CSChenyang Sun

Chenyang Sun

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Chenyang Sun has a total of 17 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Collaborative and Reidentifying Techniques for Improved Monocular 3-D Perception in Vehicles

    by Chenyang Sun, Yang Wang, Huafu Li, Junqi Guo, Yanfei Deng

    This paper proposes a method for enhancing vehicle monocular three-dimensional perception using vehicle re-identification (Re-ID) and collaborative vehicle infrastructure systems (CVIS), aimed at enhancing the perception range and safety of the majority of intelligent connected vehicles currently using cameras. The method initially employs a monocular three-dimensional perception approach to extract images and rough three-dimensional information of traffic targets from the vehicle side. Following that, an adaptive compression method called Adaptive-FALSH is introduced, which, combined with vehicle Re-ID technology, enables efficient compression and correlation of vehicle Re-ID features. Ultimately, a perception fusion method dubbed HRHF is proposed, merging monocular three-dimensional detection results from the vehicle side and high-precision perception results from the roadside. This method quickly extend roadside perception results in real-time to the vehicle side, thereby enhancing the vehicle’s perception range. Experimental results demonstrate that this method efficiently merges three-dimensional target perception information from both vehicle and road sides using just a few hundred bytes, without the need for high-precision maps and GPS assistance. While reducing communication data volume, this method also effectively widens the perception range of intelligent connected vehicles.


  • Efficient Vehicle-Infrastructure Collaborative Perception Based on Vehicle Re-Identification and Mini-ICP Algorithm

    by Chenyang Sun, Yang Wang, Yanfei Deng, Huafu Li, Rundong Zhou, Junqi Guo

    The efficient exchange of perception information between vehicles and infrastructure is crucial for implementing vehicle-infrastructure (VI) collaborative intelligent driving. To address the high real-time requirements of VI communication and lack of intelligence and flexibility in VI cooperation, this study proposes an efficient collaborative perception method based on vehicle re-identification for VI collaboration scenarios. The real-time requirements of such scenarios are addressed and a lightweight vehicle re-identification network called ShuffleBNLSH is designed. This network is combined with a hash algorithm to quickly generate ID information for collaborative sensing targets. Based on the state of the VI communication channel, the network can adaptively extract the bit features of the perceived vehicle target, adjust the feature length, and quickly perform feature matching for vehicle target re-identification. To rapidly fuse the VI collaborative perception information combined with the re-identification results and LiDAR 3D perception information from the vehicle and infrastructure, we designed a mini-ICP algorithm that can automatically select feature points and perform point-cloud registration. Experimental results show that the amount of data transmitted by a single target in cooperative sensing can be as small as hundreds of bits during the fusion of sensing targets on the vehicle and infrastructure sides. This reduces the bandwidth requirements for fusing perception targets, accelerates feature transmission and matching, and expands the perception range of VI collaborative autonomous vehicles without GPS information.


  • Performance Analysis and Transmission Block Size Optimization for Massive MIMO Vehicular Network With Spatially and Temporally Correlated Channels

    by Huafu Li, Liqin Ding, Yang Wang, Chenyang Sun, Zhenyong Wang

    We investigate the effect of spatially and temporally correlated channels on the transmission performance of multi-cell multi-user massive multiple-input multiple-output (MIMO) vehicular networks in generic non-isotropic scattering environments. A new channel model is established to evaluate the harmfulness of the non-isotropic-scattered angle-of-departure/angle-of-arrival (AoD/AoA) spread and the high mobility of users on the uplink transmission. We derive the expressions of achievable spectral efficiency (SE), taking into account the effects of line-of-sight propagation, channel aging, and pilot contamination. Specifically, two novel receive combining schemes, namely the aging-aware maximum ratio combining and the aging-aware minimum mean square error combining, are presented to mitigate the SE decline caused by outdated channel state information. A low-complexity pilot assignment algorithm is proposed to suppress pilot contamination. We find that the quasi-static assumption of the channel may be unsafe for the system design of the vehicular networks even within a single transmission block period lasting from hundreds of microseconds to a few milliseconds. We observe that there exists an optimal block size Copt that maximizes area spectral efficiency. Especially, Copt can be expressed as a function of movement speed, AoD spread, and AoA spread. Numerical results are presented to validate the efficacy of the proposed schemes and highlight the importance of correct performance evaluation for practical massive MIMO system designs.

