Hyperspectral target detection method based on multi-example twin network

Abstract

The invention discloses a hyperspectral target detection method based on a multi-example twin network, and mainly solves the problem that in the prior art, when a hyperspectral data target is insufficient, a model is easy to over-fit, so that the detection effect is reduced. According to the implementation scheme, the method comprises the following steps: 1, preparing a data set, and dividing'positive-negative 'and'positive-positive' sample pairs from a training set; 2, building a multi-example twin network formed by cascading a feature extraction module, a weight calculation module, a feature fusion module and a classifier in sequence; 3, setting training parameters, and iteratively training the multi-example twin network by using the sample pairs in the training set; and 4, performing single-point test on the test set data by using the trained multi-example twin network, and outputting the confidence of each pixel belonging to the target. The method improves the detection result when the hyperspectral data target is insufficient, reduces the overfitting phenomenon, and can be used for explosive detection and crop fine classification.

Description

technical field [0001] The invention belongs to the technical field of image processing, and further relates to a hyperspectral target detection method, which can be used for explosive detection and fine classification of crops. Background technique [0002] Due to the rich spatiotemporal information of hyperspectral images, it has been widely used in various fields such as explosive detection and fine classification of crops in recent years. However, due to the accuracy of the sensor, a pixel marked as an object in the hyperspectral image does not necessarily exist in the ground truth, but indicates that the object exists in a certain range of space including the pixel. In addition, because the background is complex and diverse, and the number of targets is much smaller than that of the background in most cases, it becomes difficult to detect targets in hyperspectral images. [0003] Multi-instance learning originated from drug activity detection. With its increasingly wid...

AI Technical Summary

Problems solved by technology

[0009] The above methods, combined with machine learning and deep learning technology, have improved performance compared with traditional methods, but these methods have higher requirements for data

However, hyperspectral data often has the problem of insufficient targets in the data, that is, the target to be detected rarely appears or even does not exist in the scene, which will lead to the problem of target imbalance in data allocation.

Using these data to train the model in the above method is prone to overfitting, resulting in a decline in detection performance

Images