A New Compression Sensing Reconstruction Method for Stitching Images Based on Deformable Convolution-Deformable Deconvolution Module

Authors

  • Jinwang Cha College of Information Technology, Nanchang Vocational University, Nanchang, China
  • Xing Hu College of Information Technology, Nanchang Vocational University, Nanchang, China
  • Li Xiao College of Information Technology, Nanchang Vocational University, Nanchang, China
  • Wen Xiong CCCC Mechanical and Electrical Engineering Bureau Co., Ltd.Wuhan Design Institute Branch, Wuhan, China
  • Qingru Guo Product Development Department, Googosoft, Jinan, China
  • Hongsheng Tian State Grid Tieling Electric Power Supply Company, Liaoning, China
  • Jiapeng Zhu College of Information Technology, Nanchang Vocational University, Nanchang, China
  • Mengsheng Wang College of Information Technology, Nanchang Vocational University, Nanchang, China
  • Hui Zhang College of Information Technology, Nanchang Vocational University, Nanchang, China
  • Jie Ren College of Information Technology, Nanchang Vocational University, Nanchang, China
  • Xinjian Li College of Information Technology, Nanchang Vocational University, Nanchang, China
  • Cheng Shao School of Control Science and Engineering, Dalian University of Technology, Dalian, China
  • Yi An School of Control Science and Engineering, Dalian University of Technology, Dalian, China
  • Ruifeng Pan College of Information Technology, Nanchang Vocational University, Nanchang, China
  • Jian Zheng College of Information Technology, Nanchang Vocational University, Nanchang, China
  • Cheng Pan College of Information Technology, Nanchang Vocational University, Nanchang, China
  • Juan Xie College of Information Technology, Nanchang Vocational University, Nanchang, China
  • Minqin Fan School of Economics and Management, Nanchang Vocational University, Nanchang, China
  • Shiming Chen Big bore material forming center, Weichai Heavy Machinery Co., Ltd., Weifang, China

Keywords:

Compression sensing reconstruction, Image stitching, Deformable convolution, SCNet

Abstract

The compression sensing reconstruction of the stitching image is important for the communication of autonomous driving, intelligent vehicles, and unmanned aerial vehicles (UAV). A compression sensing reconstruction method for the stitching image is proposed. The proposed compression sensing reconstruction method contain: image stitching method, deformable convolution module, SCNet, and deformable deconvolution module. The added deformable convolution module can extract the features of the stitching image reasonably due to image distortion. The added deformable deconvolution module can make the stitching image and the reconstructed stitching image maintain consistency. Experimental results show the reconstruction SSIM and PSNR of the proposed method is better than the image stitching method and the SCNet. The reconstruction stitching images also has better visual effects.

Downloads

Published

2025-09-30

Issue

Vol. 95 No. 4 (2025): Volume 95, Issue 4

Section

Original Articles

How to Cite

Jinwang Cha, Xing Hu, Li Xiao, Wen Xiong, Qingru Guo, Hongsheng Tian, Jiapeng Zhu, et al. , trans. 2025. “A New Compression Sensing Reconstruction Method for Stitching Images Based on Deformable Convolution-Deformable Deconvolution Module”. Human Biology 95 (4): 1190-93. https://www.humbiol.org/Home/article/view/486.

Most read articles by the same author(s)

1 2 3 4 5 6 7 > >>