Aerial image defogging method based on nonlocal feature structure tensor by UAV cameras with three-channel RGB cameras

Abstract

.The application of unmanned aerial system (UAV) remote sensing technology as a unique means of spatial data collection in various fields is based on high-resolution images captured by UAVs. However, due to the influence of atmospheric water vapor, haze, and other factors, the quality of UAV aerial images is limited. Considering that the model-based image fogging method developed according to the dark channel theory is widely used, the image edge after fogging incurs a “halo” effect owing to the excessive coarseness of the transmission map. We take advantage of the nonlocal structure tensor of the image to better protect the important details of the image edge while removing noise. The images we used are obtained from the public multi real world fog image dataset. Experiment results demonstrate that the proposed method can effectively eliminate the halo effect that occurs at the edges of an image after demisting.

Landscape Image Defogging System Based on DCPA Algorithm Optimization

“…Sun group proposed a threechannel RGB unmanned aerial vehicle IDF method based on the non-local feature structure tensor, combined with the dark channel theory to build an IDF model, and used the image non-local tensor to protect the image edge information. The research findings denoted that this method could effectively avoid the halo effect [11]. The DCP defogging algorithm relied on the AS model for defogging processing.…”

“…The image acquisition of the camera equipment includes target scene reflection imaging and natural or artificial light source projection imaging. In hazy weather, optical fiber scattering is serious, which reduces the clarity and contrast of imaging, leading to the loss of image information [11]. To improve the function of landscape image defogging (IDF), a system based on dark channel prior (DCP) algorithm was raised in this paper.…”