Chen ZHENG

Dr. Chen ZHENG


Research Focus & Metrics

Academic Career Length

20Years (2007-Present)

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

Representative Publications

View All Publications
17 February 2017 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
CZChen ZHENG
Chen ZHENG
YZYun Zhang
Yun Zhang
LWLeiguang Wang
Leiguang Wang
The Markov random field (MRF) model has attracted great attention in the field of image segmentation. However, most MRF-based methods fail to resolve segmentation misclassification problems for high spatial resolution remote sensing images due to insufficiently using the hierarchical semantic information. In order to solve such a problem, this paper proposes an object-based MRF model with auxiliary label fields that can capture more macro and detailed information and apply it to the semantic segmentation of high spatial resolution remote sensing images. Specifically, apart from the label field, two auxiliary label fields are first introduced into the proposed model for interpreting remote sensing images from different perspectives, which are implemented by setting a different number of auxiliary classes. Then, the multilevel logistic model is used to describe the interactions within each label field, and a conditional probability distribution is developed to model the interactions between label fields. A net context structure is established among them to model the interactions of classes within and between label fields. A principled probabilistic inference is suggested to solve the proposed model by iteratively renewing the label field and auxiliary label fields, in which different information of auxiliary label fields can be integrated into the label field during iterations. Experiments on different remote sensing images demonstrate that our model produces more accurate segmentation than the state-of-the-art MRF-based methods. If some prior information is added, the proposed model can produce accurate results even in complex areas.

11 March 2023 in Computers in Biology and Medicine
Verified
Journal Article
Closed access
LYLijun Yang
Lijun Yang
YWYixin Wang
Yixin Wang
XZXiangru Zhu
Xiangru Zhu
XYXiaohui Yang
Xiaohui Yang
CZChen ZHENG
Chen ZHENG

24 March 2023 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
CZChen ZHENG
Chen ZHENG
CHChen Hu
Chen Hu
YCYuncheng Chen
Yuncheng Chen
JLJingying Li
Jingying Li
Convolutional neural network (CNN) has been widely used in semantic segmentation for remote sensing images, and it has achieved great success. Due to the diversity of the spatial distribution of terrestrial objects in remote sensing images, it is difficult to effectively learn general geographical laws and apply them to a specific image. To introduce geographical knowledge into the CNN model more effectively, a self-learning-update CNN model (SLU-CNN) is proposed in this letter. It learns the representation of specific spatial dependence among different objects according to the CNN result, and then incorporates it with the CNN result to make semantic inference available. The proposed method mainly involves two modules. First, geographical objects generated from the CNN result are used as inference units. Second, the spatial dependence between inference units is learned to build a specific adaptive geographical relationship. And then, it is embedded as an adaptive penalty term into an object-based Markov random field model to achieve the collaboration between the CNN result and the semantic inference. Our method provides a general data-knowledge dual-driven framework for the deep neural network. Experiments of the GID and Sentinel-2 datasets validate the effectiveness of the proposed method by comparing it with different state-of-the-art CNN methods.

11 November 2020 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
CZChen ZHENG
Chen ZHENG
YZYun Zhang
Yun Zhang
LWLeiguang Wang
Leiguang Wang
Semantic segmentation is one of the most important tasks in remote sensing. However, as spatial resolution increases, distinguishing the homogeneity of each land class and the heterogeneity between different land classes are challenging. The Markov random field model (MRF) is a widely used method for semantic segmentation due to its effective spatial context description. To improve segmentation accuracy, some MRF-based methods extract more image information by constructing the probability graph with pixel or object granularity units, and some other methods interpret the image from different semantic perspectives by building multilayer semantic classes. However, these MRF-based methods fail to capture the relationship between different granularity features extracted from the image and hierarchical semantic classes that need to be interpreted. In this article, a new MRF-based method is proposed to incorporate the multigranularity information and the multilayer semantic classes together for semantic segmentation of remote sensing images. The proposed method develops a framework that builds a hybrid probability graph on both pixel and object granularities and defines a multiclass-layer label field with hierarchical semantic over the hybrid probability graph. A generative alternating granularity inference is suggested to provide the result by iteratively passing and updating information between different granularities and hierarchical semantics. The proposed method is tested on texture images, different remote sensing images obtained by the SPOT5, Gaofen-2, GeoEye, and aerial sensors, and Pavia University hyperspectral image. Experiments demonstrate that the proposed method shows a better segmentation performance than other state-of-the-art methods.

24 August 2017 in IET Image Processing
Verified
Journal Article
Open access
PDF file
XCXiaohui Chen
Xiaohui Chen
CZChen ZHENG
Chen ZHENG
HYHongtai Yao
Hongtai Yao
BWBingxue Wang
Bingxue Wang
Markov random field model (MRF) has attracted great attention in the field of image segmentation. Its basic unit can be pixels or regions. These pixel‐based or region‐based MRF models have their own advantages and disadvantages. In order to complement advantages of each other, a unified Markov random field (UMRF) model is proposed in this paper. The strength of the UMRF model lies in two aspects. First, the proposed model combines the benefits of the pixel‐based and the region‐based MRF models by decomposing the likelihood function into the product of the pixel likelihood function and the regional likelihood function. It can make the UMRF model take both pixel information and regional information into account. Second, a new regional feature is designed for the UMRF model to describe macro texture patterns. A principled probabilistic inference is developed to integrate different types of likelihood information and the spatial constraint by iteratively updating the posterior probability of the proposed model. Segmentation results can be achieved when iteration converges. Texture, remote sensing and nature images are employed to test the effectiveness of the proposed model. Experimental results illustrate that our model can achieve higher segmentation accuracy than either the pixel‐based or region‐based MRF models.

4 November 2021 in IEEE Signal Processing Letters
Verified
Journal Article
Closed access
JWJiaqi Wang
Jiaqi Wang
CZChen ZHENG
Chen ZHENG
XYXiaohui Yang
Xiaohui Yang
LYLijun Yang
Lijun Yang
Loss function is an important topic in the field of face recognition, while the margin-based loss function is one of the most useful methods to enhance discriminability. Recently, the method of dividing the samples into easy and hard ones effectively optimizes the margin-based loss function by emphasizing these two parts at different training stages. However, the hard samples contain not only intra-personal variations that can be easily misclassified but also wrong-labeled samples. To capture and distinguish their difference, an EnhanceFace method is proposed with a new adaptive weighted loss function in this letter to improve the accuracy of face recognition. Firstly, this method partitions the hard samples into semi-hard and harder samples. Then, a new loss function is developed to adaptively adjust corresponding weights for both semi-hard samples and harder samples during the training process. With this new loss function, their effects can be well balanced according to their importance. The EnhanceFace method is tested on different popular benchmarks. Finally, better performance is shown by the experimental results comparing with other state-of-the-art methods.