Penglei Xu

Mr. Penglei Xu


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
12 May 2021 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
PXPenglei Xu
Penglei Xu
THTang Hong
Tang Hong
JGJiayi Ge
Jiayi Ge
LFLin Feng
Lin Feng
Higher resolution building mapping from lower resolution remote sensing images is in great demand due to the lack of higher resolution data access, especially in the context of disaster assessment. High resolution building layout map is crucial for emergency rescue after the disaster. The emergency response time would be reduced if detailed building footprints were delineated from more easily available low-resolution data. To achieve this goal, we propose a super-resolution semantic segmentation network called ESPC_NASUnet, which consists of a feature super-resolution module and a semantic segmentation module. To the best of authors' knowledge, this is the first work to systematically explore a deep learning-based approach to generate semantic maps with higher spatial resolution from lower spatial resolution remote sensing images in an end-to-end fashion. The experimental results for two datasets suggest that the proposed network is the best among four different end-to-end architectures in terms of both pixel-level metrics and object-level metrics. In terms of pixel-level F1-score, the improvements are greater than 0.068 and 0.055. Regarding the object-level F1-score, the disparities between ESPC_NASUnet and other end-to-end methods are more than 0.083 and 0.161 in the two datasets, respectively. Compared with stage-wise methods, our end-to-end network is less impacted by low-resolution input images. Finally, the proposed network produces building semantic maps comparable to those generated by semantic segmentation networks trained with high-resolution images and the ground truth utilizing the two datasets.

11 June 2021 in Remote Sensing
Verified
Journal Article
Open access
PDF file
TZTao Zhang
Tao Zhang
THTang Hong
Tang Hong
YDYi Ding
Yi Ding
PLPenglong Li
Penglong Li
CJChao Ji
Chao Ji
PXPenglei Xu
Penglei Xu
Satellite mapping of buildings and built-up areas used to be delineated from high spatial resolution (e.g., meters or sub-meters) and middle spatial resolution (e.g., tens of meters or hundreds of meters) satellite images, respectively. To the best of our knowledge, it is important to explore a deep-learning approach to delineate high-resolution semantic maps of buildings from middle-resolution satellite images. The approach is termed as super-resolution semantic segmentation in this paper. Specifically, we design a neural network with integrated low-level image features of super-resolution and high-level semantic features of super-resolution, which is trained with Sentinel-2A images (i.e., 10 m) and higher-resolution semantic maps (i.e., 2.5 m). The network, based on super-resolution semantic segmentation features is called FSRSS-Net. In China, the 35 cities are partitioned into three groups, i.e., 19 cities for model training, four cities for quantitative testing and the other 12 cities for qualitative generalization ability analysis of the learned networks. A large-scale sample dataset is created and utilized to train and validate the performance of the FSRSS-Net, which includes 8597 training samples and 766 quantitative accuracy evaluation samples. Quantitative evaluation results show that: (1) based on the 10 m Sentinel-2A image, the FSRSS-Net can achieve super-resolution semantic segmentation and produce 2.5 m building recognition results, and there is little difference between the accuracy of 2.5 m results by FSRSS-Net and 10 m results by U-Net. More importantly, the 2.5 m building recognition results by FSRSS-Net have higher accuracy than the 2.5 m results by U-Net 10 m building recognition results interpolation up-sampling; (2) from the spatial visualization of the results, the building recognition results of 2.5 m are more precise than those of 10 m, and the outline of the building is better depicted. Qualitative analysis shows that: (1) the learned FSRSS-Net can be also well generalized to other cities that are far from training regions; (2) the FSRSS-Net can still achieve comparable results to the U-Net 2 m building recognition results, even when the U-Net is directly trained using both 2-meter resolution GF2 satellite images and corresponding semantic labels.

24 May 2021 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Open access
WHWei Huang
Wei Huang
THTang Hong
Tang Hong
PXPenglei Xu
Penglei Xu
It is an important task to automatically and accurately map rooftops from very high resolution remote sensing images since buildings are very closely related to human activity. Two typical technologies are often utilized to accomplish the task, i.e., semantic segmentation and instance segmentation. The semantic segmentation is to independently allocate a label (e.g., “building” or not) to each pixel, resulting in blob-like segments. On the contrary, one might model the boundary of a rooftop as a polygon to improve the shape of the rooftop by encouraging vertices of polygon to adhere to the rooftop’s boundary. Following this line of work, we present a multitask learning approach to predict rooftop corners in a sequent way using the attention learned from where the boundaries are in a given image region. The approach simulates the process of manual delineation of rooftops’ outline in a given image, which can produce accurate boundaries of rooftops with sharp corners and straight lines between them. Specifically, the proposed method consists of three components, i.e., object detection, pixel-by-pixel classification of both edges and corners, and delineation of rooftops in a sequent manner using a convolutional recurrent neural network (RNN). It is called as object-oriented, edges and corners (OEC)-RNN in this article. Three image datasets of buildings are employed to validate the performance of the OEC-RNN, which are compared with state-of-the-art methods for instance segmentation. The experimental results show that the OEC-RNN achieves the best performance in terms of overlay, boundary adherence, and vertex location between ground-truth and predicted polygons.