Eye-AI.tech: Smart Artificial Intelligence Solutions for Indoor Analytics
That Artificial Intelligence is a thrilling tech development is not news. However, its various applications definitely are! Eye-AI.tech is a one such brilliant tech startup that harnesses the power of Artificial Intelligence for indoor analytics. With this nifty Artificial Intelligence solution, store owners can get an understanding of their visitors, their behaviors and preferences.
We spoke with Max Ved of Eye-AI.tech to understand what was the inspiration behind starting this brilliant Artificial Intelligence based startup and how they are planning to make the most of Web Summit 2018. Read on!
What inspired you to start Eye-ai.tech? Tell us the story.
The idea came to us when we were doing a face recognition research on video sequences. “Why can’t we merely extract the location of the object based on video records?” we asked ourselves.
The core idea was to build the heat maps of the selected apartment based on its internal cameras. Those heat maps represent the information about the frequency of human presence in a given room. Using this novel facility, one could deduce where the majority of customers are situated or what products attract them.
How does Eye-ai.tech work? Give us an overview.
We process videos from cameras and render stats in a 2D top-down view. We need at least two cameras with an overlapping field of view, yet we plan to experimentally enable a single-camera operation mode in 2019. To implement our tracking/analysis system we will define the pipeline at first.
Generally, our process consists of three pieces: the first one detects the required type of objects from the raw image, the second one is referred to the algorithm itself and resulting frame preprocessing, and the last one is all about various types of visualization (heat map as a pivoting feature).
What are your future plans for Eye-ai.tech?
For now, we have a working prototype for customer location detection with 2 cameras and a prototype backend and UI for analysis of frequent customers’ appearances.
Further improvements we hope to make:
- Prototype backend and UI working with 2+ cameras.
- Define acceptable camera locations and orientations.
- Data collection for customer location accuracy measurements.
- Pipeline optimization, preparing code and infrastructure for production level.
- Collecting data and training POC model for estimation of customer location from a single camera, i.e. simplified scene reconstruction.
- Adding automatic detection of customer profile: favorite areas, emotions, preferred colors etc.
What are you looking forward to the most at Web Summit? How is Startup League helping you with preparing for your exhibit at the event?
We’re going to Web Summit to show our demo, to meet a lot of new people, to hear feedback from them, to learn from the influencers, to build partnerships and collaborations with other companies that will be interested in our tech or in Artificial Intelligence and Machine Learning solutions.
Startup League helped us to align our presentation, to fill the gaps in media aspects and provided a cool domain name such as eye-ai.tech.
Why did you choose a .TECH domain name? How is it helping you develop a unique online brand?
Oh, it was really easy! AI is a core technology in our product, so we decided to add that element as part of our product name. This made our choice for a domain name very obvious – only .TECH!