Image target detection method and device, terminal equipment and storage medium

A detection method and target detection technology, applied in the field of image processing, can solve problems such as prone to false detection, missed detection, and difficulty in obtaining a large amount of rich image data to train detection models, so as to avoid false detection and missed detection and improve detection efficiency Effect

CN111242234APending Publication Date: 2020-06-05SHENZHEN ZTE NETVIEW TECH +1
4 Cites 4 Cited by

Patent Information

Authority / Receiving Office
CN · China
Current Assignee / Owner
Publication Date
2020-06-05

Smart Images

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

Abstract

The invention discloses an image target detection method and device, terminal equipment and a computer readable storage medium, and the method comprises the steps: marking a label of a to-be-detectedtarget in a target sample image containing the to-be-detected target; constructing each training sample image according to the target sample image marked with the label and the scene sample image of each scene field, each scene sample image not containing the to-be-detected target; inputting each training sample image into a preset target detection model for model training, and detecting an imagetarget in the to-be-detected image by using the trained preset target detection model. According to the invention, there is no need to spend a lot of manpower resources to collect image data in different scene fields and mark image targets; training sample images for model training of the target detection model are enriched, false detection and missing detection of the target detection model during subsequent image target detection are avoided, and the image target detection efficiency is improved.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The present invention relates to the technical field of image processing, in particular to a detection method, device, terminal equipment and computer-readable storage medium of an image target. Background technique

[0002] The detection of image objects is a very important field in the development of computer vision. Different from the problem of image classification, the detection of image objects not only needs to judge whether there is an object in a picture, but also needs to locate the detected image objects. Generally speaking, the image data requirement for training the detection model for image targets is that the richer the scene where the image target is located, the better, and the more image data, the better. However, in real scenarios, the acquisition of image data is often not It is easy, and it faces the problem of heavy image data labeling. In this way, it leads to the lack of sample data required for training the target detection mod...

Examples

Embodiment Construction

[0041] It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0042] In the following description, use of suffixes such as 'module', 'part' or 'unit' for denoting elements is only for facilitating description of the present invention and has no specific meaning by itself. Therefore, 'module', 'part' or 'unit' may be used in combination.

[0043] Terminal devices may be implemented in various forms. For example, the terminal devices described in the present invention may include mobile phones, tablet computers, notebook computers, palmtop computers, personal digital assistants (Personal Digital Assistant, PDA), portable media players (Portable Media Player, PMP), navigation devices, portable Mobile terminals such as wearable devices, smart bracelets, and pedometers, and fixed terminals such as digital TVs and desktop computers.

[0044] In the following description, a mobile te...