convolutional neural network

13 Articles

Training A Self-Driving Kart

December 21, 2024 by 1 Comment

There are certain tasks that humans perform every day that are notoriously difficult for computers to figure out. Identifying objects in pictures, for example, was something that seems fairly straightforward but was only done by computers with any semblance of accuracy in the last few years. Even then, it can’t be done without huge amounts of computing resources. Similarly, driving a car is a surprisingly complex task that even companies promising full self-driving vehicles haven’t been able to deliver despite working on the problem for over a decade now. [Austin] demonstrates this difficulty in his latest project, which adds self-driving capabilities to a small go-kart.

[Austin] had been working on this project at the local park but grew tired of packing up all his gear when he wanted to work on his machine-learning algorithms. So he took all the self-driving equipment off of the first kart and incorporated it into a smaller kart with a very small turning radius so he could develop it in his shop.

He laid down some tape on the floor to create the track and then set up the vehicle to learn how to drive by watching and gathering data. The model is trained with a convolutional neural network and this data. The only inputs that the model gets are images from cameras at the front of the kart. At first, it could only change the steering angle, with [Austin] controlling the throttle to prevent crashes. Eventually, he gave it control of the throttle as well, which behaves well except at the fastest speeds.

There were plenty of challenges along the way, especially when compared to the models trained at the park; [Austin] correctly theorized that the cause of the hardship in the park was a lack of contrast at the boundary between the track and any out-of-bounds areas. With a few tweaks to the track, as well as adding some wide-angle lenses to his cameras, he was able to get a model that works fairly well. Getting started on a project like this doesn’t have as high of a barrier to entry as one might imagine, either. Take a look at this comprehensive open-source Python library for self-driving projects. If you want to start smaller, perhaps don’t start with a self-driving kart.

Continue reading “Training A Self-Driving Kart” →

Dr. Niels Olson uses the Augmented Reality Microscope. (Credit: US Department of Defense)

Google’s Augmented Reality Microscope Might Help Diagnose Cancer

October 1, 2023 by 10 Comments

Despite recent advances in diagnosing cancer, many cases are still diagnosed using biopsies and analyzing thin slices of tissue underneath a microscope. Properly analyzing these tissue sample slides requires highly experienced and skilled pathologists, and remains subject to some level of bias. In 2018 Google announced a convolutional neural network (CNN) based system which they call the Augmented Reality Microscope (ARM), which would use deep learning and augmented reality (AR) to assist a pathologist with the diagnosis of a tissue sample. A 2022 study in the Journal of Pathology Informatics by David Jin and colleagues (CNBC article) details how well this system performs in ongoing tests.

For this particular study, the LYmph Node Assistant (LYNA) model was investigated, which as the name suggests targets detecting cancer metastases within lymph node biopsies. The basic ARM setup is described on the Google Health GitHub page, which contains all of the required software, except for the models which are available on request. The ARM system is fitted around an existing medical-grade microscope, with a camera feeding the CNN model with the input data, and any relevant outputs from the model are overlaid on the image that the pathologist is observing (the AR part).

Although the study authors noted that they saw potential in the technology, as with most CNN-based systems a lot depends on how well the training data set was annotated. When a grouping of tissue including cancerous growth was marked too broadly, this could cause the model to draw an improper conclusion. This makes a lot of sense when one considers that this system essentially plays ‘cat or bread’, except with cancer.

These gotchas with recognizing legitimate cancer cases are why the study authors see it mostly as a useful tool for a pathologist. One of the authors, Dr. Niels Olsen, notes that back when he was stationed at the naval base in Guam, he would have liked to have a system like ARM to provide him as one of the two pathologists on the island with an easy source of a second opinion.

(Heading image: Dr. Niels Olson uses the Augmented Reality Microscope. (Credit: US Department of Defense) )

Teaching A Mini-Tesla To Steer Itself

September 2, 2023 by 4 Comments

At the risk of stating the obvious, even when you’ve got unlimited resources and access to the best engineering minds, self-driving cars are hard. Building a multi-ton guided missile that can handle the chaotic environment of rush-hour traffic without killing someone is a challenge, to say the least. So if you’re looking to get into the autonomous car game, perhaps it’s best to start small.

If [Austin Blake]’s fun-sized Tesla go-kart looks familiar, it’s probably because we covered the Teskart back when he whipped up this little demon of an EV from a Radio Flyer toy. Adding self-driving to the kart is a natural next step, so [Austin] set off on a journey into machine learning to make it happen. Having settled on behavioral cloning, which trains a model to replicate a behavior by showing it examples of the behavior, he built a bolt-on frame to hold a steering servo made from an electric wheelchair motor, some drive electronics, and a webcam attached to a laptop. Ten or so human-piloted laps around a walking path at a park resulted in a 48,000-image training set, along with the steering wheel angle at each point.

