We're excited to provide our first update of 2021! First, our mission has not changed: we work every day to make Computer Vision (CV) easy and affordable for all developers. It has been an amazing journey to watch devs use our platform to build and deploy a wide variety of CV apps onto an equally diverse set of IoT devices - new value is created every day on the alwaysAI platform.

Video Streaming with alwaysAI

Open Office Hour

What is Human Pose Estimation?

Raising money and growing a startup during a global pandemic has certainly been a challenging and novel experience. But making real progress during this unprecedented time is somehow more rewarding – there was no playbook, no ‘best practice’ to follow for 2020.

alwaysAI works for developers.  We help you explore the exciting world of Computer Vision (CV); but, more importantly, we help you build and deploy CV apps on the edge - where your business and customers can benefit from the real-time insights that only CV can provide.  

Hacky Hour TriviaThis special holiday hacky hour is a chance for you to test your knowledge about alwaysAI and computer vision! If you missed it, no worries, you can test your knowledge with the Hacky Hour quiz below. The answers are located at the bottom of the blog. For explanations, watch the Hacky Hour Trivia video below. 1. Where is the origin for the Numpy axis 0,0?A. top left corner B. right bottom cornerC. MiddleD. Bottom left corner2. What tool does alwaysAI’s Model Training Toolkit...

What is the Model Training Toolkit?

We are proud to introduce an all new desktop version of the alwaysAI Model Training Toolkit. The new robust interface and simple workflow of the desktop app will allow alwaysAI users of all levels to train their own Computer Vision models. The model training desktop application is the first of a suite of applications that will support your Computer Vision model operations, from data-collection and organization to model deployment and maintenance. The model training module is the backbone of...

This blog post is a follow-up to the Hacky Hour presented on 12/3/2020, Build a Virtual Green Screen with Semantic Segmentation.

What is Semantic Segmentation?

What is Computer Vision?

More often than not, the most difficult part of a task is simply getting started. alwaysAI’s Model Training tool is now integrated with a Jupyter Notebook interface, which not only makes kicking off your Computer Vision project a breeze, but also keeps things simple from end-to-end. The alwaysAI Model Training toolkit - Jupyter Lab interface allows you to upload your dataset, dial in your training configuration, and start training, all in just a few clicks.

What is Balena?

What is the RealSense Depth Camera? 

How an alwaysAI user is using computer vision with IoT to solve logistics problems.

As always, we are proud of our users and what they are accomplishing by using alwaysAI to integrate Computer Vision into their projects. This week we would like to highlight our user Abhijeet Bhatikar who is using alwaysAI as part of his project for the OpenCV Spatial AI Competition. Read on to find out more about how he is combining alwaysAI, computer vision and depth cameras to help solve logistics...

At alwaysAI, we want you to create unique and powerful models that help accomplish your computer vision goals. With the Model Training Toolkit you can create a custom object detection model with little experience and no coding. This video outlines the end-to-end process of doing exactly that - and in a way that is easy to follow. It is meant to be interactive, so you can pause it after each step to take action and then come back. 

Here at alwaysAI, we love to engage with our community of over 10K developers. We have been listening closely to the feedback and are proud to announce the launch of the most requested feature: Model Training.

We recently caught up with one of our talented users, Leonardo Cohen. He is the founder and Managing Partner of Editek. Editek is a consulting company that does IT & Technology projects and Information and Knowledge Management for corporate and sports events. Editek was founded in Portugal in 1993 and moved its operations to the United States in 2003. Editek has an extensive portfolio of projects delivered in more than 10 countries across the creative, corporate, and sports markets.

The...

Recent trends in computation and automation highlight a massive and sustained growth for computer vision based applications on the edge. Market research also points to tremendous interest in these applications amongst entrepreneurs and developers alike. However, developing commercial-grade Computer Vision applications for the edge is hard (link to the new article here). There are two primary reasons for this.

Overcoming Challenges in Bringing CV Applications to Production

Developing a Computer Vision (CV) application and bringing it to production requires  integrating several pieces of hardware and software.

How can we ensure the pieces work seamlessly together? With the right methodologies, we can expedite development and deployment of Computer Vision applications. It is essential to find a platform with the goal of helping developers create computer vision applications from scratch quickly and...

In this tutorial, we will cover how to create an app that will read license plates using the license plate detection model from alwasyAI and the optical recognition software EasyOCR. 

At alwaysAI, we love to engage with our growing developer community and highlight their cool projects. Most recently, two of our users created an alwaysAI Discord bot. This bot, developed by Nathan Wise and Valentine W. allows you to do two main things right from our Discord community:

alwaysAI makes building and deploying Computer Vision Apps Easy

At alwaysAI we have the singular mission of making the process of building and deploying computer vision apps to edge devices as easy as possible. That includes training your model, building your app, and deploying your app to edge devices such as the Raspberry Pi, Jetson Nano, and many others. alwaysAI apps are built in Python and can run natively on Mac and Windows, and in our containerized edge runtime environment optimized...

We're happy to announce the addition of the alwaysAI discord bot developed by Nathan W. and Valentine W. , and implemented by Chris Chu. This bot allows you to do 2 main things right from our Discord community:

We recently connected with an awesome blogger in the computer vision space. We wanted to highlight his blog to our community as he publishes several relevant and interesting articles about Computer Vision and Robotics. It is called the Serious Computer Vision Blog, and is definitely worthwhile checking out.  

In this tutorial, we’ll cover how to create your own license plate tracker using the new license plate detection model, which was created using alwaysAI’s model training tool.

