Method and device for detecting left article based on fusion algorithm

A technology of item detection and fusion algorithm, which is applied in the field of detection of legacy items based on fusion algorithm, can solve the problems that monitoring personnel are difficult to detect in time, difficult to find, insufficient accuracy and timeliness, etc.

CN113393482APending Publication Date: 2021-09-14INDUSTRIAL AND COMMERCIAL BANK OF CHINA
0 Cites 2 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Publication Date
2021-09-14

Smart Images

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

Abstract

The embodiment of the invention provides a method and device for detecting a left article based on a fusion algorithm, which can be used in the technical field of artificial intelligence, and the method comprises the steps: carrying out the target article discrimination processing of a plurality of obtained to-be-detected images and a difference part image of a preset background frame, and generating a target article discrimination result; if the target object judgment result is that the difference part image comprises the target object, obtaining a target image comprising the target object from the to-be-detected image; and according to the target image, subjecting the target article to left article discrimination processing, and outputting the left article detection result, so that the accuracy of the left article can be improved, the timeliness of left article detection can be ensured, and the left article can be retrieved for a client in time.
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 the technical field of artificial intelligence, and in particular to a fusion algorithm-based detection method and device for leftover items. Background technique

[0002] For business places such as banks, shopping malls, and catering, where there is a large flow of people, once a customer loses an item, it is difficult to find it, and the lost item is easily picked up by others and taken away illegally; Due to factors such as limited human resources, it is difficult for monitoring personnel to detect in time. In related technologies, detection methods based on background separation, detection methods based on dual background modeling, or target detection algorithms based on deep learning are usually used to automatically detect leftover items. The above methods have obvious deficiencies in terms of accuracy and timeliness. Contents of the invention

[0003] ...

Examples

Embodiment Construction

[0050] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0051] It should be noted that a fusion algorithm-based detection method and device for legacy items disclosed in this application can be used in the field of artificial intelligence technology, and can also be used in any field other than the field of artificial intelligence technology. The application fields of the algorithmic leftover object detection method and device are not limited.

[0052] In order to facilitate the understanding of the technical solut...