Object detection model training method and target object detection method

Abstract

The invention relates to a target object detection method and device, a computer readable storage medium and computer equipment. The method comprises the steps that acquiring a to-be-detected image; inputting the to-be-detected image into the target object detection model, wherein the target object detection model is obtained by carrying out parameter adjustment on an initial object detection model through training a loss value; wherein the training loss value is obtained through calculation according to target pixel points determined by a first area and a second area, and the first area and the second area are obtained through determination according to the position of the sample mass center of a target type object in the training sample image; generating a prediction graph correspondingto the to-be-detected image by the target object detection model, wherein the prediction graph describes the relation degree of each pixel point of the to-be-detected image belonging to the target detection object; and carrying out region segmentation on the prediction image to obtain a target detection object region. In addition, the invention further provides an object detection model training method and device, a computer readable storage medium and computer equipment.

Description

technical field [0001] The present application relates to the field of computer technology, in particular to an object detection model training method, device, computer-readable storage medium and computer equipment, and a target object detection method, device, computer-readable storage medium and computer equipment. Background technique [0002] In the traditional technology, the training samples of the object detection model require the annotator to accurately mark the training target object area in the training sample, so that they can be used as the training samples of the object detection model for training, so that the finally trained target object detection model can achieve the highest effect. However, this method of accurately labeling the training target object area in the training samples requires a lot of labor costs and a lot of time for the labelers, and the labeling results are also easily affected by the labelers, which leads to the final training The predi...

AI Technical Summary

Problems solved by technology

However, this method of accurately labeling the training target object area in the training samples requires a lot of labor costs and a lot of time for the labelers, and the labeling results are also easily affected by the labelers, which leads to the final training The prediction accuracy of the target object detection model is low

Images