Semcam Live PRO, PRO+, and ULTRA serve professional motion-capture deployments at different scales, from real-time markerless capture to HPE high-precision processing and hybrid rigid-body capture with Goku, forming deployable motion-data infrastructure.
Each camera has built-in edge AI computing power to complete human detection, tracking, segmentation, 2D key points, ReID and confidence calculation at the collection source.
The power consumption of a single camera is between 10–18W, and power supply and data transmission are completed through a single PoE network cable.
The real-time link transmits structured key point data aligned with frame numbers, reducing network bandwidth and video processing pressure on the host computer.
The camera can switch between RGB and optical modes to operate as a AI marker-free camera or participate in Goku optical workflows
Nanosecond-level clock synchronization technology is used between cameras to ensure accurate 3D reconstruction
Each camera is equipped with 256-color auxiliary LED indicators to facilitate system operation and maintenance
Each camera is equipped with a color LCD screen to intuitively display the serial number and working status.
PRO+ and ULTRA support HPE high-precision solution expansion and can be used for post-harvest non-real-time high-quality motion data processing
All cameras can be mixed with Goku series optical cameras, supporting the same coordinate system, the same timeline, and the same project
A flagship edge AI mocap camera for large spaces and multi-person capture, with a 100 TOPS embedded GPU, support for 12-person capture, and HPE high-precision processing.
For large-space labs, LBE, simulation training, and multi-person data capture
A professional edge AI mocap camera for high-quality motion data capture, with a 55 TOPS embedded GPU and support for the HPE High-Precision Extension.
For life sciences, university labs, robotics training, and animation/VFX
An edge AI mocap camera for real-time markerless capture of up to 4 people, with a 40 TOPS embedded GPU and 120fps real-time output.
For small studios, teaching demos, creative previs, and rapid deployment
| Semcam Live | Optical motion capture system | Inertial motion capture system | |
|---|---|---|---|
| Technical principles | Multi-camera AI markerless capture + local 3D reconstruction | Marker point optical tracking | Inertial sensor measurement |
| Do you need to wear | ✓ No need | ✗ Required | ✗ Required |
| real time output | 120fps body rig and key points | High-precision marker points/rigid body | Sensor attitude data |
| High precision processing | HPE supports post-harvest non-real-time resolution | Mature and high-precision process | Depends on sensor drift control |
| Rigid body tracking | Can be mixed with projects via Goku | Native support | Often requires additional equipment |
| Deployment preparation | No markers required, suitable for natural motion capture | Requires patching, maintenance and occlusion management | Requires wearing, calibration and maintenance |
| fit for task | Markerless human motion + professional data workflow | High-precision rigid body and marker point measurement | Wearable mobile collection |
| Semcam Live | CloudAIMotion Capture | ServerAIMotion Capture | Consumer GradeAIMotion Capture | |
|---|---|---|---|---|
| Technical principles | Edge processing local reconstruction | Cloud processing | Server processing | PC processing |
| Edge computing capabilities | ✓ Supported | ✗ | ✗ | ✗ |
| Data transmission method | Structured key points and confidence | Video upload | Multiple video backhaul | Native video processing |
| Real-time capture capability | 120fps, less than 100ms | non real time | Longer delay | Longer delay |
| Number of people captured at the same scene | PRO/PRO+ support 4 people; ULTRA supports 12 people | Usually 1 person | Usually 1–4 people | Usually 1 person |
| High-precision expansion | HPE and Goku hybrid workflow | — | Rely on central computing power | — |
| Locally controllable | ✓ Supported | ✗ | ✓ | ✓ |
Semcam Live is an edge computing AI markerless motion capture system. Target detection, 2D keypoints, ReID, tracking, segmentation, cropping and confidence calculation are completed on the camera side, and Active Center locally completes cross-camera matching, triangulation, 3D keypoints, body rig solving, IK, filtering, retargeting and exporting.
Semcam Live is designed for multi-camera, simultaneous acquisition and on-site deployment, and does not rely on single video post-processing. The system uses a fixed-edge AI camera array to output frame-synchronized structured data and complete 3D reconstruction locally, making it more suitable for laboratories, robotics, virtual production, LBE and long-term training scenarios.
The live link delivers 120fps motion output and sub-100ms end-to-end latency, making it suitable for live previews, live drives, interactions and acquisition inspections. HPE is a post-harvest high-precision processing pipeline suitable for research, training data production, key shots and projects requiring higher quality keypoint results.
PRO is suitable for real-time capture of up to 4 people, and does not support HPE and facial capture; PRO+ is suitable for professional projects that require HPE for up to 4 people; ULTRA is suitable for larger spaces and multi-person capture, supports up to 12 people, supports HPE and facial capture, and will be launched soon.
Yes. Semcam Live is responsible for unmarked human motion, and Goku is responsible for rigid body objects such as robot joints, end effectors, tools, props, handles, training equipment, rackets, drones, and cameras. Both share the coordinate system, timeline, and project in Active Center.