Image target detection method based on weak supervised learning

Abstract

The invention discloses an image target detection method based on weak supervised learning, and belongs to the technical field of machine vision. The method comprises the following steps: firstly, collecting an image data set, and training a constructed deep convolutional neural network model based on a multi-scale feature map by adopting a multi-example learning method; inputting an actual image,and extracting a category thermodynamic diagram of the actual image through the deep convolutional neural network model; and finally, outputting a bounding box of a target in the category thermodynamic diagram by adopting a binarization image connected region analysis method to obtain a target detection result. According to the method, an image target detection task is realized based on a weak supervised learning method. The target detection task can be completed only by using the image-level classification annotation information in annotation in convolutional neural network model training, which is different from the target bounding box annotation information required in the prior art, so that the work of manually annotating the target in the image is greatly reduced, and the completionof the image target detection task has more economic benefits.

Description

technical field [0001] The invention belongs to the technical field of neural networks, and in particular relates to an image target detection method based on weakly supervised learning. Background technique [0002] With the increasing application of deep learning in computer vision tasks, the current deep neural network models perform well in tasks such as image classification, object detection, and semantic segmentation. However, training models in supervised learning requires a large amount of manual labeling information. Information, especially position-related annotation, often consumes a lot of manpower and material resources, so weakly supervised learning methods that rely less on annotation information have become a research hotspot. Weakly supervised learning is a method of machine learning. Different from supervised learning models that require one-to-one correspondence between labels and model outputs, weakly supervised learning relies on labeling information tha...

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to: in order to solve the technical problem that the existing image target detection method based on deep learning is overly dependent on manual labeling, a deep convolutional neural network model based on multi-scale feature maps is designed to extract the category heat map of the generated image, based on The category heat map output by the model realizes the image target detection task, and proposes an image target detection method based on weakly supervised learning

Images