A method, device, terminal device and storage medium for identifying a falling object
A recognition method and object technology, applied in character and pattern recognition, image analysis, image enhancement, etc., can solve the problems of high labor cost, distraction, etc., and achieve low false positive detection rate, high robustness and universality Applicability, improvement of monitoring efficiency and effectiveness of monitoring timeliness
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0031] Figure 1A It is a flow chart of a method for identifying a falling object provided by Embodiment 1 of the present invention. This embodiment is applicable to monitoring whether there is a falling object in a surveillance video. recognition device, which can be implemented by software and / or hardware, and integrated in the monitoring camera component or a management control device (for example, server, edge computing device) connected to the monitoring camera component, the method specifically includes the following steps:
[0032] S110. Obtain the video image frame of the surveillance video, and perform background difference with the background image frame to obtain a plurality of binarized marked image frames, and obtain the moving track image frame of the motion area according to each of the binarized marked image frames .
[0033] Surveillance video can be obtained through surveillance camera components installed in front of buildings, such as Figure 1B As shown, ...
Embodiment 2
[0049] figure 2 It is a flow chart of a falling object recognition method provided by Embodiment 2 of the present invention. This embodiment is embodied on the basis of the above embodiments. In this embodiment, when each binarization within the preset detection time When the marked image frames all include motion areas, it is judged that there is a suspicious falling object in the surveillance video, and then the image classification model is used to further determine whether it is a falling object. The method specifically includes:
[0050] S210. Acquire a video image frame of the surveillance video, and perform background difference with the background image frame to obtain a plurality of binarized marked image frames.
[0051] S220. If it is determined that each of the binarized marked image frames within the preset detection time includes a motion area, then determine the first binarized marked image frame within the preset detection time as the motion start frame, and ...
Embodiment 3
[0061] image 3 It is a structural block diagram of a device for identifying a falling object provided in Embodiment 3 of the present invention, and the device specifically includes: a moving trajectory acquisition module 310, a trajectory classification execution module 320, and a falling object determination module 330;
[0062] The movement trajectory acquisition module 310 is used to acquire video image frames of the surveillance video, and perform background difference with the background image frames to obtain a plurality of binarized marked image frames, and obtain motion The moving track image frame of the region;
[0063] The track classification execution module 320 is used to input the moving track image frame of the moving area into the trained image classification model, so as to judge whether the moving track of the moving area is a falling object track through the image classification model;
[0064] The falling object determination module 330 is configured to ...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com