RENBO LUO

Dr. RENBO LUO

orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
15 December 2022 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
JLJiabin Liu
Jiabin Liu
HHHuaigang Huang
Huaigang Huang
HSHanxiao Sun
Hanxiao Sun
ZWZhifeng Wu
Zhifeng Wu
RLRENBO LUO
RENBO LUO
The building extraction method of remote sensing images that uses deep learning algorithms can solve the problems of low efficiency and poor effect of traditional methods during feature extraction. Although some semantic segmentation networks proposed recently can achieve good segmentation performance in extracting buildings, their huge parameters and large amount of calculation lead to great obstacles in practical application. Therefore, we propose a lightweight network (named LRAD-Net) for building extraction from remote sensing images. LRAD-Net can be divided into two stages: encoding and decoding. In the encoding stage, the lightweight RegNet network with 600 million flop (600MF) is finally selected as our feature extraction backbone net though lots of experimental comparisons. Then a multi-scale depthwise separable atrous spatial pyramid pooling (DSASPP) structure is proposed to extract more comprehensive and important details of buildings. In the decoding stage, the squeeze-and-excitation (SE) attention mechanism is applied innovatively to redistribute the channel weights before fusing feature maps with low-level details and high-level semantics, thus can enrich the local and global information of the buildings. What's more, a lightweight residual block with polarized self-attention (LPA) is proposed, it can incorporate features extracted from the space of maps and different channels with a small number of parameters, and improve the accuracy of recovering building boundary. In order to verify the effectiveness and robustness of proposed LRAD-Net, we conduct experiments on a self-annotated UAV dataset with higher resolution and three public datasets (the WHU aerial image dataset, the WHU satellite image dataset and the Inria aerial image dataset). Compared with several representative networks, LRAD-Net can extract more details of building, and has smaller number of parameters, faster computing speed, stronger generalization ability, which can improve the training speed of the network without affecting the building extraction effect and accuracy.

6 July 2022 in Remote Sensing
Verified
Journal Article
Open access
PDF file
Qifei ZhangQifei Zhang
Qifei Zhang
Zihao ZhengZihao Zheng
Zihao Zheng
ZWZhifeng Wu
Zhifeng Wu
ZCZheng Cao
Zheng Cao
RLRENBO LUO
RENBO LUO
The DMSP/OLS Nighttime light (NTL) data directly reflect the spatial distribution and light intensity of artificial lighting from the Earth’s surface at night, and has become an emerging instrument for urbanization research, including in the monitoring of urban expansion, assessment of socio-economic vitality, and estimation of energy consumption and population. However, due to the imperfect sensor design of DMSP/OLS, the dynamic range of the digital number (DN) of NTL is limited (0, 63), leading to a significant saturation problem when describing the actual light intensity, especially in dense urban areas with high light intensity. This saturation problem masks spatial differences in light intensity and weakens the reliability of DMSP/OLS NTL data. Therefore, this study proposes a novel desaturation indicator that combines NDBI and POI, the Building and POI Density-Adjusted Nighttime Light Index (BPANTLI), to regulate the DMSP/OLS NTL saturation problem based on the spatial characteristics of urban structures and human activity intensity. The proposed method is applied to three urban agglomerations with the most severe light saturation issues in China. The geographical detector model is firstly utilized to quantify the effectiveness of NDBI and POI in reflecting the difference in light intensity distribution from the NTL potential saturation region (NTL DN value (53, 63)) and NTL unsaturation region (NTL DN value (0, 52)), so as to clarify the feasibility of developing the BPANTLI. The applicability of BPANTLI is validated through three aspects—comparison of the desaturation capacity and the performance of delineating light intensity; verification of the consistency of BPANTLI with radiometric calibration nighttime light product (RCNTL) and NPP/VIIRS data; and assessing the accuracy of the BPANTLI in estimating socio-economic parameters (GDP, electricity consumption, population density). The results indicate that the BPANTLI possesses superior capability in regulating the NTL saturation problem, achieving good performance in distinguishing inner-urban structures. The regulated results reveal a remarkably improved correspondence with the RCNTL and NPP/VIIRS data, providing a more realistic picture of the light intensity distribution. It is worth noting that, given the advantages of NDBI and POI vector data in spatial resolution, the BPANTLI established in this study can overcome the limitation of the spatial resolution of DMSP/OLS nighttime lighting data and achieve dynamic transformation of the spatial resolution. The higher spatial resolution desaturation results allow for a better characterization of the light intensity distribution. Moreover, the BPANTLI-regulated light intensity significantly improves the accuracy of estimating electricity consumption, GDP, and population density, which provides a valuable reference for urban socio-economic activity assessment. Thus, the BPANTLI proposed in this study can be considered as a reasonable desaturation method with a high application value.

