Infrared image target detection method based on deep transfer learning and extreme learning machine

Abstract

The invention relates to an infrared image target detection method based on deep transfer learning and an extreme learning machine. The infrared image target detection method comprises the following steps: training a visible light image target detection model, training on a visible light sample set D by using a maskrcnn two-stage multi-task detection architecture, inputting a mask mask into a neural network, and redefining a loss function of an overall network structure; based on a sample migration method, obtaining a data set of migration learning by expanding the distribution of a target domain, namely an infrared sample set T; based on a model migration method, taking a target detection model with high precision based on a visible light image as a pre-training model of the generated migration learning data set, and carrying out training by adopting the same framework as visible light target detection; adopting an extreme learning machine to replace a network full connection layer, so as to overcome the over-fitting phenomenon of small sample model migration training.

Description

technical field [0001] The invention belongs to the field of image detection and relates to an infrared image target detection method. Background technique [0002] At present, small sample learning is a research hotspot in deep learning. There are a large number of unlabeled images in the real world. The realization of detection tasks relies on a large amount of labeled data, which greatly increases the cost of time and money. There is a serious disadvantage in the traditional machine learning method: it is assumed that the training data and the test data obey the same data distribution, but this assumption is not satisfied in many cases, and it usually takes a lot of manpower and resources to relabel a large amount of data to meet the training requirements. It causes a waste of data; while transfer learning can extract and transfer knowledge from existing data to complete new learning tasks. As a branch of machine learning, the original intention of transfer learning is t...

AI Technical Summary

Problems solved by technology

There is a serious disadvantage in the traditional machine learning method: it is assumed that the training data and the test data obey the same data distribution, but this assumption is not satisfied in many cases, and it usually takes a lot of manpower and resources to relabel a large amount of data to meet the training requirements. It causes a waste of data; while transfer learning can extract and transfer knowledge from existing data to complete new learning tasks

Images