bynvidia-ai-blueprints· 17 skills
Deploy and operate the RTVI-CV-3D microservice as MV3DT (MODE=mv3dt): per-camera DeepStream perception plus BEV Fusion over calibrated cameras. Supports the bundled sample dataset, custom video files, and RTSP streams, and chains to vss-generate-video-calibration when calibration is missing. Use vss-deploy-profile for the full warehouse blueprint and vss-deploy-detection-tracking-2d for single-camera 2D detection.
$npx -y skills add nvidia-ai-blueprints/video-search-and-summarization --skill vss-deploy-detection-tracking-3dInstalls into the current project.
Run `npx skills use "https://github.com/nvidia-ai-blueprints/video-search-and-summarization" --skill "nvidia-ai-blueprints/video-search-and-summarization/vss-deploy-detection-tracking-3d"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/nvidia-ai-blueprints/video-search-and-summarization" that are relevant to the current task. Run `npx skills add "https://github.com/nvidia-ai-blueprints/video-search-and-summarization"` and select the relevant skills, then follow their instructions.