In this paper, a resource partitioning scheme combined with a new multi-carrier optical modulation technique for indoor visible light communication (VLC) system is proposed. In VLC systems, the coverage area is divided into multiple atto-cells. In each atto-cell, multiple LED arrays are used as access points (APs) serving the assigned users. The coverage area of APs might be overlapped to avoid service discontinuity for mobile users. The overlapped coverage zones result in co-channel interference (CCI). We develop a shared frequency reuse (SFR) technique combined with two resource allocation algorithms to minimize interference and maximize the system throughput. This technique divides the overall bandwidth into two parts: the shared and reused bands. The shared band serves the users in the interference area while the reused band serves users in the non-interfering area. Furthermore, we propose a new multi-carrier optical modulation technique called odd clipped optical-OFDM (OCO-OFDM). This technique applies the odd symmetry on the frequency-domain OFDM to enhance the spectral efficiency compared to the asymmetrical clipped optical OFDM (ACO-OFDM) which is currently used. Then we study and evaluate the system performance in terms of the signal-to-interference and noise ratio (SINR), total throughput, and the outage probability. The proposed system achieved total throughput of up to 800 Mbps with 40 dB SINR at the cell edge. Furthermore, the outage probability can be optimized to its minimum value when the receiver fieldof-view (FOV) is taken by 40 when the minimum SINR is 10 dB.
Automatic lane detection is a classical task in autonomous vehicles that traditional computer vision techniques can perform. However, such techniques lack reliability for achieving high accuracy while maintaining adequate time complexity in the context of real-time detection in complex and dynamic road scenes. Deep neural networks have proved their ability to achieve competing accuracy and time complexity while training them on manually labeled data. Yet, the unavailability of segmentation masks for host lanes in harsh road environments hinders fully supervised methods' operability on such a problem. This work proposes integrating traditional computer vision techniques and deep learning methods to develop a reliable benchmarking framework for lane detection tasks in complex and dynamic road scenes. Firstly, an automatic segmentation algorithm based on a sequence of traditional computer vision techniques has been experimented. This algorithm precisely segments the semantic region of the host lane in the complex urban images of nuScenes dataset used in this framework; hence corresponding weak labels are generated. After that, the developed data is qualitatively evaluated to be used in training and benchmarking five state-of-the-art FCN-based architectures: SegNet, Modified SegNet, U-Net, ResUNet, and ResUNet++. The performance evaluation of the trained models is done visually and quantitatively by considering lane detection a binary semantic segmentation task. The output results show robust performance, especially ResUNet++, which outperforms all the other models while testing them in different complex road scenes with dynamic scenarios and various lighting conditions.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.