Abstract
Optical camera communication is an emerging technology that enables communication using light beams, where information is modulated through optical transmissions from light-emitting diodes (LEDs). This work conducts empirical studies to identify the feasibility and effectiveness of using deep learning models to improve signal reception in camera communication. The key contributions of this work include the investigation of transfer learning and customization of existing models to demodulate the signals transmitted using a single LED by applying the classification models on the camera frames at the receiver. In addition to investigating deep learning methods for demodulating a single VLC transmission, this work evaluates two real-world use-cases for the integration of deep learning in visual multiple-input multiple-output (MIMO), where transmissions from a LED array are decoded on a camera receiver. This paper presents the empirical evaluation of state-of-the-art deep neural network (DNN) architectures that are traditionally used for computer vision applications for camera communication.
Highlights
Optical camera communication is an emerging technology that enables communication using light beams, where information is modulated through optical transmissions from light-emitting diodes (LEDs)
We present a systematic empirical evaluation of existing state-of-the-art deep neural network (DNN) models used for classification problems in computer vision towards demodulation of the LED signal registered on a camera image
We evaluate the performance of different state-of-the-art DNN models towards classifying or demodulating the LED signal state from camera sampled images in Optical Camera Communication (OCC)
Summary
The use of optical frequencies for communication through the concept of VLC or visible light communication (400–800 THz) has garnered significant interest over the last decade. The other challenges in OCC are carried over from those in computer vision, such as impact of lighting conditions (day vs night, morning vs evening and sunny vs cloudy), weather conditions (fog, rain or snow) and mobility (variable perspectives between transmitter and receiver) on the quality of LED signal registered on the camera image. Considering the advances made in the computer vision and image analysis areas with the help of deep neural networks (DNN), in this paper, we hypothesize that DNN models can be helpful in addressing the OCC challenges In this regard, we present a systematic empirical evaluation of existing state-of-the-art DNN models used for classification problems in computer vision towards demodulation of the LED signal registered on a camera image. Based Demodulation Evaluation; Section 4—Case Study A: LED Array MIMO Multiplexing; Section 5—Case Study B: Underwater OCC under MIMO Civersity; Section 6—Conclusions
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
