Two years ago, when Anurag Mundhada and Jayesh Hannurkar, both IIT-Bombay graduates, had weight problems during the first wave of Corona Virus Pandemic, they considered bringing their expertise in sensors and computer vision to create an interactive home training platform.
Mendada explained the idea behind this crazy AI implementation from the point of view of the consumer we’re working on is motivation. “Super fitness models and trainers can sometimes really turn off beginners, but if you make the initial setup process as smooth and friction-free as possible, fitness can be fun and fit for everyone,” he said.
Insane AI, which has been in beta for more than a year and is approaching an official launch soon, is different from other fitness apps, the founders claim. unlike apple The Fitness Plus or Nike Training Club, they said, Insane AI uses your smartphone’s front camera to track your movement during a workout.
“The camera tracks the body and breaks it down into 21 points: your shoulders, elbows, ankles, and knees. Once we’ve finished tracking the points in real time, we run an AI video layer over the layer that analyzes the movement, shows the exercise being performed, counts the number of reps, and then the system gives a score for how intense the exercise is. He,” said Menda Indianexpress.com during a video call.
“If you’re doing squats and your hips are below your knees, you get a score of one, and if you’re doing very shallow squats, you don’t get the same score,” he added. Mundhada claimed the AI-powered exercise tracking technology is 98 percent accurate based on the company’s internal testing data.
The intent to use a smartphone as an integral part of your fitness journey and create a new user experience around phone cameras comes from Mundhada and Jayesh’s previous experience in camera sensing technologies. was jayesh with Sony Japan prior to co-founding Insane AI and working on LiDAR sensors, a technology that adds deep scanning for better images and AR in smartphones and has been primarily found in Apple’s high-end iPhone and iPad Pro since 2020. Mundhada, on the other hand, has worked with Bengaluru-based Axogyan AI where it conducted a project with Mercedes-Benz for human sensing of self-driving vehicles.
Mandada said that he and his team were fascinated by the Nintendo Wii and Microsoft Kinect wanted to bring the ability to track body movement using a phone’s camera. Although smartphones have gotten better hardware over the years, depth sensors are still limited to a few more expensive phones. “Using artificial intelligence, we have enabled the regular RGB camera for real-time exercise tracking on all phones to do what a Nintendo Wii or Xbox Kinect can do,” he said when asked how a smartphone camera can track body movement without additional sensors.
To test whether a smartphone camera really tracks body movement and whether an app can be built around home workouts, Mundhada developed Pushup dojo that was published in the early days of the pandemic. The app was used as a proof of concept to demonstrate that technology and exercise tracking using a phone’s camera could be possible. It was a basic beta app that attracted 2,000 users, most of whom were the immediate friends and family of the co-founders. This gave Mundhada some confidence to rework algorithms, the user interface, and perfect body-tracking technology to create the Insane AI app in early 2021. This time around, the team worked with fitness coaches to create the app and intended a broad user base.
Mundhada Insane AI describes it as a home exercise app that has a “very fun gaming experience”. The application that can be downloaded from a file The Google Play Store and Apple App Store, currently require people to sign up for waiting list, and beginning the last week of October, crazy AI will be available to those currently on waiting list.
To use the app, one has to first set up a cartoon (y) that represents your virtual identity on the exercise platform. You can just put the phone in front of you at a distance, start the exercise, then the camera will start tracking your body movement during the exercise. Every workout or exercise that users take will be counted and they will be rewarded with coins that can be exchanged in the form of digital collectibles and coupons that the startup associates with a few partners. Users can also challenge their friends in real time as well as in turn-based fitness battles. The Insane AI app works on any smartphone launched in 2016 and later. In the coming days, users will see a completely new interface and a bunch of features including lots of workouts and exercises.
The AI-powered exercise technology model developed by Mundhada and his team not only tracks body points but also users’ fitness levels across five different dimensions such as strength, cardio, upper body and lower body. Mundhada said they took a lot of input from fitness experts to develop exercise plans and decide on different fitness levels, while the company’s in-house data science team worked to create a fitness model that could be customized and customized by the user. This crazy AI app offers 35 different exercises and 150 exercises, of which 4 are free exercises to get you started.
According to Mundhada, crazy AI appears to be widely used at 7:30 in the morning and another peak comes in the evening, around 6 p.m. On average, users spend nine minutes on the app, up from 5 minutes in the early days of Insane AI. However, power users spend nearly an hour on the platform.
“Crazy AI is not meant to completely replace a personal trainer,” said Menda, adding that the app is “designed to have an easy path to learn fitness and get further ahead.” “For situations like severe obesity, it’s always a good idea to have a human in the loop, and this is not only for learning but also for injury prevention, someone who can help you spot when you’re lifting weights.” Mundhada explains that Insane AI aims to provide a rewarding and enjoyable experience and complete your journey along the way.
The home workout app comes with the promise of not collecting users’ photos and videos but only collecting anonymized data of the movement itself to improve the AI engine that tracks the movement.
In order to monetize, Mundhada says they are turning to a freemium model that will allow users to try the app for free, with certain features like advanced challenges and redeeming rewards that require a subscription. Currently, those who subscribe to the app will get a free subscription for up to six months. Mundhada and the team are yet to figure out the cost of the subscription.
Last year, the startup raised $900,000 in seed funding. The round was led by early stage venture capital fund pi Ventures, Anupam Mittal, Samer Pitalwalla, and other angels in sports, fitness and technology. In the long run, Mundhada wants to turn crazy AI into fitness metaverse And work to build the foundation for an immersive world has already begun.
#Indian #startup #front #camera #smartphone #fitness #fun