Object Detection And Monitor System For Building Security Based On Internet Of Things (IoT) Using Illumination Invariant Face Recognition

Ivan Chatisa (Politeknik Caltex Riau)
Yoanda Alim Syahbana (Politeknik Caltex Riau)
Agus Urip Ari Wibowo (Politeknik Caltex Riau)

Proceeding International Applied Business and Engineering Conference
Vol. 2 (2022): Proceeding International Applied Business and Engineering Conference 2022

Theft, burglary and intrusion are criminal acts that often occur in the environment when there are opportunity or negligence made by the owner and security officers. Many studies have been carried out to improve environmental security by applying cameras as a surveillance medium. However, the camera is still not optimal at detecting objects if the environment is in poor lighting conditions (dark). Therefore, in this study, a monitoring and object detection system was built by applying the Illumination Invariant model. Illumination Invariant model that is used to improve the appearance of object images from light and shadow reflections. In this study, the detection process and objects are carried out using human facial features captured by the camera. The camera used is a Logitec C270 Webcam HD 720p via the USB port on the Raspberry Pi. Raspberry Pi processes human face image data and sends the results of data processing to a MySQL database using the HTTP Protocol. The process of sending data is done with the concept of API (Application Programming Interface) using Python Flask. In this study, all tests were carried out on the system using black box testing techniques with the results of the functional requirements being successfully executed 100%. In this study, testing the object detection feature based on different lighting conditions. The test was carried out 15 times by comparing the original image and the results of the implementation of the Illumination Invariant model. Based on the test results by applying the illumination of the Invariant model, the quality of object detection accuracy is 86.7%.