Regional deformation target detection method and system based on online learning

Abstract

The invention discloses a regional deformation target detection method and system based on online learning. The regional deformation target detection method based on the online learning comprises the following steps: firstly, a sample image is utilized to intensively train a regional deformation target detection model, and the regional deformation target detection model after preliminary training is obtained; secondly, the regional deformation target detection model is utilized to carry out target detection on an image to be detected, and the existing regional deformation target detection model is renewed and optimized by utilizing a GUI label online learning method. The regional deformation target detection method distributes the entire time-consuming training process in each time of target detection, meanwhile, the model can be renewed in real time, the robustness of the regional deformation target detection model is further improved, and the required inner storage is not large. According to the regional deformation target detection method, the data used for the target detection can be effectively and rapidly processed in the background of big data.

Description

technical field [0001] The invention relates to the field of pattern recognition and machine learning, in particular to a method and system for detecting locally deformable targets based on online learning. Background technique [0002] The traditional target detection is to use the features extracted from the image, use the support vector machine for training to obtain a target detection model, and then use the trained target detection model for detection. This method is feasible when the model is not very complex, there are not many training samples, and the real-time requirements are not high. In the context of large-scale data, the training data is very large and is collected successively. Every time a new data set is collected, if you want to update the model, you need to label the new training data, and then retrain after merging the previous training data with the new training data. This not only complicates the labeling operation process, but also takes time to ret...

AI Technical Summary

Problems solved by technology

[0005] In order to solve the deficiencies of traditional target detection methods in processing training data under the background of large-scale data, such as poor model robustness, complex labeling, slow training speed, large memory usage, inconvenient operation, and inability to update in real time, the present invention provides A local deformable object detection method and system based on online learning

Images