Input - Click on the “+” button in the video player and upload a decent resolution video with less than 40mb.
Output - Provides an inferred video after locating every person in the frame and provides their locations (XY Coordinates) over a time in JSON format.
Note: Upload the appropriate video for optimal performance. Video that doesn't relate to the model might provide you unexpected results
The complexity of detection might increase with the increase in the number of people in the frame due to the dynamic nature of people movements and it is next to impossible for humans to track the people. TensorGo SOTA algorithms can detect the people regardless of their orientation or angle they are facing, light levels and clothing. The application can not only detect multiple people in a frame but can also get their location in the frame.
Taking an example of counting the number of people and tracking them over a stadium or in a public place is extremely important for law enforcement authorities and governments. Considering the Covid-19 situation we can count, track the people and analyse the crowd for better decision making.
Crowd Analytics, Crowd Behaviour, People Counting, People Tracking etc.,
TensorGo Platform provides you with a one stop solution to customize the our API offerings as per your use case by mixing and matching the existing APIs or requesting for a new custom model. This accelerates the development of use cases with minimal or no code towards deep learning applications.