Garuda

Clicking selfies using mobile phones has become a trend in the past few years. It is documented that the thrill of clicking selfies at adventurous places has resulted in serious injuries and even death in some cases. To overcome this, we propose a system, which can alert the user by detecting the level of the danger in the background, during capturing selfies. Our app is based on a Convolution Neural Network (CNN) and analyzes the image in the camera view for risks in the background. The prediction is performed as a 5 category classification problem, with classes representing a different level of danger. Face detection, and device orientation information using accelerometer and magnetometer sensors, respectively, are also used for ease of use and lesser battery consumption.

Some snapshots of Garuda predictions in real-time