The first go-around wasn’t so great, with the Teskart seemingly bent on going off the track. [Austin] retooled by adding two more webcams, to get a little parallax data and hopefully improve the training data. After a bug fix, the improved model really seemed to do the trick, with the Teskart pretty much keeping in its lane around the track, no matter how fast [Austin] pushed it. Check out the video below to see the Teskart in action.

It’s important to note that this isn’t even close to “Full Self-Driving.” The only thing being controlled is the steering angle; [Austin] is controlling the throttle himself and generally acting as the safety driver should the car veer off course, which it tends to do at one particular junction. But it’s a great first step, and we’re looking forward to further development.

Continue reading “Teaching A Mini-Tesla To Steer Itself” →

Insect class-order-family-genus-species chart with drawn examples

Neural Network Identifies Insects, Outperforming Humans

July 16, 2022 by 15 Comments

There are about one million known species of insects – more than for any other group of living organisms. If you need to determine which species an insect belongs to, things get complicated quick. In fact, for distinguishing between certain kinds of species, you might need a well-trained expert in that species, and experts’ time is often better spent on something else. This is where CNNs (convolutional neural networks) come in nowadays, and this paper describes a CNN doing just as well if not better than human experts.

Continue reading “Neural Network Identifies Insects, Outperforming Humans” →

Machine Learning Takes The Embarrassment Out Of Videoconference Wardrobe Malfunctions

June 3, 2020 by 19 Comments

Telecommuters: tired of the constant embarrassment of showing up to video conferences wearing nothing but your underwear? Save the humiliation and all those pesky trips down to HR with Safe Meeting, the new system that uses the power of artificial intelligence to turn off your camera if you forget that casual Friday isn’t supposed to be that casual.

The following infomercial is brought to you by [Nick Bild], who says the whole thing is tongue-in-cheek but we sense a certain degree of “necessity is the mother of invention” here. It’s true that the sudden throng of remote-work newbies certainly increases the chance of videoconference mishaps and the resulting mortification, so whatever the impetus, Safe Meeting seems like a great idea. It uses a Pi cam connected to a Jetson Nano to capture images of you during videoconferences, which are conducted over another camera. The stream is classified by a convolutional neural net (CNN) that determines whether it can see your underwear. If it can, it makes a REST API call to the conferencing app to turn off the camera. The video below shows it in action, and that it douses the camera quickly enough to spare your modesty.

We shudder to think about how [Nick] developed an underwear-specific training set, but we applaud him for doing so and coming up with a neat application for machine learning. He’s been doing some fun work in this space lately, from monitoring where surfaces have been touched to a 6502-based gesture recognition system.

Continue reading “Machine Learning Takes The Embarrassment Out Of Videoconference Wardrobe Malfunctions” →

AI Knows If The Pitch Is On Target Before You Do

December 10, 2019 by 21 Comments

Pitching a baseball is about accuracy and speed. A swift ball on target is the goal, allowing the pitcher to strike out the batter. [Nick Bild] created an AI system that can determine a ball’s trajectory in mid-flight, based on a camera feed.

The system uses an NVIDIA Jetson AGX Xavier, fitted with a USB camera running at 100FPS. A Nerf tennis ball launcher is used to fire a ball towards the batter. Once triggered, the AI uses the camera to capture two successive images of the ball in flight. These images are fed into a convolutional neural network (CNN), and the software determines whether the ball is heading for the strike zone, or moving off-target. It uses this information to light a green or red LED respectively to alert the batter.

While such a system is unlikely to appear in professional baseball anytime soon, it shows the sheer capability of neural network systems to quickly and effectively analyse data in ways simply impossible for mere humans. [Nick]’s future goals involve running the system on faster hardware, and expanding it to determine effects like spin and more accurate positioning within the strike zone.

We’ve seen CNNs do everything from naming tomatoes to finding parking spaces. Video after the break.

Continue reading “AI Knows If The Pitch Is On Target Before You Do” →

Colorizing Images With The Help Of AI

November 18, 2019 by 15 Comments

The world was never black and white – we simply lacked the technology to capture it in full color. Many have experimented with techniques to take black and white images, and colorize them. [Adrian Rosebrock] decided to put an AI on the job, with impressive results.

The method involves training a Convolutional Neural Network (CNN) on a large batch of photos, which have been converted to the Lab colorspace. In this colorspace, images are made up of 3 channels – lightness, a (red-green), and b (blue-yellow). This colorspace is used as it better corresponds to the nature of the human visual system than RGB. The model is then trained such that when given a lightness channel as an input, it can predict the likely a & b channels. These can then be recombined into a colorized image, and converted back to RGB for human consumption.

It’s a technique capable of doing a decent job on a wide variety of material. Things such as grass, countryside, and ocean are particularly well dealt with, however more complicated scenes can suffer from some aberration. Regardless, it’s a useful technique, and far less tedious than manual methods.

CNNs are doing other great things too, from naming tomatoes to helping out with home automation. Video after the break.

Continue reading “Colorizing Images With The Help Of AI” →