19 December 2024 in IEEE Access
Verified
Journal Article
Open access
JHJunyu Huang
Junyu Huang
RLRENBO LUO
RENBO LUO
YTYuna Tan
Yuna Tan
WZWu Zhuowen
Wu Zhuowen
This study focuses on the detection of Jaboticaba trees in an orchard located in Nanxiong City, Guangdong Province, utilizing UAV platforms to enhance precision agriculture practices. The primary objective is to compress the parameters of deep learning models while improving accuracy to enable their deployment on UAV platforms for rapid Jaboticaba tree identification. The proposed CRE-YOLO model integrates a Cross-Scale Feature Fusion Module (CCFM), the RepDWBlock, and an Efficient Channel Attention (ECA) mechanism, reducing model parameters by 54%, effectively decreasing model complexity while improving detection precision. CRE-YOLO achieves a mean average precision (mAP) of 97.1% at IoU 0.5 and 60.3% at IoU 0.95, with a processing speed of 387 frames per second. Field experiments conducted in the research area identified over 13,000 Jaboticaba trees, demonstrating the model’s potential for practical UAV-based orchard management. The study contributes to the modernization of agricultural practices by providing an efficient, scalable solution for rapid and accurate tree detection. Future work will extend the model’s application to other crops and focus on enhancing its generalization capabilities.

20 January 2026 in Drones
Verified
Journal Article
Open access
PDF file
JCJiawei Chen
Jiawei Chen
JHJunyu Huang
Junyu Huang
ZZZuye Zhang
Zuye Zhang
Jinxin YangJinxin Yang
Jinxin Yang
ZWZhifeng Wu
Zhifeng Wu
RLRENBO LUO
RENBO LUO
UAV-based object detection faces critical challenges including extreme scale variations (targets occupy 0.1–2% image area), bird’s-eye view complexities, and all-weather operational demands. Single RGB sensors degrade under poor illumination while infrared sensors lack spatial details. We propose ATM-Net, a lightweight multimodal RGB–infrared fusion network for robust UAV vehicle detection. ATM-Net integrates three innovations: (1) Asymmetric Recurrent Fusion Module (ARFM) performs “extraction→fusion→separation” cycles across pyramid levels, balancing cross-modal collaboration and modality independence. (2) Tri-Dimensional Attention (TDA) recalibrates features through orthogonal Channel-Width, Height-Channel, and Height-Width branches, enabling comprehensive multi-dimensional feature enhancement. (3) Multi-scale Adaptive Feature Pyramid Network (MAFPN) constructs enhanced representations via bidirectional flow and multi-path aggregation. Experiments on VEDAI and DroneVehicle datasets demonstrate superior performance—92.4% mAP50 and 64.7% mAP50-95 on VEDAI, 83.7% mAP on DroneVehicle—with only 4.83M parameters. ATM-Net achieves optimal accuracy–efficiency balance for resource-constrained UAV edge platforms.

3 January 2025 in Remote Sensing
Verified
Journal Article
Open access
PDF file
WXWenya Xue
Wenya Xue
FLFeng Liping
Feng Liping
Jinxin YangJinxin Yang
Jinxin Yang
YXYong Xu
Yong Xu
HHHung Chak Ho
Hung Chak Ho
MWMan Sing Wong
Man Sing Wong
Vegetation indices, especially the normalized difference vegetation index (NDVI), are widely used in urban vegetation assessments. However, estimating the vegetation abundance in urban scenes using the NDVI has constraints due to the complex spectral signature related to the urban structure, materials and other factors compared to natural ground surfaces. This paper employs the 3D discrete anisotropic radiative transfer (DART) model to simulate the spectro-directional reflectance of synthetic urban scenes with various urban geometries and building materials using a flux-tracking method under shaded and sunlit conditions. The NDVI is calculated using the spectral radiance in the red (0.6545 μm) and near-infrared bands (0.865 μm). The effects of the urban material heterogeneity and 3D structure on the NDVI, and the performance of three NDVI-based fractional vegetation cover (FVC) inversion algorithms, are evaluated. The results show that the effects of the building material heterogeneity on the NDVI are negligible under sunlit conditions but not negligible under shaded conditions. The NDVI value of building components within synthetic scenes is approximately zero. The shaded road exhibits a higher NDVI value in comparison to the illuminated road because of scattering from adjacent pixels. In order to correct the effects of scattering caused by building geometry, the reflectance of the Landsat 8/OLI image is corrected using the sky view factor (SVF) and then used to calculate the FVC. Jilin-1 satellite images with high spatial resolution (0.5 m) are used to extract the vegetation cover and then aggregated to 30 m spatial resolution to calculate the FVC for validation. The results show that the RMSE is up to 0.050 after correction, while the RMSE is 0.169 before correction. This study makes a contribution to the understanding of the effects of the urban 3D structure and material reflectance on the NDVI and provides insights into the retrieval of the FVC in different urban scenes.

13 November 2023 in Land
Verified
Journal Article
Open access
PDF file
KGKai Guo
Kai Guo
ZHZhenhao He
Zhenhao He
XLXiaojin Liang
Xiaojin Liang
XCXuanwei Chen
Xuanwei Chen
RLRENBO LUO
RENBO LUO
KZKexin Zhang
Kexin Zhang
Land use changes are an important factor contributing to the increasingly severe deterioration of the ecological environment. Therefore, regional analyses of land use and ecological risk should be developed for the restoration of ecological functions. In this study, a comprehensive ecological risk assessment was constructed on a regional scale and applied to Daye, a traditional mining city in China. Cointegration analyses and Granger causality tests were used to explore the complex relationship between land use and ecological risks in the study area from 2007 to 2021. The results show a long-term and stable relationship between land use changes in different sub-regions and ecological risks, albeit with distinct Granger causality relationships. This research presents the development trend of the relationship between land use change and ecological risks in a mining city, from rapid economic growth to economic restructuring and full-region ecological governance.