Requirements

NVIDIA GPU & Driver

An NVIDIA GPU with compute capability 7.5 or higher is required (Turing architecture and newer — GeForce RTX 20-series and up, Quadro RTX, Tesla T4, and all NVIDIA data-center GPUs from Turing through Blackwell).

Maxwell, Pascal, and Volta GPUs are no longer supported (e.g. GeForce GTX 900/10-series, Quadro P-series, Tesla V100). Check your card against NVIDIA's CUDA GPU compute capability list before installing.

Install an NVIDIA display driver version >= 580.65.06. Download drivers from NVIDIA.

Bundled dependencies

CUDA 13.0, TensorRT 10.13.3.9, cuDNN 9.x, NDI, Intel IPP, PyTorch, and cuVSLAM runtime libraries, as well as the Microsoft Visual C++ Redistributable and .NET 8 runtimes, are installed automatically by the Viz Object Tracker installer below. No separate downloads or manual copy steps are required.

Installer

Viz Object Tracker ships as two separate installers:

  • Viz Object Tracker (VizObjectTracker-<version>.exe) — the main application: GUI, tracking server, and all runtime dependencies.

  • Viz Object Tracker Data (VizObjectTrackerData-<version>.exe) — the TensorRT engine builder and the DNN model weights, needed to (re)build .engine files for your specific GPU/driver/TensorRT version (see First Power up below). Without it, Viz Object Tracker still runs normally, it just can't automatically rebuild engines for a new GPU.

Both are needed for full functionality, but they can be run in either order:

  • Download both installer files into the same folder before running either one.

  • Run either installer first — if the other one is sitting in the same folder and not already installed, it will be installed automatically right afterwards.

  • If the other product is already installed on the machine, running just one installer is enough; nothing gets installed twice.

  • If Viz Object Tracker Data is installed on top of an already-running Viz Object Tracker, the running app is automatically restarted afterwards so it can pick up the newly installed files and (re)build engines as needed.

To install:

  • Run the installer — it extracts its bundled files into a temporary folder.

  • Windows may briefly show a User Account Control prompt while Viz Object Tracker's installer silently installs its bundled prerequisites (Microsoft Visual C++ Redistributable and .NET runtimes) — this is expected, allow it.

  • Accept the license terms to continue the installation.

  • Then the installer will copy all the necessary files.

  • Press Install/Finish to complete installation (and, if the other installer was found alongside it, to chain into that one automatically).

  • Once installation finishes, Object Tracker starts automatically, and shows up with a green light in the icon tray.

  • The installer adds Object Tracker into the Startup Apps so it starts up automatically after logging in.

Icon Tray

Right click the icon tray to get a context menu.

  • Connected/Disconnected: Indicates whether the Object Tracker is running.

  • Start Server Manually: Starts the service in case it has stopped.

  • Stop Server Manually: Stops the service.

  • Show Console: Visualizes the console with debugging information.

  • Hide Console: Hides the console.

  • Exit: Stops the service and closes the icon tray.

First Power up

Once both Viz Object Tracker and Viz Object Tracker Data are installed (see Installer above — Data provides the engine builder), Viz Object Tracker automatically compiles the model into a GPU-specific engine for every CUDA-capable graphics card in the workstation the first time it starts. This takes a few minutes per graphics card.

Before compiling the model for a GPU, the installer waits (up to 60 seconds) for that GPU's utilization to drop to 3% or below. TensorRT's build-time tactic/kernel selection is timing-sensitive, so if something else is actively using the GPU during compilation, it can pick a meaningfully slower tactic set for that engine. While it waits, it lists which process(es) are currently using the GPU so you can close them — closing other GPU-heavy applications before this step is recommended for the best-performing engine. If the GPU is still busy after 60 seconds, compilation proceeds anyway.

‌