Chubo Deng

Dr. Chubo Deng

orcid

Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

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

Representative Publications

View All Publications
18 September 2023 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
FYFanglong Yao
Fanglong Yao
WLWanxuan Lu
Wanxuan Lu
HYHeming Yang
Heming Yang
LXLiangyu Xu
Liangyu Xu
CLChenglong Liu
Chenglong Liu
KFKun Fu
Kun Fu
Remote sensing spatiotemporal prediction aims to infer future trends from historical spatiotemporal data, e.g., videos and time series images, has a broad application prospect in many fields. The foundation model is a promising research direction for spatiotemporal information mining because of its robust feature extraction capability, and has made rapid progress in natural scenes. Nevertheless, due to the spatially multi-scale and temporally multi-scale properties in remote sensing data, these methods still encounter bottlenecks when applied to remote sensing. Therefore, we propose a foundation model for remote sensing spatiotemporal prediction via spatiotemporal evolution decoupling, abbreviated as RingMo-Sense. Considering spatial affinity, temporal continuity, and spatiotemporal interaction, we construct spatial, temporal, and spatiotemporal triple-branch prediction networks. Specifically, we use parameter-sharing and progressive joint training strategies to achieve stable long-range prediction and parameter reduction simultaneously. In addition, we build a remote sensing spatiotemporal dataset by collecting various remote sensing videos and time series images. The experimental results on six downstream spatiotemporal tasks demonstrate that the proposed model yields competitive performance.

8 November 2020 in Remote Sensing
Verified
Journal Article
Open access
PDF file
CDChubo Deng
Chubo Deng
YCYi Cen
Yi Cen
Lifu ZhangLifu Zhang
Lifu Zhang
Hyperspectral images (HSIs), which obtain abundant spectral information for narrow spectral bands (no wider than 10 nm), have greatly improved our ability to qualitatively and quantitatively sense the Earth. Since HSIs are collected by high-resolution instruments over a very large number of wavelengths, the data generated by such sensors is enormous, and the amount of data continues to grow, HSI compression technique will play more crucial role in this trend. The classical method for HSI compression is through compression and reconstruction methods such as three-dimensional wavelet-based techniques or the principle component analysis (PCA) transform. In this paper, we provide an alternative approach for HSI compression via a generative neural network (GNN), which learns the probability distribution of the real data from a random latent code. This is achieved by defining a family of densities and finding the one minimizing the distance between this family and the real data distribution. Then, the well-trained neural network is a representation of the HSI, and the compression ratio is determined by the complexity of the GNN. Moreover, the latent code can be encrypted by embedding a digit with a random distribution, which makes the code confidential. Experimental examples are presented to demonstrate the potential of the GNN to solve image compression problems in the field of HSI. Compared with other algorithms, it has better performance at high compression ratio, and there is still much room left for improvements along with the fast development of deep-learning techniques.

30 October 2019 in Applied Sciences
Verified
Journal Article
Open access
PDF file
CDChubo Deng
Chubo Deng
Lifu ZhangLifu Zhang
Lifu Zhang
YCYi Cen
Yi Cen
This study focuses on the retrieval of chemical oxygen demand (COD) in the Baiyangdian area in North China, using a modified capsule network. Herein, the capsule model was modified to analyze the regression relationship between 1-D hyperspectral data and COD values. The results indicate there is a statistically significant correlation between COD and the hyperspectral data. The accuracy of the capsule network was compared with the results obtained from using a traditional back-propagation neural network (BP) method. The capsule network achieved superior accuracy with fewer iterations, compared with the BP algorithm. An R2 value of 0.78 was obtained against measured COD values retrieved using the capsule network method, compared with a value of 0.42 for the BP algorithm retrievals. This suggests the capsule network method has great potential to solve regression problems in the field of remote sensing.

