Target duplicate removal method and device, electronic equipment and storage medium
A target and new target technology, applied in the field of target deduplication methods, devices, electronic equipment and storage media, to achieve the optimal effect of the target
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0026] figure 1 It is a flow chart of the object deduplication method provided by Embodiment 1 of the present invention. This embodiment can be applied to the situation of analyzing video streams, for example, it is applied to the situation of querying valuable video clips from surveillance videos. This method can be used by the target The deduplication device may be implemented by means of software and / or hardware, and may be integrated on electronic equipment, for example, on a server or computer equipment.
[0027] Such as figure 1 As shown, the target deduplication method specifically includes:
[0028] S101. Acquire any two temporally adjacent first slice video and second slice video.
[0029] Wherein, there is a pre-marked first marked time period at the end of the first slice video, and a pre-marked second marked time period at the beginning of the second slice video, and the first marked time period and the second marked time period overlap . Exemplarily, the first...
Embodiment 2
[0054] Figure 2a It is a schematic flow chart of the target deduplication method in the embodiment of this application. This embodiment is optimized on the basis of the above embodiments. See Figure 2a , the method specifically includes:
[0055] S201. Obtain a video to be divided.
[0056] Exemplarily, a 1-hour surveillance video (for example, 10:00-11:00) is used as the video to be divided. According to the picture of the live video surveillance, set the time to normally track a target as n seconds, and overlap according to n seconds, that is, it is necessary to ensure that the overlapping duration of any two slices in adjacent time series after segmentation is n seconds, where , The value of n can be adjusted according to different monitoring sites. It should be noted here that setting the time for normally tracking a target as the overlapping duration can ensure that a target can be completely tracked within the overlapping time period.
[0057] S202. Determine the n...
Embodiment 3
[0075] image 3 is a schematic structural view of the target weight removal device in Embodiment 3 of the present invention, such as image 3 As shown, the device includes:
[0076] The first acquiring module 301 is configured to acquire any two temporally adjacent first slice video and second slice video, wherein there is a pre-marked first calibration time period at the end of the first slice video, so There is a pre-marked second marked time period at the beginning of the second slice video, and the first marked time period overlaps with the second marked time period;
[0077] The calibration processing module 302 is configured to perform target detection and target tracking on the sub-slice video recordings in the first calibration time period and the sub-slice video recordings in the second calibration time period, and perform target detection and target tracking according to the target detection results and target tracking results. performing target calibration process...
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