A method of object detection based on fully automatic learning

Abstract

The invention discloses a target detection method based on fully automatic learning. The method includes: using a preprocessed small-scale manual labeling data set, using a deep neural network to train a model, and using a model trained in an Imagenet data set to perform Fine-tune and obtain the depth model; use the depth model to reason and predict the pseudo-labeled part of the original large-scale image dataset, remove the repeated prediction of the same target after non-maximum suppression, and store the bounding box and its confidence of the prediction result by category Degree; Through self-supervised pseudo-labeling and active learning sample selection, jointly learn the information entropy and divergence degree predicted by the deep neural network, sort the unlabeled samples according to the weight, and assign the pseudo-label to the top-ranked high-confidence samples. The purpose of the present invention is to solve the problems of high manpower cost for common target detection and labeling and poor transferability and adaptability of training models in actual scenarios.

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