6 March 2023 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
HYHongfeng Yu
Hongfeng Yu
CDChubo Deng
Chubo Deng
ZLzhao liangjin
zhao liangjin
LHLingxiang Hao
Lingxiang Hao
XLXiaoyu Liu
Xiaoyu Liu
HYHongjian You
Hongjian You
With the continuous maturity of remote sensing technology, the obtained remote sensing images' quality and quantity have surpassed any previous period. In this context, the content-based remote sensing image retrieval (CBRSIR) task attracts a lot of attention and research interest. Nowadays, the previous CBRSIR works mainly face the following problems. First of all, few works can realize one to many cross-modal image retrieval task (such as using optical image to retrieve SAR, optical images at the same time); secondly, researches mainly focus on small-area, target-level retrieval, and few on semantic-level retrieval of the whole image; last but not the least, most of the existing networks are characterized by massive parameters and huge computing need, which cannot be applied to resource-constrained edge devices with power and storage limit. For the sake of alleviating these bottlenecks, the paper introduces a novel light-weighted non-local semantic fusion network based on hypergraph structure for CBRSIR (abbreviated as HGNLSF-Net). Specifically, in the framework, using the topological characteristics of hypergraph, the relationship among multiple nodes can be modeled, so as to understand the global features on remote sensing images better with fewer parameters and less computation. In addition, since the non-local semantics often involves a lot of noise, the hard-link module is constructed to filter noise. A series of experimental results on typical CBRSIR dataset, i.e., MMRSIRD well show that with fewer parameters, the proposed HGNLSF-Net outperforms other methods and achieves optimal retrieval performance.

30 November 2021 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
JPJingquan Peng
Jingquan Peng
XSXian Sun
Xian Sun
HYHongfeng Yu
Hongfeng Yu
YTYu Tian
Yu Tian
CDChubo Deng
Chubo Deng
FYFanglong Yao
Fanglong Yao
With the availability of very high-resolution remote sensing imagery, the fine-grained recognition of complex geospatial facilities has become possible. We can view these facilities as a combination of component objects with specific functions and distribution. However, the existing methods are insufficient in modeling spatial relations of component objects. In this paper, we propose an instance-based multi-task graph network (IBMG-Net) for complex facility recognition. Specifically, we perform pixel-level component objects prediction and facility recognition simultaneously and achieve performance improvement of both tasks by joint multi-tasking training. Given the component information, we build an instance-based graph neural network (IBGN) where components are defined as nodes and their spatial relations are encoded as edges. The IBGN module aim to flexibly model spatial relations of complex facility. To enhance the feature representation of component objects, we utilize the multi-scale region of interest module (MS-ROI) to retain all scale-specific features and the sparse context module(SCM) to aggregate long-range context information. In addition, we build a new multi-task dataset for complex facility recognition in remote sensing (MCF dataset) to verify the effectiveness of our method and alleviate the lack of pixel-level labeled multi-task datasets in remote sensing. Extensive experiments on MCF also indicate that the significant performance improvement of our approach to complex facility recognition.

17 July 2025 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
QYQiwei Yan
Qiwei Yan
CDChubo Deng
Chubo Deng
CLChenglong Liu
Chenglong Liu
ZHZhongyan Hou
Zhongyan Hou
XLXiaorui Liu
Xiaorui Liu
XSXian Sun
Xian Sun
Scene graph generation (SGG) is a high-level visual understanding and reasoning task aimed at extracting entities (such as objects) and their interrelationships from images. Significant progress has been made in the study of SGG in natural images in recent years, but its exploration in the domain of remote sensing images remains very limited. The complex characteristics of remote sensing images necessitate higher time and manual interpretation costs for annotation compared to natural images. The lack of a large-scale public SGG benchmark is a major impediment to the advancement of SGG-related research in aerial imagery. In this article, we introduce the first publicly available large-scale, million-level relation dataset in the field of remote sensing images, which is named ReCon1M. Specifically, our dataset is built upon FAIR1M and comprises 22 262 images. It includes annotations for 873 761 object bounding boxes across 60 categories and 1 052 223 relation triplets across 59 categories based on these bounding boxes. We provide a detailed description of the dataset’s characteristics and statistical information. In addition, an efficient global context-aware network (EGCAN) is proposed to improve inference efficiency in dense relation prediction through an object-pair pre-screening mechanism. By integrating visual, spatial, and semantic features, EGCAN captures fine-grained pairwise features and object-level contextual information to enhance its ability to discriminate relation. We conduct two object detection tasks and three subtasks within SGG on this dataset, assessing the performance of mainstream methods on these tasks. The experimental results show that the proposed EGCAN achieves state-of-the-art (SOTA) performance in 17 out of 24 accuracy metrics across three tasks and delivers the best performance in frames per second (FPS) for model inference. The ReCon1M dataset and related resources are available at https://recon1m-dataset.github.io/