Abstract
A surveillance system is still the most exciting and practical security system to prevent crime effectively. Surveillance systems run on edge devices such as the low-cost Raspberry mobile camera with the Internet of Things (IoT). The primary purpose of this system is to recognize the identity of the face caught by the camera. However, it raises the challenge of unstructured image/video where the video contains low quality, blur, and variations of human poses. Moreover, the challenge is increasing because people used to wear a mask during the Covid -19 pandemic. Therefore, we proposed developing an all-in-one surveillance system with face detection, recognition, and face tracking capabilities. The surveillance system integrated three modules: Multi-Task Cascaded Convolutional Network (MTCNN) face detector, VGGFace2 face recognition, and Discriminative Single-Shot Segmentation (D3S) tracker. We train new face mask data for face recognition and tracking. This system utilizes the Raspberry Pi camera and processes the frame on the cloud as a mobile sensor approach. The proposed method was successfully implemented and got competitive detection, recognition, and tracking results under an unconstrained surveillance camera.
Original language | English |
---|---|
Pages (from-to) | 104-119 |
Number of pages | 16 |
Journal | International Journal of Interactive Mobile Technologies |
Volume | 15 |
Issue number | 23 |
DOIs | |
Publication status | Published - 2021 |
Keywords
- face detection
- face recognition
- face tracking
- low-cost camera
- masked face
- surveillance system