-
Notifications
You must be signed in to change notification settings - Fork 639
Getting Transformation Matrices
To get started you need to:
- Plug 6 Azure Kinect Sensor and complete the Initial Configuration Steps on each machine
- All of the computers you will use should be on the same network
- Print the calibration pattern “pattern.jpg” on a piece of paper (inside of spaceport/registration”)
Step 1: Choose a computer that will act as a server (this computer may also be a client at the same time), we recommend that it is the most powerful of the available machines.
Our default setup:
hal: Nvidia GTX 1070 – i7 8700K
marvin1: Nvidia GTX 1060 – i5 7400
marvin2: Nvidia GTX 1060 – i5 7400
Step 2: Run the roscore
on the chosen machine (hal).
Step 3: Use the sendjob
script under the script folder to start all publishers. In a nutshell, the sendjob
script will connect to your devices and run publishers on each device at the same time to avoid sync issues.
cd VolumetricVideoRegistration/scripts
bash sendjob.sh
Step 4: In order to run the clients you need the printed calibration pattern. Once printed, attach it to something rigid and place it in a position where it is visible to all sensors.
Step 5: Create a serial.txt. The format should be as follows
null = for reference camera 0 = looking to the same side as the reference camera 1 = looking to the opposite side with the reference camera
Step 6: Then run the startRegistration.sh
on the chosen machine.
cd /VolumetricVideoRegistration/src/registraiton
bash startReg.sh
Step 7: Press S to get the image and then Press Q to skip the next step
Step 8: Find contours with the trackbar for both image and then press space
Note: After you found contours you can press s and then capture a new frame for the same camera pairs. Thus you can expand registration quality.
Step 9: Back to Step 7 until all camera pairs are registered
Result: You are going to get the transformation matrices for each camera in a similar way below.
1.out
2.out
3.out
4.out
5.out
Once the Transformation matrices of all cameras have been calculated, move these values into binaries/spaceport/TransDir.
- Introduction
- Quick Start
- Installation
- Publishing Live Streams
- Playing Live Streams
- Conference Call
- Peer to Peer Call
- Adaptive Bitrate(Multi-Bitrate) Streaming
- Data Channel
- Video on Demand Streaming
- Simulcasting to Social Media Channels
- Clustering & Scaling
- Monitor Ant Media Servers with Apache Kafka and Grafana
- WebRTC SDKs
- Security
- Integration with your Project
- Advanced
- WebRTC Load Testing
- TURN Servers
- AWS Wavelength Deployment
- Multi-Tenancy Support
- Monitor Ant Media Server with Datadog
- Clustering in Alibaba
- Playlist
- Kubernetes
- Time based One Time Password
- Kubernetes Autoscaling
- Kubernetes Ingress
- How to Install Ant Media Server on EKS
- Release Tests
- Spaceport Volumetric Video
- WebRTC Viewers Info
- Webhook Authentication for Publishing Streams
- Recording Streams
- How to Update Ant Media Server with Cloudformation
- How to Install Ant Media Server on GKE
- Ant Media Server on Docker Swarm
- Developer Quick Start
- Recording HLS, MP4 and how to recover
- Re-streaming update
- Git Branching
- UML Diagrams