Created on 30th October 2020
•
The module consists of face mask detection system, social distancing alert raising system and thermal processing to detect fever . In this robust cross platform AI software product, we are using highly accurate object detection algorithms and methods. These methods and algorithms are based on deep learning frameworks. We can detect every little detail of object in image by the area object in a highlight rectangular boxes and identify every object and assign its tag to the object. This also includes the accuracy of each method for identifying objects. In this project our object is mask and pedestrians. Along with mask detection we have fever, conjunctivitis detection and screening using Thermal and RGB camera respectively. This system can be coupled in ‘AND’ logic and used at the doorbell. This solution will be helpful in preventing the spread of novel corona virus in post pandemic world. Explain your Idea/Solution with Key functions.
This is our AI Product to check and screen out the person who are not following the rules or carrying infection symptoms.
✔Contrary to others, this system is scalable and can detect multiple streams in optimal time.
✔Can be deployed on edge and cloud both along with battery backup (12 hrs max.) ✔The USP of this project is that it can detect multiple people (around 100) in one frame.
✔This has great use in surveillance and security purpose to find out who all are following the rules
1-) The main challange the we faced was in data optimisation and collection because the chinese based dataset was giving false results.
2-) Lowering the FPS of the output was another challenge the we faced as it was of utmost importance that the output feed could be made live
3-) We had to manually add the dataset with heavy beard as sometimes beard was detected as mask
Technologies used