Jun Wang

Dr. Jun Wang


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
24 November 2022 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
JWJun Wang
Jun Wang
TZTianchen Zhao
Tianchen Zhao
XJXiaoliang Jiang
Xiaoliang Jiang
KLKun Lan
Kun Lan
This letter presents a novel graph-driven synthetic aperture radar (SAR) image change detection approach. A hierarchical heterogeneous graph is proposed, combining two distinct graphs: a weighted graph based on adjacency of superpixels of an initial over-segmentation, and the dual-weighted heterogeneous graph. The superpixel-based regional affinities are coupled with pixel-based heterogeneous affinities, being embedded into the structure of hierarchical heterogeneous graph. The difference image generation relies on the matching of the bitemporal graphs, as well as the multiscale features of vertex domain. Finally, traditional graph cuts algorithm is applied to separate the difference image into changed and unchanged areas. Experiments on three real SAR datasets show that the proposed approach outperforms other experimental approaches and is a good candidate for SAR image change detection tasks.

24 May 2024 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
JWJun Wang
Jun Wang
FZFei Zeng
Fei Zeng
SNSanku Niu
Sanku Niu
JZJun Zheng
Jun Zheng
XJXiaoliang Jiang
Xiaoliang Jiang
Synthetic aperture radar (SAR) image change detection is currently a popular topic, but the existence of speckle noise renders it challenging. Making full use of the neighborhood information can reduce noise interference and improve accuracy. To this end, this study proposes a graph-guided method for SAR image change detection. First, we establish the local, nonlocal and global connections according to three types of neighboring rules. A novel heterogeneous graph is then constructed by assigning different weights to these multi-level connections. On the basic of heterogeneous graph, a composite random walk matrix (CRWM) is presented to quantify the similarity of multi-level connections. Thereafter, the heterogeneous graph shift system consisting of the multi-order CRWM is designed to aggregate the attributes of neighboring vertices along the multi-order and multi-level connections. The change measure can be implemented by comparing the output signals from the heterogeneous graph shift systems, resulting in the generation of difference image with good separability. Finally, change analysis is carried out using binary classification algorithm. Experiments conducted on six real SAR datasets confirm that the proposed M2HG method successfully strikes a balance between speckle suppression and change enhancement. This strategic balance translates into improve-ments in performance metrics, with OA, κ and F1 indicators surpassing those of the sub-optimal method by 0.87%, 3.34%, and 3.84%, respectively. Overall, the proposed method emerges as a promising contender for SAR image change detection tasks.

20 January 2023 in Remote Sensing
Verified
Journal Article
Open access
PDF file
XYXiangyu Yang
Xiangyu Yang
Xuezhi YangXuezhi Yang
Xuezhi Yang
CZChunju Zhang
Chunju Zhang
JWJun Wang
Jun Wang
Classification algorithms integrated with convolutional neural networks (CNN) display high accuracies in synthetic aperture radar (SAR) image classification. However, their consideration of spatial information is not comprehensive and effective, which causes poor performance in edges and complex regions. This paper proposes a Markov random field (MRF)-based algorithm for SAR image classification which fully considers the spatial constraints between superpixel regions. Firstly, the initialization of region labels is obtained by the CNN. Secondly, a probability field is constructed to improve the distribution of spatial relationships between adjacent superpixels. Thirdly, a novel region-level MRF is employed to classify the superpixels, which combines the intensity field and probability field in one framework. In our algorithm, the generation of superpixels reduces the misclassification at the pixel level, and region-level misclassification is rectified by the improvement of spatial description. Experimental results on simulated and real SAR images confirm the efficacy of the proposed algorithm for classification.

30 December 2021 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
JWJun Wang
Jun Wang
TZTianchen Zhao
Tianchen Zhao
XJXiaoliang Jiang
Xiaoliang Jiang
This letter proposes a novel graph-guided approach for unsupervised change detection between multi-look synthetic aperture radar (SAR) images. The dual-layer graph (DG) is proposed to combine both the intensity and texture attributes of an SAR image. It can not only preserve the characteristics of each attribute in the single layer, but also excavate the multiple affinities of attributes from different layers. With the support of DG, change measure is achieved through comparing the graphs based on the supra-adjacency matrix, thus generating the difference image with good separability. The final change detection results are obtained via a traditional binary classification algorithm. Experimental results on two real SAR datasets demonstrate the effectiveness of the proposed graph-guided approach in which DG and multiple affinities provide great contributions for improving the accuracy and robustness of change detection.

31 May 2025 in International Journal of Remote Sensing
Verified
Journal Article
Closed access
JWJun Wang
Jun Wang
QFQiongjun Fu
Qiongjun Fu
JLJiahui Li
Jiahui Li
SNSanku Niu
Sanku Niu
YZYaohui Zhu
Yaohui Zhu
PCPengle Cheng
Pengle Cheng

25 November 2024 in Neural Processing Letters
Verified
Journal Article
Open access
PDF file
LJLu Jia
Lu Jia
BSBinglin Su
Binglin Su
DXDu Xu
Du Xu
YWYewei Wang
Yewei Wang
JFJing Fang
Jing Fang
JWJun Wang
Jun Wang
As a ubiquitous on-policy reinforcement learning algorithm, proximal policy optimization (PPO) has achieved the state-of-the-art performance in both single-agent and cooperative multi-agent scenarios. However, it still suffers from the instability and inefficiency of the policy optimization with the non-strictly restricted likelihood-ratio in clipping strategy. In this work, we propose an activation likelihood-ratio (ALR) for solving this issue. The ALR is restricted by a tanh activation function, and it can be employed in multiple functional clipping strategies. The resulted ALR clipping strategy produces a smooth but precipitous objective curve, which can provide high policy update stationarity and efficiency. The ALR clipping strategy is incorporated into the PPO loss function, thus resulting in the method proximal policy optimization with activation likelihood-ratio (PPO-ALR). The rationality and superiority of the ALR-based target function are proved and analyzed. Moreover, experiments on the Pistonball cooperative multi-agent game show that PPO-ALR produces competitive and superior results compared with the standard PPO, PPO with rollback, and PPO smoothed algorithms, especially its high efficiency and success probability in searching optimal policies in multi-agent environments.