3 个仓库
Awesome GitHub RepositoriesVisual Stream Processing
Low-latency analysis and processing of sequential video frames.
Distinct from Real-Time Streaming: Focuses on the processing/analysis of visual frames rather than just the streaming I/O of the multimodal agent
Explore 3 awesome GitHub repositories matching artificial intelligence & ml · Visual Stream Processing. Refine with filters or upvote what's useful.
Awesome Visual Stream Processing GitHub Repositories
用 AI 发现最棒的仓库。我们将通过 AI 为您搜索最匹配的仓库。
- zhkkke/modnet
ZHKKKe/MODNet
4,331在 GitHub 上查看MODNet 是一个深度学习图像分割和人像抠图模型，旨在将人物主体从背景中分离出来。它仅使用标准 RGB 输入即可为图像和视频生成高质量的 Alpha 遮罩，消除了对手动三元图（trimap）引导的需求。 该框架针对实时推理进行了优化，并提供了将预训练模型权重导出为特定格式以部署在目标硬件上的实用工具。 该项目涵盖了人像分离的完整工作流，包括在标记数据集上进行监督式抠图模型训练、实时视频背景移除以及边缘硬件部署。
Analyzes video frames sequentially with low latency to maintain consistent subject isolation during playback.
Pythonportrait-matting - basedhardware/openglass
BasedHardware/OpenGlass
4,069在 GitHub 上查看OpenGlass 是一个 AI 智能眼镜框架和微控制器硬件项目，旨在将标准眼镜变成计算机视觉可穿戴设备。它提供了一个将可穿戴摄像头传感器与多模态 AI 集成的系统，以实时处理视觉数据。 该项目支持开发 AI 驱动的眼镜，可以识别人物和物体、翻译视觉文本并记录生活事件。它将现成的电子元件连接到移动软件和大语言模型进行视觉分析。 该系统涵盖了多种功能，包括实时视觉流处理和抬头显示投影。它利用基于微控制器的硬件接口、无线命令协议和移动应用编排的组合来管理可穿戴设备与基于云的视觉推理之间的数据流。
Processes real-time visual streams from a wearable camera for immediate AI analysis.
C - vincentqyw/image-matching-webui
Vincentqyw/image-matching-webui
1,283在 GitHub 上查看This project is a web-based platform designed for benchmarking, visualizing, and evaluating computer vision algorithms focused on image feature extraction and matching. It provides a unified interface to compare the performance and accuracy of different models by processing image pairs or live video streams. The system distinguishes itself through a modular architecture that allows users to define custom processing pipelines and register external algorithms via configuration files. It incorporates geometric verification techniques to refine visual data and improve the precision of detected co
Performs low-latency analysis and feature matching on live video frames captured from connected webcams.
Pythonaspanformerdeep-learningfeature-matching
