Chenyang Lu

Chenyang Lu

Auto-generated profile, based on publicly available information

Chenyang Lu

Faculty of Electrical Engineering and Computer Science, Ningbo University, Ningbo, China

Research Focus & Metrics

Academic Career Length

21Years (2006-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
7 January 2019 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
CLChenyang Lu
Chenyang Lu
MMMarinus Jacobus Gerardus van de Molengraft
Marinus Jacobus Gerardus van de Molengraft
GDGijs Dubbelman
Gijs Dubbelman
In this work, we research and evaluate end-to-end learning of monocular semantic-metric occupancy grid mapping from weak binocular ground truth. The network learns to predict four classes, as well as a camera to bird's eye view mapping. At the core, it utilizes a variational encoder-decoder network that encodes the front-view visual information of the driving scene and subsequently decodes it into a 2-D top-view Cartesian coordinate system. The evaluations on Cityscapes show that the end-to-end learning of semantic-metric occupancy grids outperforms the deterministic mapping approach with flat-plane assumption by more than 12% mean IoU. Furthermore, we show that the variational sampling with a relatively small embedding vector brings robustness against vehicle dynamic perturbations, and generalizability for unseen KITTI data. Our network achieves real-time inference rates of approx. 35 Hz for an input image with a resolution of 256×512 pixels and an output map with 64×64 occupancy grid cells using a Titan V GPU.

24 June 2024 in IEEE Transactions on Instrumentation and Measurement
Verified
Journal Article
Closed access
ZXZhengxuan Xie
Zhengxuan Xie
FSFeng Shao
Feng Shao
BMBaoyang Mu
Baoyang Mu
HCHangwei Chen
Hangwei Chen
Qiuping JiangQiuping Jiang
Qiuping Jiang
YHYo-Sung Ho
Yo-Sung Ho
In recent years, crowd counting has attracted widespread attention due to its enormous potential in the public safety inspection process. Visual-based measurement techniques had been widely applied in crowd counting, which is a fundamental and challenging sub-task in crowd analysis and smart city systems. With the popularization of infrared sensors, RGBT crowd counting method that collaboratively utilizes RGB and thermal information to estimate the number of crowds has been developed. However, the failure to effectively explore the complementary information between RGB and thermal modality features has hindered the further development of RGB-T crowding counting. Most existing methods attempt to achieve the effective fusion of RGB and thermal features through various fusion strategies. However, most of these methods ignore the inherent modality differences between the RGB and thermal information, resulting in inaccurate crowd counting. For this, we propose a Bidirectional gated and dynamic fusion network (BGDFNet) for RGB-T crowd counting. Specifically, we propose a novel bidirectional gated module (BGM) to make full use of supplementary information between modalities to bridge the modality gaps. In addition, we propose a multi-scale dynamic fusion (MSDF) module to achieve effective feature fusion by dynamically selecting the weights of multi-scale convolutions. Finally, an effective crowd density map is obtained through the decoder and fully connected layer. On the available RGB-T crowd counting dataset, compared to the existing state-of-the-art (SOTA) methods, the proposed BGDFNet has achieved 12.35%, 8.23%, 2.02%, and 12.01% performance improvements on GAME (0), GAME (1), GAME (2), and RMSE, respectively. The code and models are available at: https://github.com/ZhengxuanXie/BGDFNet.

20 January 2020 in IEEE Robotics and Automation Letters
Verified
Journal Article
Closed access
CLChenyang Lu
Chenyang Lu
GDGijs Dubbelman
Gijs Dubbelman
Semantic scene understanding is an essential task for self-driving vehicles and mobile robots. In our work, we aim to estimate a semantic segmentation map, in which the foreground objects are removed and semantically inpainted with background classes, from a single RGB image. This semantic foreground inpainting task is performed by a single-stage convolutional neural network (CNN) that contains our novel max-pooling as inpainting (MPI) module, which is trained with weak supervision, i.e., it does not require manual background annotations for the foreground regions to be inpainted. Our approach is inherently more efficient than the previous two-stage state-of-the-art method, and outperforms it by a margin of 3% IoU for the inpainted foreground regions on Cityscapes. The performance margin increases to 6% IoU, when tested on the unseen KITTI dataset. The code and the manually annotated datasets for testing are shared with the research community at https://github.com/Chenyang-Lu/semantic-foreground-inpainting.

31 May 2024 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
HQHangfeng Qiao
Hangfeng Qiao
HJHuiping Jiang
Huiping Jiang
Gang YangGang Yang
Gang Yang
FJFaming Jing
Faming Jing
Weiwei SunWeiwei Sun
Weiwei Sun
Xiangchao MengXiangchao Meng
Xiangchao Meng
Urban functional zones (UFZ) identification with remote sensing imagery (RSI) is attracting increasing attention in urban planning and resource allocation in urban areas, etc. The UFZ is a comprehensive unit comprising geographical, how to effectively integrate the RSI and points of interest (POI) with different physical and socioeconomic characteristics is important and promising. However, there are two challenges for the UFZ identification. On one hand, the UFZ is closely related to buildings, and most current methods lack an in-depth understanding of building semantics. Therefore, an efficient integration of building footprint (FT) data deserves further investigation. On the other hand, these RSI, POI, and FT data are heterogeneous; how to effectively leverage complementary information among these highly heterogeneous modalities to enhance the comprehensive understanding of urban. To solve the above challenges, this study introduces an end-to-end deep learning-based multi-source dynamic fusion network for UFZ identification on RSI, POI, and FT. In the proposed method, an adaptive weight interactive fusion module (AW-IFM) is designed to comprehensively integrate the complementary information among the heterogeneous RSI, POI, and FT data sources. In addition, a multi-scale feature focus module (MS-FFM) is proposed to extract multi-scale image features and emphasize critical characteristics. This method was applied to UFZ classification in Ningbo, Zhejiang Province, China, and the experimental results demonstrate the competitive performance.

1 November 2020 in Pattern Recognition
Verified
Journal Article
Open access
CLChenyang Lu
Chenyang Lu
GDGijs Dubbelman
Gijs Dubbelman

4 October 2006
Verified
Conference Paper
Closed access
XWXiaorui Wang
Xiaorui Wang
JDJia Dong
Jia Dong
CLChenyang Lu
Chenyang Lu
XKXenofon Koutsoukos
Xenofon Koutsoukos