A vision-based infrared decoy tracking algorithm for air conditioner spot cooling

Air conditioner has become one of the most common electrical appliances in every household. With the increase in their demand, the challenge to reduce the energy usage of air conditioner has become a subject of intense study in recent years. Spot cooling is one of the methods that can reduce the ene...

Full description

Bibliographic Details
Main Authors: Tan, Andy Wei Keat (Author), Chan, Hao Jie (Author), Teoh, Soo Siang (Author), Lim, Cheng Siong (Author)
Format: Article
Language:English
Published: Penerbit UTHM, 2020-05.
Subjects:
Online Access:Get fulltext
Description
Summary:Air conditioner has become one of the most common electrical appliances in every household. With the increase in their demand, the challenge to reduce the energy usage of air conditioner has become a subject of intense study in recent years. Spot cooling is one of the methods that can reduce the energy wastage. In this method, a control algorithm is implemented to actively track the location of users and direct the air conditioner's air flow to these targeted areas. This can make the cooling more efficient since the air conditioner does not need to cool down the entire room. By selectively directing the air flow, the users can still achieve the same cooling comfort. This paper proposed a technique of spot cooling for air conditioner using infrared (IR) camera and a decoy. The decoy is based on IR light emitting diodes arranged in a specific pattern. The IR camera captures the video of the room to locate the position of the decoy. Image processing techniques include thresholding and template matching are used for the decoy detection. Once the decoy is detected, the movement of the decoy is tracked by using a Kalman filter. To test the performance of the proposed method, a prototype system was implemented on a Raspberry Pi board and the accuracy of detection was evaluated. Experimental results showed that the system is able to detect the position of decoy with 98% accuracy in both day and night-time conditions.