Department of Electronics Engineering, Kookmin University, Seoul 02707, Korea.
Department of Electrical and Computer Engineering, Stevens Institute of Technology, Hoboken, NJ 07030, USA.
Sensors (Basel). 2021 Jun 23;21(13):4283. doi: 10.3390/s21134283.
Embedding optical camera communication (OCC) commercially as a favorable complement of radio-frequency technology has led to the desire for an intelligent receiver system that is eligible to communicate with an accurate light-emitting diode (LED) transmitter. To shed light on this issue, a novel scheme for detecting and recognizing data transmitting LEDs has been elucidated in this paper. Since the optically modulated signal is captured wirelessly by a camera that plays the role of the receiver for the OCC technology, the process to detect LED region and retrieval of exact information from the image sensor is required to be intelligent enough to achieve a low bit error rate (BER) and high data rate to ensure reliable optical communication within limited computational abilities of the most used commercial cameras such as those in smartphones, vehicles, and mobile robots. In the proposed scheme, we have designed an intelligent camera receiver system that is capable of separating accurate data transmitting LED regions removing other unwanted LED regions employing a support vector machine (SVM) classifier along with a convolutional neural network (CNN) in the camera receiver. CNN is used to detect every LED region from the image frame and then essential features are extracted to feed into an SVM classifier for further accurate classification. The receiver operating characteristic curve and other key performance parameters of the classifier have been analyzed broadly to evaluate the performance, justify the assistance of the SVM classifier in recognizing the accurate LED region, and decode data with low BER. To investigate communication performances, BER analysis, data rate, and inter-symbol interference have been elaborately demonstrated for the proposed intelligent receiver. In addition, BER against distance and BER against data rate have also been exhibited to validate the effectiveness of our proposed scheme comparing with only CNN and only SVM classifier based receivers individually. Experimental results have ensured the robustness and applicability of the proposed scheme both in the static and mobile scenarios.
将嵌入式光通信（OCC）商业化作为射频技术的有利补充，这就需要一个智能接收器系统，使其能够与精确的发光二极管（LED）发射器进行通信。为了解决这个问题，本文提出了一种新颖的用于检测和识别数据传输 LED 的方案。由于光调制信号是由摄像机无线捕获的，摄像机在光通信技术中充当接收器的角色，因此需要智能的检测 LED 区域的过程，以及从图像传感器中提取准确信息的过程，以实现低误码率（BER）和高数据速率，从而确保在智能手机、车辆和移动机器人等最常用的商业摄像机的有限计算能力内实现可靠的光通信。在提出的方案中，我们设计了一种智能摄像机接收器系统，该系统能够通过支持向量机（SVM）分类器和摄像机接收器中的卷积神经网络（CNN），将精确的数据传输 LED 区域与其他不需要的 LED 区域分离。CNN 用于从图像帧中检测每个 LED 区域，然后提取关键特征，将其输入到 SVM 分类器中进行进一步的精确分类。广泛分析了接收器工作特性曲线和分类器的其他关键性能参数，以评估性能，证明 SVM 分类器在识别精确 LED 区域和以低 BER 解码数据方面的辅助作用。为了研究通信性能，详细展示了所提出的智能接收器的 BER 分析、数据速率和符号间干扰。此外，还展示了 BER 与距离和 BER 与数据速率的关系，以验证与仅基于 CNN 和仅基于 SVM 分类器的接收器相比，我们提出的方案的有效性。实验结果确保了所提出方案在静态和移动场景中的鲁棒性和适用性。
