Nowadays, we get drones that say they are tracking objects. But what they actually use is the GPS location of your mobile phone. So basically what the drone is tracking is the phone and not the actual object/human. This was the reason we came up with this idea of making an Object Tracking Camera system that can be mounted on an autonomous drone. This system will track an object using Real-Time Image Processing.
##Components and Software Used:
- Python 2.7.5
- Open CV 2.9
- Raspberry-Pi B + board
- 3-D printed Camera mount frame
- Raspberry-Pi Camera(experimental purpose)
- Tower Pro SG90 mini servos
##Description:
The Object Tracking Camera mounted on the drone takes a Region of Interest(Object) from the user and tracks it using different algorithms and commands the drone to follow the object. Such capabilities are useful in several applications from photo/video shoots to surveys and search and rescue missions.
##Features:
- Selection of Object through an ROI
- Effective CAM shift Tracking Algorithm
- Camera wont get confused with similar colored objects
- Re-recognizing the lost Object
##Key Tasks
- Developing an Object Tracking Algorithm
- Making a Gimbal system for mounting the camera
- Building a Pan-Tilt camera with motors
- Interfacing Raspberry Pi with the camera
- Develop python codes to achieve autonomous behaviour of camera
##Deliverables
- A system that can mounted on an Autonomous drone
- Code and Documentation
- Tutorials explaining individual modules
##Documentation
- Detailed tutorials with actual component pictures on every module and detailed code of the project have been uploaded on GitHub.
##Contributors
##License
This project is open-sourced under MIT License