Jian Wang

Jian Wang

Auto-generated profile, based on publicly available information

Jian Wang

Aerospace Information Research Institute, CAS, Beijing 100094, China

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
23 September 2022 in Remote Sensing
Verified
Journal Article
Open access
PDF file
XZXiaoyan Zhang
Xiaoyan Zhang
LLLinhui Li
Linhui Li
DDDonglin Di
Donglin Di
JWJian Wang
Jian Wang
GCGuangsheng Chen
Guangsheng Chen
Mahmoud EmamMahmoud Emam
Mahmoud Emam
The semantic segmentation of high-resolution remote sensing images (HRRSIs) is a basic task for remote sensing image processing and has a wide range of applications. However, the abundant texture information and wide imaging range of HRRSIs lead to the complex distribution of ground objects and unclear boundaries, which bring huge challenges to the segmentation of HRRSIs. To solve this problem, in this paper we propose an improved squeeze and excitation residual network (SERNet), which integrates several squeeze and excitation residual modules (SERMs) and a refine attention module (RAM). The SERM can recalibrate feature responses adaptively by modeling the long-range dependencies in the channel and spatial dimensions, which enables effective information to be transmitted between the shallow and deep layers. The RAM pays attention to global features that are beneficial to segmentation results. Furthermore, the ISPRS datasets were processed to focus on the segmentation of vegetation categories and introduce Digital Surface Model (DSM) images to learn and integrate features to improve the segmentation accuracy of surface vegetation, which has certain prospects in the field of forestry applications. We conduct a set of comparative experiments on ISPRS Vaihingen and Potsdam datasets. The results verify the superior performance of the proposed SERNet.

21 February 2022 in Remote Sensing
Verified
Journal Article
Open access
PDF file
WJWeipeng Jing
Weipeng Jing
WZWenjun Zhang
Wenjun Zhang
LLLinhui Li
Linhui Li
DDDonglin Di
Donglin Di
GCGuangsheng Chen
Guangsheng Chen
JWJian Wang
Jian Wang
Classification and segmentation of point clouds have attracted increasing attention in recent years. On the one hand, it is difficult to extract local features with geometric information. On the other hand, how to select more important features correctly also brings challenges to the research. Therefore, the main challenge in classifying and segmenting the point clouds is how to locate the attentional region. To tackle this challenge, we propose a graph-based neural network with an attention pooling strategy (AGNet). In particular, local feature information can be extracted by constructing a topological structure. Compared to existing methods, AGNet can better extract the spatial information with different distances, and the attentional pooling strategy is capable of selecting the most important features of the topological structure. Therefore, our model can aggregate more information to better represent different point cloud features. We conducted extensive experiments on challenging benchmark datasets including ModelNet40 for object classification, as well as ShapeNet Part and S3DIS for segmentation. Both the quantitative and qualitative experiments demonstrated a consistent advantage for the tasks of point set classification and segmentation.

13 July 2022 in Big Earth Data
Verified
Journal Article
Open access
SWShuang Wang
Shuang Wang
JWJian Wang
Jian Wang
QZQin Zhan
Qin Zhan
LZLianchong Zhang
Lianchong Zhang
Xiaochuang YaoXiaochuang Yao
Xiaochuang Yao
Guoqing LiGuoqing Li
Guoqing Li
Unified representation of spatial earth data is an essential scientific issue. The analysis and mining of interdisciplinary spatial earth data resources can help discover hidden scientific knowledge, and even reveal the intrinsic relationship among different disciplines. However, the different description methods and inner structures among interdisciplinary spatial earth data bring significant challenges to unified data management and collaborative analysis in earth environment research. To address this issue, this paper proposes a unified representation method for interdisciplinary spatial earth data. First, this paper establishes a general metadata model and realizes the unified description of interdisciplinary data. Second, an entity data organization model is presented, which can realize the unified organization of entity data with different inner structures. Finally, we introduce the Spatial Earth Data Format (SEDF), a data format based on HDF5 for implementing the data organization model of interdisciplinary spatial earth data. Data representation experiments and validation are conducted to verify the availability and practicability of the proposed data representation method. The results suggest the powerful ability to represent spatial earth data efficiently and ensure data integrity, which is convenient for data management and application.

13 June 2022 in Remote Sensing
Verified
Journal Article
Open access
PDF file
WJWeipeng Jing
Weipeng Jing
SZSongyu Zhu
Songyu Zhu
PKPeilun Kang
Peilun Kang
JWJian Wang
Jian Wang
SCShengjia Cui
Shengjia Cui
Houbing Herbert SongHoubing Herbert Song
Houbing Herbert Song
With the development of big data, analyzing the environmental benefits of transportation systems by artificial intelligence has become a hot issue in recent years. The ground traffic changes can be overlooked from a high-altitude perspective, using the technology of multi-temporal remote sensing change detection. We proposed a novel unsupervised algorithm by combining the image transformation and deep learning method. The new algorithm for remote sensing images is named multi-attention slow feature analysis (ASFA). In this model, three parts perform different functions respectively. The first part records to the K-BoVW to classify the categories of the ground objects as a channel parameter. The second part is a residual convolution with multiple attention mechanisms including temporal, spatial, and channel attention. Feature extraction and updating are completed at this link. Finally, we put the updated features in the slow feature analysis to highlight the variant components which we want and then generate the change map visually. Experiments on three very high-resolution datasets verified that the ASFA has a better performance than four basic change detection algorithms and an improved SFA algorithm. More importantly, this model works well for traffic road detection and helps us analyze the environmental benefits of traffic changes.

6 May 2021 in Concurrency and Computation: Practice and Experience
Verified
Journal Article
Closed access
PDF file
FHFang Huang
Fang Huang
HYHao Yang
Hao Yang
JTJian Tao
Jian Tao
JWJian Wang
Jian Wang
XTXicheng Tan
Xicheng Tan