A Real-Time Distance Prediction via Deep Learning and Microsoft Kinect

Abstract 3D(Dimension) understanding has become the herald of computer vision and graphics research in era technology. It benefits many applications such as autonomous cars, robotics, medical image processing. The pros cons 3D detection bring convenience to human community instead 2D detection. consists RGB (Red, Green Blue) colour images depth which are able perform better than real. current technology is relying on high costing light ranging (LiDAR). However, use Microsoft Kinect replaced LiDAR systems for gradually. In this project, a camera used extract information. From images, distance can be defined easily. As scale, red nearest blue farthest. will turn black when reaching limitation measuring range. information collected trained with deep learning architecture real-time prediction.