Weekend Project: Jetson TX1 Cat Spotter

Weekend Project: Jetson TX1 Cat Spotter

Hi, this is Wayne again with a topic “Weekend Project: Jetson TX1 Cat Spotter”.
If you’re a pet owner, you know that if there’s one thing cats love it’s technology; okay, maybe it’s cat owners who love technology either way. Today, we’re going to build a hyper-intelligent cat toy that moves the laser about to play with the cat when they’re around but doesn’t bother you when they’re. Not this project created by Sam Brown is built around the Nvidia Jetson tx1 developer kit based on their popular GPUs. It’S the second generation of their boards, aimed at makers and other developer projects, it’s capable of massive multitasking computation and deep learning, and it’s what enables this project to identify whether a cat is present before activating the laser to jumpstart you into this project.

Weekend Project: Jetson TX1 Cat Spotter

We prepare to complete and solve the Jetson with the cat’s water running from the moment. It turns on NVIDIA jetpack, the software that updates the Jetson only runs on a bun to Linux. So we’ll start by making a flash drive that lets any computer boot up as an Ubuntu computer will download the utility unetbootin that makes this bootable USB stick for us. We’Ll also need the hard drive image that we’re going to clone onto a second flash drive with your boon to boot. Image ready boot into Linux, put the TX one into recovery mode to receive the flash start with a board powered off and connect the TX one to the computer via the micro, USB port powered on and immediately hold down.

The update button then tap the reset button, while continuing to hold the Update button for a few seconds verify that the board is ready to receive the image by typing LS USB into the terminal window on your computer. You should see an Nvidia device. That’S the Jetson mount the other USB Drive with the device image and then flash the TX one board using this command check the link below for links to the image file in full instructions, while the image is being flashed and it’ll take a little while set up The Arduino part of the cat’s Potter start by building the pan tilt armature. Here we’ve used some acrylic, but you can use just about anything here, cardboard sheet metal or you can 3d print your own parts.

All you need to do is have one servo rigidly mounted to your enclosure, a right-angle attached to the servo rotor and then a second servo mounted to the upper right part of the right angle. The laser then attaches to the horn of the second servo connect, the laser and the two servos to the Arduino and then upload. The sketch check the link below to get the sketch with the image installed onto the Jetson board, connect the Arduino via USB and test it out with a fairly Spartan background, such as a white wall, see if it will recognize a cat. If you don’t have a cat handy, you can test using printed photos when the camera sees a cat, the laser will spring to life. Moving about with a number of different gestures. If the cat get bored or wanders off the laser routine will stop install the Jetson board and the Arduino into enclosure and set it up where your cat is likely to play with it, make sure the enclosure gives easy access to the buttons and has an opening For the camera, your cat toy recognizes felines using a neural network and with the Jetson TX one, it can run a new image through that Network in milliseconds, rather than seconds image.

Recognition that runs in fractions of a second opens up new options for robots that need to keep up with the real world and dodge obstacles. Some of the software packages that make cats Potter work could be turned into countless other uses. The tools that make the cat, smarter work are CUDA, cafe and digit, and all are ready to go on your TX one now ready to train new neural networks to learn more about the Jetson TX one and jet pack check out the links in the video description. Now we really want to thank Nvidia for making the tools available to us to build this project thanks for watching and we’ll see you in the next weekend, project .