skills.rest
sayalinvidia
sayalinvidiaCOMMUNITY
Explore all skills by this author →
GitHub

vss-deploy-detection-tracking-3d

Deploy and configure the MV3DT multi-camera 3D tracking stack with DeepStream and BEV fusion.

Updated Apr 16, 2026
Search Tags:#deployment#calibration#warehouse#vst#multi-view#mv3dt#3d-tracking
One-click install
npx skills add https://github.com/sayalinvidia/sayali-skills-test --skill vss-deploy-detection-tracking-3d
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: vss-deploy-detection-tracking-3d
Source: https://github.com/sayalinvidia/sayali-skills-test/tree/main/skills/vss-deploy-detection-tracking-3d
Command: npx skills add https://github.com/sayalinvidia/sayali-skills-test --skill vss-deploy-detection-tracking-3d

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill provides a complete, end-to-end procedure to deploy and operate the MV3DT multi-camera 3D tracking stack (RTVI-CV-3D) with per-camera DeepStream perception and BEV fusion, enabling warehouse-scale multi-view 3D analytics.

Core Features & Use Cases

  • Automates the end-to-end MV3DT workflow: calibration landing, camera configuration, MV3DT stack deployment, and verification via the VST video wall.
  • Supports routing decisions for sample, videos, and RTSP data sources, including AMC calibration integration for custom data.
  • Provides guidance on profiling, resource gates, and readiness checks to ensure a stable MV3DT deployment in production.

Quick Start

Walk through provisioning MV3DT from calibration to deployment and verification.

Frequently Asked Questions about vss-deploy-detection-tracking-3d

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I deploy multi-view 3D tracking for a warehouse scenario?▼

Multi-view 3D tracking deployment for warehouse scenarios uses the MV3DT stack to configure per-camera DeepStream perception and BEV fusion. It requires camera configuration, calibration, stack deployment, and verification via the VST video wall.

What is the best way to calibrate cameras for MV3DT multi-camera tracking?▼

Camera calibration for MV3DT tracking is handled through calibration landing or AMC-driven calibration for custom data. This process ensures accurate multi-view alignment before deploying the BEV fusion stack.

Does the MV3DT stack support both Kafka and Redis for warehouse deployments?▼

Yes, MV3DT warehouse deployments support both Kafka and Redis messaging backends. You configure the stack during deployment using the BP_PROFILE parameter set to either bp_wh_kafka or bp_wh_redis.

How do I verify that my multi-view 3D tracking deployment is working correctly?▼

Verify multi-view 3D tracking deployment by checking the VST video wall output. The workflow includes readiness checks for active data sources and broker offsets to ensure stable BEV fusion and perception operations.

What prerequisites are needed for multi-camera 3D tracking stack deployment?▼

Multi-camera 3D tracking deployment requires proper data and permissions prerequisites, active data sources, and broker offset readiness. You must complete calibration and camera configuration before executing the MV3DT compose deployment.

Can I use RTSP streams as data sources for warehouse 3D tracking?▼

Yes, RTSP streams are supported as data sources for warehouse 3D tracking. The MV3DT stack routing accommodates sample data, video files, and RTSP streams through explicit workflow decisions for flexible deployment scenarios.

Related Skills

Explore More Software Engineering Skills→
olibartfastolibartfast

amc-run-rtsp-calibration

Automate camera calibration from live RTSP streams via the AutoMagicCalib REST API.

Community
Advanced
olibartfastolibartfast

deepstream-run-mv3dt

Manage containerized DeepStream MV3DT execution with configuration generation and prerequisite validation.

Community
Advanced
KAIROS7-team3KAIROS7-team3

robot-perception

Configure, calibrate, and optimize robot perception systems with cameras and LiDARs.

Official
Advanced
NVIDIANVIDIA
189

deepstream-run-mv3dt

Operate the DeepStream Multi-View 3D Tracking reference application with pipeline configuration and execution workflows.

Official
Advanced