In this tutorial, we’ll walk through the steps and decision points involved in the creation of the ‘alwaysai/vehicle_license_mobilenet_ssd’ model, an object detection model for identifying vehicles and license plates. 

If you haven’t already started thinking about building computer vision into your products, now is the time.

Many of us spend most of our days hunched over a desk, leaning forward looking at a computer screen, or slumped down in our chair. If you’re like me, you’re only reminded of your bad posture when your neck or shoulders hurt hours later, or you have a splitting migraine. Wouldn’t it be great if someone could remind you to sit up straight? The good news is, you can remind yourself! In this tutorial, we’ll build a posture app using a pose estimation model available from alwaysAI.

Separating certain variables from the main application into a configuration file can improve your development time by reducing the need to recompile apps for minor changes. In this tutorial, we’ll cover how to setup a very basic method for leveraging a JSON file for runtime configuration options.

Many models, including those for pose estimation, may have much better performance when run on a GPU rather than a CPU. In this tutorial, we’ll cover how to run pose estimation on the Jetson Nano B01 and cover some nuances of running starter apps on this edge device.

Building and running your app on alwaysAI can be done a few different ways, depending on the platform you want to develop on and the device you want to deploy on. We’ve concentrated these options in one place for your convenience and we’ll update this document as the platform evolves!

This architectural guide walks you through one way of creating an app for monitoring when things (animals, cars, etc) come and go.

alwaysAI’s Co-Founder & CEO, Marty Beard, recently shared in a quarterly report (click here or see video below) key updates around the company’s product, developer, partner and corporate progress - as well as exciting news for the remaining months of 2020.

alwaysAI Product

alwaysAI set out to create a platform for developers to easily and affordably build and deploy computer vision (CV) applications on edge devices. Early this year, alwaysAI came out of beta and officially released a...

Training a computer vision model is one component of a complex and iterative undertaking, which can often seem daunting. At alwaysAI we want to make the process simple and approachable. To get you started, we have compiled a general overview of the training process of Deep Neural Networks (DNNs) for use in computer vision applications. We will focus on supervised learning in this overview, which uses labeled training data to teach the model what the desired output is. This article provides...

hitepaperblog

The Jetson TX2 is part of NVIDIA’s line of embedded AI modules enabling super fast computation on the edge. The TX2 is a leg up compared to the Nano and will give you faster inferencing times in your AI applications. In fact, the Jetson TX2 is the fastest, most power-efficient embedded AI computing device. This 7.5 watt supercomputer on a module brings true AI computing at the edge. 

Please note: This setup guide can only be followed if you have a Linux computer. VM support is un-verified.

This short guide will show you how to combine alwaysAI and Balena to easily deploy a computer vision application to multiple devices with a single command.

The process of developing computer vision applications has been greatly simplified by alwaysAI, which now includes native support for Mac OSX (Mojave and Catalina), and enables developers to get started prototyping applications right away with very little setup required. By the way, you can also learn how to install alwaysAI on Ubuntu and Windows.

Many people are now working or learning from home, introducing the new issue of enforcing professionalism and academic honesty by remote. Whether you are trying to prevent students from cheating on tests, want to double check that your kids aren’t just playing on their phones, or maybe you want to stop yourself from checking social media while you’re supposed to be working, computer vision can help. In this tutorial, I’ll show how you can create your own contraband object alert system using...

As you most likely noticed in the image above, the edges generated by this model are fairly large. In a subsequent tutorial, I’ll cover how to smooth these edges for a less blocky look!

Computer vision (CV) is a huge part of Industry 4.0 and the changing technological landscape as we know it. Computer vision will allow deeper, more impactful insights into businesses in all sectors. Healthcare providers will be able to more quickly and safely diagnose and treat patients. Manufacturing operations will have enhanced security and productivity.

Companies looking for more security while operating virtually, can use computer vision to keep track of their assets, and assure the...

In this guide, we’ll make an app that can count vehicles in real-time utilizing object counting, a technique used in computer vision that combines object detection and object tracking. Our final computer vision application will tell us how many objects of a specific kind are currently being detected in a video stream.

There are many use cases in which it could be beneficial to have automated text messages sent that contain data obtained from computer vision. Perhaps you’d like to be notified whenever a person or animal walks into your yard or house (by using object detection), or when your kids appear to be fighting (by using pose estimation), or any other number of scenarios — the possibilities are endless! In this tutorial, we’ll show you how easy it is to accomplish this task by using a very basic...

Watching the Road Less Traveled

productOps is a boutique software development and consulting firm located in Santa Cruz, California. They serve a broad range of clients across a number of industries, creating custom applications and answering general business challenges.

Christian Piper is a 16-year-old high school student from Pennsylvania, who equipped his First Robotics Competition robot with machine learning sight. He did this with the alwaysAI platform.

If you have a host of images that you’d like to sort based on the presence of particular things (like people, cars, buildings, etc.), using computer vision classifiers can make this a pretty simple and fast thing to accomplish.

During the 2020s, artificial intelligence (AI), robotics and machine learning will transform the marine industry. New developments with autonomous underwater vehicles will require processing huge amounts of data, propelling AI advancements. Seafloor Systems, Inc. is diving right in.

The code for this tutorial is available here: https://github.com/alwaysai/video-streamer

In this article I will demonstrate how to easily modify existing apps offered with alwaysAI to use two object detection models simultaneously, and to display the output in side-by-side frames.