A Method of Weak and Small Target Detection Based on Hyperspectral Image

Abstract

A method for detecting weak and small targets based on hyperspectral images. The specific scheme is as follows. Step 1: Use the signal-to-clutter ratio to analyze the detectability of the target. The background has several spectral segments with the difference from large to small; Step 2: Extract weak and small targets in the spectral segment with the largest difference between the preferred target and the background, use the multi-structural element mathematical morphology method to suppress the background, and use the self-adaptive Threshold segmentation to obtain several suspected targets; Step 3: Using the spectral information of the optimal detection spectrum, the aliased spectra of the target and the background in different scenes are used as the standard spectrum when the target is located in different scenes, and based on the principle of spectral angle matching, calculate the suspected target and The similarity between the aliased spectrum of the background and the standard spectrum realizes the confirmation of weak and small targets. The invention belongs to the technical field of target detection and recognition, and can realize efficient confirmation of long-distance weak and small targets in complex environment backgrounds.

Description

technical field

[0001] The invention belongs to the technical field of target detection and recognition, and in particular relates to a method for detecting weak and small targets based on hyperspectral images. Background technique

[0002] High-probability detection of weak and small targets in complex cloud backgrounds has always been a key technology in the field of target detection and recognition. However, for the actual air target detection process, long-distance detection is usually required. After the target is imaged by the detection system, it generally lacks geometric shape, texture and other information. The environmental background of the non-target area, especially the complex and changeable cloud background will increase the difficulty of target detection, and with the development of aircraft stealth technology, the radiation intensity of the target itself is greatly reduced, making the target signal easily detected by complex clouds. The background drowns ou...

Examples

specific Embodiment approach 1

[0017] The invention provides a method for detecting weak and small targets based on hyperspectral images, such as figure 1 As shown, the specific implementation steps of the method are as follows:

[0018] Step 1: Use the signal-to-clutter ratio to analyze the detectability of the target. By calculating the signal-to-clutter ratio of the target in different spectral bands relative to its neighborhood background, select a number of spectral bands with the difference between the target and the background from large to small. Detect the spectrum segment; the specific steps are as follows:

[0019] (1) Based on the concept of target signal-to-clutter ratio in infrared images, consider the situation that different targets are located in different scenes in different flight states, and calculate the signal-to-clutter ratio and signal-to-clutter ratio of the target in the hyperspectral image for each situation relative to its neighborhood background defined as:

[0020]

[0021...

technical field

[0001] The invention belongs to the technical field of target detection and recognition, and in particular relates to a method for detecting weak and small targets based on hyperspectral images. Background technique

[0002] High-probability detection of weak and small targets in complex cloud backgrounds has always been a key technology in the field of target detection and recognition. However, for the actual air target detection process, long-distance detection is usually required. After the target is imaged by the detection system, it generally lacks geometric shape, texture and other information. The environmental background of the non-target area, especially the complex and changeable cloud background will increase the difficulty of target detection, and with the development of aircraft stealth technology, the radiation intensity of the target itself is greatly reduced, making the target signal easily detected by complex clouds. The background drowns ou...

Examples

specific Embodiment approach 1

[0017] The invention provides a method for detecting weak and small targets based on hyperspectral images, such as figure 1 As shown, the specific implementation steps of the method are as follows:

[0018] Step 1: Use the signal-to-clutter ratio to analyze the detectability of the target. By calculating the signal-to-clutter ratio of the target in different spectral bands relative to its neighborhood background, select a number of spectral bands with the difference between the target and the background from large to small. Detect the spectrum segment; the specific steps are as follows:

[0019] (1) Based on the concept of target signal-to-clutter ratio in infrared images, consider the situation that different targets are located in different scenes in different flight states, and calculate the signal-to-clutter ratio and signal-to-clutter ratio of the target in the hyperspectral image for each situation relative to its neighborhood background defined as:

[0020]

[0021...

Images