Infrared target detection method, device, equipment and medium based on multi-feature fusion
A multi-feature fusion and infrared target technology, which is applied in the field of infrared target detection, can solve the problems of less target feature information and low contrast of infrared images, and achieve the effects of fast calculation speed, stable detection results, and reduced false alarm rate
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0077] The current infrared image target detection method requires simple background, high signal-to-noise ratio of target imaging, and is greatly affected by noise and interference, which makes the false alarm rate of infrared target detection higher. New methods developed in recent years, such as methods based on neural networks, genetic algorithms, and deep learning, cannot effectively adapt to weak and small target detection, and because the algorithms are relatively complex and require high storage space, it is difficult to achieve engineering applications in terms of real-time performance. requirements. Infrared target detection methods with good performance, fast calculation speed and engineering application are still the goal pursued by the majority of scientific researchers.
[0078] In order to solve the above technical problems, various embodiments of the multi-feature fusion-based infrared target detection method of the present invention are proposed.
[0079] ref...
Embodiment 2
[0113] refer to Figure 6 ,Such as Figure 6 Shown is a structural block diagram of an infrared target detection device provided in this embodiment, and the device specifically includes:
[0114] The target acquiring module 10 is used to acquire the detection target image.
[0115] The global threshold segmentation module 30 is configured to perform global threshold segmentation on the detection target image to obtain a binarized image.
[0116] The connected domain marking module 40 is configured to perform connected domain marking on the binarized image to obtain candidate objects.
[0117] The feature extraction module 50 is used to perform feature extraction on each candidate target, and the features include target points, target mean value, target signal-to-noise ratio, shape ratio and diagonal local signal-to-noise ratio, and filter each feature channel to obtain each Feature component values of candidate targets.
[0118] The feature fusion module 60 is configured...
Embodiment approach
[0122] As an implementation manner, the global threshold segmentation module 30 performs global threshold segmentation on the detection target image specifically includes:
[0123] To calculate the mean value of the infrared image, the formula for calculating the segmentation threshold is
[0124] .
[0125] in, is the mean value of the background, k is a constant coefficient, and the binarization segmentation judgment condition is:
[0126] .
[0127] in, represents the segmented image, Indicates the image to be segmented, i represents the abscissa, and j represents the ordinate.
[0128] As an implementation manner, the connected domain marking module 40 performs connected domain marking on the binarized image specifically includes:
[0129] Mark the connected domains of 8 domains on the binarized image. In the marked image, the values in the respective regions of the candidate targets correspond to the numbers.
[0130] As an implementation manner, the featu...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com