Wenhao Pan

Mr. Wenhao Pan

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
22 April 2023 in Sensors
Verified
Journal Article
Open access
PDF file
JJJingjie Jiao
Jingjie Jiao
LZLixing Zhao
Lixing Zhao
WPWenhao Pan
Wenhao Pan
LXLi Xiaoyan
Li Xiaoyan
With the development of infrared detection and imaging technology, infrared cameras (IRCs) play an important role in many fields, such as military, industry, and civilian. Additionally, the requirements for the size, performance, and intelligence of IRCs are becoming more and more strict. Consequently, the associated research and development (R&D) of IRCs is gradually focused on the aspects of miniaturization, high performance, intelligence, low power consumption, and low cost, involving many frontier fields, including artificial intelligence, new materials, new optical systems, and electronics systems. In fact, there are continual studies on intelligent SWaP3 IRCs, but unfortunately, a systematic arrangement and analysis are lacking. Therefore, a systematical and comprehensive review for the developments and core technologies of the intelligent SWaP3 IRCs is really needed. In this paper, in terms of the aforementioned requirements, we conduct a review and analysis of current intelligent SWaP3 IRCs based on 90 literature and statistics in recent decades to provide the relevant developers with a helpful reference for facilitating the indicator optimization of intelligent SWaP3 IRCs with new developed technologies. We analyze the development of SWaP3 IRCs in the aspects of lightweight, miniaturization, low price, and high performance, including hyperspectral resolution, high spatial resolution, large field of view (FOV), and wide dynamic elaborately. Moreover, the development in low power consumption and intelligence is also discussed in detail. Additionally, we briefly summarize the primary applications of intelligent SWaP3 IRCs in military, scientific, and civil. Then, the core technologies comprising high-integration, lightweight, hyperspectral imaging (HSI), low-power consumption, as well as the realization of high performance such as high-resolution, high-frame, and wide-dynamic range of SWaP3 IRCs are discussed and analyzed in detail. Finally, we prospect for the intelligent SWaP3 IRCs that it is necessary to continuously expand the concept of SWaP3 by reliability, stability, extensibility, and safety. In addition, it is useful to embed cutting-edge technologies such as small pixel pitch array, multi-sensors fusion, and deploy intelligent algorithms to IRCs. Additionally, the improvement of the whole machine from multi-dimension such as chip, camera, and system is expected and needs to be taken more seriously. It is hoped that this paper can provide a reference for the R&D of intelligent SWaP3 IRCs in the future.

18 May 2023 in Remote Sensing
Verified
Journal Article
Open access
PDF file
LZLixing Zhao
Lixing Zhao
JJJingjie Jiao
Jingjie Jiao
LXLi Xiaoyan
Li Xiaoyan
WPWenhao Pan
Wenhao Pan
FZFanjun Zeng
Fanjun Zeng
Fansheng ChenFansheng Chen
Fansheng Chen
Ground Control Points (GCPs) are of great significance for applications involving the registration and fusion of heterologous remote sensing images (RSIs). However, utilizing low-level information rather than deep features, traditional methods based on intensity and local image features turn out to be unsuitable for heterologous RSIs because of the large nonlinear radiation difference (NRD), inconsistent resolutions, and geometric distortions. Additionally, the limitations of current heterologous datasets and existing deep-learning-based methods make it difficult to obtain enough precision GCPs from different kinds of heterologous RSIs, especially for thermal infrared (TIR) images that present low spatial resolution and poor contrast. In this paper, to address the problems above, we propose a convolutional neural network-based (CNN-based) layer-adaptive GCPs extraction method for TIR RSIs. Particularly, the constructed feature extraction network is comprised of basic and layer-adaptive modules. The former is used to achieve the coarse extraction, and the latter is designed to obtain high-accuracy GCPs by adaptively updating the layers in the module to capture the fine communal homogenous features of the heterologous RSIs until the GCP precision meets the preset threshold. Experimental results evaluated on TIR images of SDGSAT-1 TIS and near infrared (NIR), short wave infrared (SWIR), and panchromatic (PAN) images of Landsat-8 OLI show that the matching root-mean-square error (RMSE) of TIS images with SWIR and NIR images could reach 0.8 pixels and an even much higher accuracy of 0.1 pixels could be reached between TIS and PAN images, which performs better than those of the traditional methods, such as SIFT, RIFT, and the CNN-based method like D2-Net.