Image target detection model training method and device based on consistency negative sample

A target detection and negative sample technology, applied in the field of image processing, can solve the problem that the model is difficult to learn discriminative features, and achieve the effect of enhancing the ability to distinguish

CN110969200AActive Publication Date: 2020-04-07INST OF AUTOMATION CHINESE ACAD OF SCI
3 Cites 6 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Publication Date
2020-04-07

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention relates to the technical field of image processing, in particular to an image target detection model training method and device based on consistency negative samples. In order to solve the problem that in the prior art, a fixed negative sample is adopted, so that a model difficultly learns features with discrimination force, the invention provides an image target detection model training method, which comprises the steps of obtaining an initial image sample set based on the overlapping degree of a real frame in a to-be-identified image and a preset initial anchor frame; accordingto the initial image sample set, through a preset image target detection model, obtaining the prediction anchor frame corresponding to the initial anchor frame, and based on the overlapping degree ofthe real frame and the prediction anchor frame, obtaining an updated image sample set; and training the image target detection model through the updated image sample set. By using the method and thedevice of the invention, the image target detection model can be trained by using more comprehensive information.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the technical field of image processing, in particular to a method and device for training an image target detection model based on consistent negative samples. Background technique

[0002] Target detection is to predict the position of all target objects in the image, mark the position of the target object with a rectangular frame, and predict the category of the object in the rectangular frame. At present, most of the robust and efficient methods are based on convolutional neural networks, and the method based on anchor boxes is often used, that is, the anchor boxes are evenly spread on the image at a certain interval in advance. During the prediction process, the model regresses the prior anchor boxes, so that Their shape and position gradually approach the foreground object, and the model predicts the category of the object in the frame to complete the target detection.

[0003] In order to supervise the training of the m...

Examples

Embodiment Construction

[0056] In order to make the embodiments, technical solutions and advantages of the present invention more obvious, the technical solutions of the present invention will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of them. Example. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the present invention, and are not intended to limit the protection scope of the present invention.

[0057] Such as figure 1 as shown, figure 1 It exemplarily shows a schematic flowchart of the method for training an image object detection model based on consistent negative samples in this application. The image target detection model training method based on consistent negative samples of the present application includes the following steps:

[0058] Step S101 , based on the degree of ov...