NVIDIA DeepStream 9.1 新增13个智能体技能，用自然语言就能让Claude Code帮你搭多摄像头视频分析，自动3D追踪，不再手动标定摄像头。
NVIDIA DeepStream 9.1新增13种智能体技能，允许Claude Code和Codex等编码智能体通过自然语言提示构建多摄像头视频分析管道。它引入Multi-View 3D Tracking（MV3DT），将各摄像头检测融合到共享3D世界并提供全局一致对象ID。AutoMagicCalib（AMC）功能自动完成摄像头标定，无需手动操作。该版本还支持JetPack 7.2，并统一了开源GitHub单仓库核心。
NVIDIA Released DeepStream 9.1: Bringing Agentic AI to Vision AI With 13 Skills and Multi-View 3D Tracking
NVIDIA DeepStream 9.1 introduces 13 agentic skills that let coding agents like Claude Code and Codex build multi-camera video analytics pipelines from natural-language prompts. Multi-View 3D Tracking (MV3DT) fuses per-camera detections into one shared 3D world with a globally consistent object ID, while AutoMagicCalib (AMC) removes manual camera calibration. The release also adds JetPack 7.2 support and a unified open-source GitHub monorepo. The post NVIDIA Released DeepStream 9.1: Bringing Agentic AI to Vision AI With 13 Skills and Multi-View 3D Tracking appeared first on MarkTechPost .