the road!).

The team designed SAM using OpenCV to track your face in order to recognize when you aren’t watching the road. It alerts you through a variety of audible beeps and LED lights, and is programmed to only alert you after set time values — i.e. it’s not going to go off when you’re checking your blind spot, unless you’ve been checking it for over a certain length of time. It also has a silence button you can press for situations like looking around while you are parked.

The proof of concept device was built using a Raspberry Pi, the PiCam, and a breadboard to accommodate some manual controls, the buzzer, and LEDs. It also continuously records video of you on a 30 second loop, and in the event of an accident, it saves all the video — perhaps proving it was your fault. Can you imagine if all cars had this installed? On the plus side you wouldn’t have to argue with insurance companies — but if it really was your fault, well then you’re straight out of luck.

Android+Arduino – Face Following RC Car

androidRCcar_01_14

To some of us, hacking an RC Car to simply follow a black line or avoid obstacles is too easy, and we’re sure [Shazin] would agree with that, since he created an RC Car that follows your face!

The first step to this project was to take control of the RC Car, but instead of hijacking the transmitter, [Shazin] decided to control the car directly. This isn’t any high-end RC Car though, so forget about PWM control. Instead, a single IC (RX-2) was found to handle both the RF Receiver and H-Bridges. After a bit of probing, the 4 control lines (forward/back and left/right) were identified and connected to an Arduino.

[Shazin] paired the Arduino with a USB Host Shield and connected it up with his Android phone through the ADB (Android Debug Bridge). He then made some modifications to the OpenCV Android Face Detection app to send commands to the Arduino based on ‘where’ the Face is detected; if the face is in the right half of the screen, turn right, if not, turn left and go forward.

This is a really interesting project with a lot of potential; we’re just hoping [Shazin] doesn’t have any evil plans for this device like strapping it to a Tank Drone that locks on to targets!

[Read more...]

The Face-Tracking Confectionery Cannon!

top500

A team of mechanical and electrical engineering students at Olin College came up with a very fun semester project — a pneumatic powered marshmallow cannon that can track faces, and aim for the mouth!

The device — dubbed the Confectionery Canon — is an impressive mechanical build which required many of Olin College’s manufacturing resources such as the laser cutter, the mill, and the lathe. The majority of the device was made out of acrylic, which was chosen for easy laser cutting, and affordability. Specific aluminum pieces provide strength and were made using mostly scrap found in the shop.

Four servos, a webcam, a solenoid and an Arduino Uno make up the electrical system, which uses Python and OpenCV to track faces (GitHub). A PVC tank is used as the pneumatic reservoir, charged with a safety release valve at 30PSI. To fire the cannon, a sprinkler valve is controlled by a beefy solenoid. It currently only has a magazine capacity of 4 large marshmallows, but the team is planning on upgrading soon.

They have put together a great website with tons of information on the project, and following the break is a fun promo video they made for the project — they even got the VP of  the college to try it!

[Read more...]

Follow

Get every new post delivered to your Inbox.

Join 92,114 other followers