Target detection method based on full-automatic learning

Abstract

The invention discloses a target detection method based on full-automatic learning. The method comprises the following steps: carrying out the training of a model through employing a small-scale manual labeling data set after preprocessing and a deep neural network, carrying out the fine adjustment of the model trained through an Imagenet data set, and obtaining a deep model; carrying out reasoning prediction on the pseudo-labeled part of the original large-scale image data set by utilizing the deep model, removing repeated prediction of the same target after carrying out non-maximum suppression, and respectively storing bounding boxes and confidence of prediction results according to categories. Through self-supervised pseudo labeling and active learning sample selection, the informationentropy and the divergence degree predicted by the deep neural network are learned in a combined manner, unlabeled samples are sorted according to the weight, and pseudo labels are allocated to high-confidence samples ranked at the top. The objective of the invention is to solve the problems of too high labor cost of common target detection and labeling and poor mobility and adaptability of a training model in an actual scene.

Description

technical field [0001] The invention relates to the field of target detection, in particular to a target detection method based on fully automatic learning. Background technique [0002] With the maturity of deep learning and computer vision technology, the use of deep learning to judge the object category, position, and size information contained in the picture—that is, target detection has begun to develop on a large scale. The common target detection workflow is as follows: First, use manually collected image data sets or image data on the network to manually label and construct a data set; secondly, use commonly used target detection algorithms such as Faster-RCNN, YOLO and other training data sets, Get the required model; then, put the model and forward reasoning algorithm on the deployment end or cloud, judge the object category and position contained in the image in the required scene, and get the image information. [0003] However, this workflow has the following p...

AI Technical Summary

Problems solved by technology

[0007] The present invention provides a target detection method based on fully automatic learning. The purpose of the present invention is to solve the problems of high manpower costs for common target detection and labeling and poor transferability and adaptability of training models in actual scenarios. See the following description for details:

Images