Laser Detection#
Authors: Holoscan Team (NVIDIA)
Supported platforms: aarch64
Language: Python
Last modified: May 13, 2025
Latest version: 1.0
Minimum Holoscan SDK version: 2.1.0
Tested Holoscan SDK versions: 2.2.0
Contribution metric: Level 1 - Highly Reliable
Overview#
This application demonstrates the latency differences between USB and EVT cameras by detecting laser pointer positions on a monitor. It uses two camera sources to track laser positions and displays the results in real-time with different colored icons.
Hardware Requirements#
- USB camera (Logitech 4k Pro Webcam or compatible)
- EVT camera (HB-9000-G 25GE or compatible)
- Monitor with matte screen (120fps or higher refresh rate recommended)
- Safe laser pointer for viewing purposes
- Completed calibration files from both USB and EVT calibration apps
Setup Instructions#
- Complete the calibration process for both USB and EVT cameras
- Ensure both cameras are properly connected and configured
- Position the cameras to have a clear view of the monitor
- Verify the calibration files (
usb-cali.npy
andevt-cali.npy
) are present in the build directory
Running the Application#
./run build laser_detection
sudo LD_PRELOAD=/usr/lib/aarch64-linux-gnu/nvidia/libnvjpeg.so ./run launch laser_detection
Usage#
- A white icon represents the USB camera's laser detection
- A green icon represents the EVT camera's laser detection
- Point the laser at the monitor to see the latency difference between the two cameras
- The icons will move to the coordinates where the laser is detected
Notes#
- Use only a matte screen monitor to avoid specular reflections
- Ensure proper lighting conditions
- Use only safe laser pointers designed for viewing purposes
- If detection is inaccurate, recalibrate both cameras
- The application requires sudo privileges to run