Fusion algorithm of UAV infrared image and visible image registration

Shi, Yonghua; Jiang, Xishun

doi:10.1007/s00500-021-05918-8

Cited by 4 publications

(2 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Image perception integrates and extracts two or more multi-source image information to obtain more accurate, comprehensive and reliable information about the same scene or target, making it more suitable for human eye perception or computer follow-up processing. According to the abstract degree of information processing in the fusion system, fusion perception algorithm can be divided into three levels in structure: data level fusion (pixel level fusion), feature level fusion and decision level fusion 18 .…”

Section: Image Fusion Perception Technology Based On Low-cost Uav Sen...mentioning

confidence: 99%

Overview of image fusion technology for low-cost UAVs perception system

Luo¹,

Bi²,

Xuan³

2023

Advanced Fiber Laser Conference (AFL2022)

View full text Add to dashboard Cite

With the gradual improvement of the autonomous capabilities of unmanned aerial vehicles (UAVs), the field of tasks has expanded, and it is necessary for UAVs to fully perceive target information from multiple levels and dimensions in the process of target detection and identification in the complex environment. Therefore, for UAVs, the main goal of fusion perception technology is to achieve resource interoperability and information complementarity between sensors, such as to increase the detection advantages of different image sensors in frequency, space, and time.In this paper, based on low-cost UAVs, the research is carried out from two aspects: UAVs and fusion perception sensors, and image-based fusion perception technology. The factors that need to be considered in UAVs' sensor configuration are analyzed from four aspects: UAVs' platform attributes, sensor attributes, flight environment, and task types and requirements. Then, we summarize the current image fusion perception technology in the process of UAVs' detection and identification, which provides an effective reference for product development and technology research in related fields.Finally, the challenges faced by the future development of fusion technology are proposed. The overview shows that, sensor configuration scheme and information fusion scheme have the relationship of mutual promotion and restriction in the process of searching for the optimal fusion strategy. It is necessary to develop heterogeneous information fusion algorithm based on sensor characteristics. Moreover, the level of precise sensing elements, efficient information acquisition algorithms, configuration schemes and fusion algorithm implementations are required to improve for the result of 1+1>2.

show abstract

Section: Image Fusion Perception Technology Based On Low-cost Uav Sen...mentioning

confidence: 99%

Overview of image fusion technology for low-cost UAVs perception system

Luo¹,

Bi²,

Xuan³

2023

Advanced Fiber Laser Conference (AFL2022)

View full text Add to dashboard Cite

show abstract

“…Fast adaptive bidimensional empirical mode decomposition (FABEMD) algorithm is implemented on the basis of BEMD algorithm [7], which can effectively improve the efficiency and complexity of BEMD algorithm. Based on the traditional image fusion algorithm, the color space IHS transform and lifting wavelet transform are combined according to the characteristics of UAV imaging equipment [8]. This algorithm not only keeps the brightness information of infrared target, but also has good robustness.…”

Section: Introductionmentioning

confidence: 99%

An adaptive infrared image denoising method based on two-dimensional empirical mode decomposition for distribution network inspection UAV

Zhou¹,

Yang²,

Liu³

et al. 2023

J. meas. eng.

View full text Add to dashboard Cite

An adaptive denoising method based on 2D empirical mode decomposition (EMD) is proposed to improve the infrared image quality of inspection UNMANNED aerial vehicles (UAVs) and provide guarantee for improving the inspection level of distribution network. Through rapid adaptive two-dimensional empirical mode decomposition algorithm decomposition of a UAV collected for distribution network inspection original noise of infrared image, get more than the IMF component and the residual amount, a forecast noise dominated the IMF component parameters such as threshold value and the variance of noise, using the estimated parameters in combination with the optimal linear interpolation algorithm of noise threshold function of leading the IMF component implementation of threshold denoising. After the denoised IMF component is obtained, the denoised infrared image is obtained after reconstruction with the signal-dominated IMF component, and the adaptive denoising of the infrared image of the distribution network inspection UAV is realized. The experimental results show that the method in this paper can maintain the details of the image, improve the definition, significantly improve the visual effect, the overall denoising performance is stable and feasible, and ensure the quality inspection UAV to collect infrared images.

show abstract