Artlabs Inc.

Overview

Today, with the development of Computer Vision and Deep Learning algorithms it is extremely important to make use of them in your apps. This ensures the best and most up-to-date user experience and gives your customers access to functions, that a few years ago weren’t possible.

ArtLabs team developed a set of algorithms & wrapped everything into iPhone & Android Apps to help tennis players track their progress during tennis matches. We used recent advancements in Computer Vision, such as the Mediapipe library from Google, to make calculations on the client-side as much as it was possible.

Match Tracking

Our app supports both live and prerecorded matches tracking. For that, we used the latest Computer Vision algorithms directly on the client-side to save costs as much as possible, yet paying attention to the performance of the app

During the game, we track the ball, players, and court. For the ball and players tracking we trained custom Machine Learning models and wrapped them into the Google Mediapipe library for the easiest calculation. The court detection algorithm is based on OpenCV and is embedded directly into the app as well.

Player Statistics

Our app is able to accurately track statistics for both players and save them for later use. Once you create a single player in the app, you are able to track his performance through all your games.

During the matches, we track various metrics as well as your selected goals. You can always stay on track with your performance and reach your goals quicker!

Match Statistics

Our app allows all users to track all their matches and set weekly and monthly goals. With the help of our goals this becomes much easier to progress even faster!

During the game, we track such metrics as shots in, average ball speed, first serves in, seconds serves in, and more! With the help of our app, you can feel as comfortable as real athletes during official tournaments!

Overview

Finding leads has been always a pain in the neck, especially for B2B companies. To search for leads they use Linkedin, Email marketing, calls, and more. 

ArtLabs team developed a smart marketplace aiming to connect B2B companies with the new clients on the Ukrainian market. We designed, built, and integrated Machine Learning algorithms for the best user experience possible.

Smart Search with Recommendation AI

The web app has a built-in recommendation engine, that allows giving personalized recommendations to every user based on his/her previous search statistics.

Our recommendation engine works not only on the search page but also below each company profile, recommending similar vendors. This allows maximizing conversion and revenues.

Detailed company profile

We have designed and developed a comprehensive company profile, that can be easily shared with your clients. The company profile contains all the company data and is highly customizable.

We allow not only to change the basic company information, but also the layout of the profile, making each page a unique masterpiece, representing your business how you like it.

Overview

ArtLabs team has developed a solution for item counting on the production line. 

The main problem of the client was the control of the production count. The company tried to use sensors to count the amount of bread on the conveyor, but the result was inaccurate, and had to use manual labor to count.

Object Tracking Algorithm

A computer vision solution has been proposed that counts bread with a single camera. As a result, it comes out quite cheaply, you just need a simple camera and computer.

Having invested in training once, you can get a result of recognizing different types of bakery products. Also, machine learning can be tuned to reduce scrap.

During our research, we tried to come up with a variety of algorithms including YOLO V3, RetinaNet, and others. In the end, we chose the EfficientDet algorithm due to the robust results and high-speed inference.

UI & Dashboards

In the end, we wrapped our software into a simple and user-friendly UI with access to dashboards and product line statistics.

Our system was very simple to use and didn’t require human intervention for product counting. Moreover, it is very easy to fine-tune the existing model on new item sets in the inventory.