Target tracking methods, devices, equipment, and media based on dual-mode optoelectronic devices

CN116883451BActive Publication Date: 2026-05-26TSINGHUA UNIVERSITY
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
TSINGHUA UNIVERSITY
Filing Date
2023-05-25
Publication Date
2026-05-26

AI Technical Summary

Technical Problem

In existing technologies, target localization suffers from low information transmission timeliness, high energy consumption, complex manufacturing processes, and difficulty in achieving collaborative integration of multifunctional and multimodal devices due to the separation of sensors, memory, and processors.

Method used

By employing dual-mode optoelectronic devices, combining non-volatile and volatile modes, target tracking is achieved through template memory and dynamic video image extraction. The non-volatile mode is used for template memory, while the volatile mode is used for dynamic video image extraction, and similarity matching is performed to generate target tracking results.

Benefits of technology

It improves processing timeliness, simplifies preparation process, achieves multi-functional integration, and reduces redundant information exchange.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN116883451B_ABST
    Figure CN116883451B_ABST
Patent Text Reader

Abstract

This application relates to a target tracking method, apparatus, device, and medium based on a dual-mode optoelectronic device. The dual-mode optoelectronic device includes a non-volatile mode and a volatile mode. The method includes: using the non-volatile mode of the dual-mode optoelectronic device to memorize a template of the pixel region of the target to be tracked, obtaining a template of the target; using the volatile mode of the dual-mode optoelectronic device to extract a dynamic video image of the target to be tracked, obtaining a dynamic scene image of the target; performing similarity matching between the template of the target to be tracked and the dynamic scene image of the target, and generating a target tracking result based on the region corresponding to the maximum similarity. This solves the problems of low information transmission timeliness, high energy consumption, and complex fabrication processes in related technologies due to the separation of sensors, memory, and processors in target localization. It reduces redundant information exchange, improves processing timeliness, simplifies the fabrication process, and facilitates multi-functional integration.
Need to check novelty before this filing date? Find Prior Art