一种基于事件信号驱动的低光视频目标分割方法
By constructing a low-light video target segmentation method based on event signals, and combining the high dynamic characteristics of event data and the motion characteristics of objects, the instability problem of video target segmentation under low light conditions is solved, higher segmentation accuracy and stability are achieved, and the application scope of video target segmentation technology is expanded.
CN118052985BActive Publication Date: 2026-07-17UNIV OF SCI & TECH OF CHINA
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- UNIV OF SCI & TECH OF CHINA
- Filing Date
- 2024-02-27
- Publication Date
- 2026-07-17
Smart Images
Figure CN118052985B_ABST
Abstract
本发明公开了一种基于事件信号驱动的低光视频目标分割方法，其步骤包括：1、准备低光场景下视频数据，目标掩码和对应的事件序列；2、构建低光视频目标分割模型；3、对构建的低光视频目标分割神经网络模型进行离线训练；4、利用训练好的模型在低光场景下预测掩码，以实现低光视频目标分割的目标。本发明通过利用事件数据驱动的方式，能提升低光场景下视频目标分割的效果，从而能生成准确的目标掩码。
Need to check novelty before this filing date? Find Prior Art