  • User-Centric Cell-Free Massive MIMO for IoT in Highly Dynamic Environments

    by Huafu Li, Yang Wang, Chenyang Sun, Zhenyong Wang

    Cell-free massive multiple-input-multiple-output (CF-mMIMO) network and its low-complexity user-centric (UC) alternative rely on accurate and up-to-date channel state information (CSI) for combining and/or precoding a large number of signals received by the distributed antenna array to achieve their anticipated performance gains. When serving highly mobile Internet of Things (IoT) devices, limited Line-of-Sight (LoS) information and nonnegligible channel aging (CA) effects will undermine CSI acquisition and inevitably degrade system performance. As a result, fundamental limit assessment and performance degradation mitigation under imperfect CSI are important for practical system designs. In this article, we focus on the performance of UC CF-mMIMO IoT systems in the interaction of sufficient and insufficient LoS knowledge, nonisotropic Non-LoS components, and heterogeneous CA effects. The novel and exact closed-form expressions for uplink spectral efficiency (SE) under the impaired CSI are derived. Numerical results verify the correctness of the SE expressions and reveal that the system parameters, such as resource block length and pilot overhead, should be optimally preconfigured according to environmental information and transmission tasks to alleviate the performance degradation caused by the imperfect CSI. Finally, a UC soft handover scheme is designed to enhance the mobility support of CF-mMIMO IoT systems in practical implementation.


  • Collision-Free Waterway Segmentation for Inland Unmanned Surface Vehicles

    by Rundong Zhou, Yulong Gao, Peng Wu, Xiongwei Zhao, Wenhao Dou, Chenyang Sun, Yu Zhong, Yang Wang

    Accurate detection of passable regions in images is important for ensuring the safe navigation of unmanned surface vehicles, especially in inland waterways with irregular waterlines and various obstacles. However, the existing methods are susceptible to environmental changes and produce high false-positive rates (FPRs) for confusable textures and complex edge details. We, therefore, propose a collision-free waterway segmentation network based on deep learning such that pixel-level classification results can be obtained. The segmentation accuracy for indistinguishable textures is improved by learning the context dependency of features through a modified context prior, and the detailed refinement of waterlines and small obstacles is achieved via an asymmetric encoder–decoder structure. To learn the features of waterways as comprehensively as possible, data integration and data augmentation are performed on three public datasets. In addition, a new annotated urban waterway dataset called the Dasha River dataset is proposed and made publicly available. The proposed model is tested and cross validated using multiple inland and maritime water segmentation datasets, the results of which show that the model achieves superior performance than the current state of the art with pixel accuracy (PA) of 97.43% and FPR of 1.37%.


  • Pedestrian Re-identification with Adaptive Feature Dimension Reduction for Vehicle-Road Cooperative Perception

    by Yixin Zeng, Chenyang Sun, Liqin Ding, Jianyao Hu, Zhenwu Chen, Yu Tian, Yang Wang

    Using vehicles and roads to perceive pedestrians cooperatively can eliminate the visual limitation of a single vehicle, thus improve the pedestrian collision warning capability of the driving assistance system. In this paper, we propose a vehicle-road pedestrian re-identification (ReID) system for vehicle-road cooperative perception of pedestrians, which can provide real-time and reliable ReID results under the premise of minimizing the occupation of communication resources. Among the system, we propose the CNN-LSH feature extraction algorithm and adaptive feature dimension reduction algorithm to adjust the dimension of pedestrian images features effectively according to the status of wireless channel, and use Hamming distance metric to simplify the calculation of feature similarity, which accelerates the speed of image feature matching in ReID. Experimental results demonstrate that the vehicle-road ReID system can significantly reduce the communication overhead and computation time while providing reliable ReID results in real-time.