Smart lighting system
Background
Using a mounted camera with facial recognition, an IKEA TRÅDFRI gateway, and several IKEA smart light bulbs, develop a "follow me" system that can track a person’s position in a room and control the lighting accordingly. The system should detect where the person is and automatically turn on the lights closest to them.
Task
The main task of this project is to develop a smart lighting system that dynamically controls and adjusts the lighting based on facial detection within a room. The system will rely on a combination of computer vision and smart bulbs to allocate lighting in response to room occupancy and the position of people.
Main task:
- Develop a system that maps the camera’s image to the physical layout of the room.
- Detect the presence and position of a single people in the room. This will provide real-time data about people and their spatial distribution
- Turn on the light closest to the detected person and turn off the light if person is moving far from one light or disappear from the camera's view.
Bonus task:
- Develop the system with multiple persons.
- Control the brightness of the lighting based on the number of persons or the natural conditions like weather, day/night, etc.
- Warning system (i.g. change the colour once "unknown" persons are detected).
- Implement algorithms to optimize energy consumption by reducing lighting intensity when fewer people are present or when people are not near light sources.
Epic
This system will build upon prior work about facial recognition light-controller project, which provides a basic foundation.
Research Question
- Evaluate and compare the efficiency of different machine learning algorithms for person detection and tracking.
- The comparison between the smart lighting system and traditional static lighting solutions, from different perspectives such as user experience, energy saving, etc.
Legal and Technical Requirements
- All source code must be released under a copyleft license (e.g., GPLv3).
- Emphasis should be on product readiness, stability, and maintainability.
- Code must follow best practices, standardized language conventions, and provided templates.
- Automated checks, tests, and build procedures (via GitLab CI) should be implemented where possible.
- The final deliverable (build package) must be directly installable on the host operating system.