Depth Perception — Using Intel RealSense

The goals of this project were to develop a computer vision model that identified the subject of interest as input from the user and measured its distance from the camera using its inbuilt LiDAR.

For this project, I decided to use a combination of the two systems available on Intel RealSense to create a depth estimation system that would provide accurate depth measurements with less noise. The system was based on a combination of a laser-based Lidar and an Infrared (IR) light-based camera. The Lidar was used to capture the coarse measurements of the environment and the IR camera was used to capture the fine details and to remove the noise from the measurements. This was done by calibrating the two systems such that the measurements from the Lidar and the camera were in sync with each other. The output of the system was then used for various applications such as object detection and tracking, collision avoidance, and navigation.