Capture｜Project Decode_RoboDecode-SHANGHAI CHINGMU VISION TECHNOLOGY CO., LTD

RoboDecode Capture｜Project Decode

Project Decode is a high-precision multimodal data acquisition system developed by Chingmu for embodied intelligence research.

It synchronously collects motion, tactile, and video data in real-world scenarios, enabling efficient and reusable dataset construction.

Consult >

Scenarios Covered

Desktop Logistics Packaging

Home & Living Scenarios

Industrial Manufacturing Scenarios

Retail Merchandising

Large-Space Group Acquisition

Product advantages

High AccuracyPowered by CHINGMU’s self‑developed optical mocap system, it delivers sub‑mm spatial positioning, pose angle accuracy down to 0.1°, and drift‑free data throughout – providing a precise and reliable data benchmark for robot ground‑truth measurement and algorithm validation.

Consult >

High SensitivityE‑skin sensors capture subtle tactile pressure across contact, sliding, grasping – building high‑fidelity tactile datasets for Embodied AI manipulation training.

Consult >

Optical-Inertial HybridLeveraging an optical‑inertial hybrid solution to overcome the limitations of single‑sensor systems, with robust anti‑occlusion and magnetic‑noise‑immunity performance – ensuring smooth and continuous motion data output for high‑quality dataset acquisition in complex dynamic scenarios.

Consult >

Spatiotemporal SynchronizationLeveraging global hardware‑level synchronization technology to unify the temporal reference of multimodal data sources – including motion capture, tactile, and visual data – eliminating timing discrepancies and spatial misalignment to deliver a precise and consistent data foundation for multimodal dataset construction.

Consult >

Production-Integrated Unobtrusive Data CaptureUnobtrusive in-production acquisition – capturing human motion and force signals naturally for robot manipulation datasets grounded in real industrial environments.

Consult >

Clean Data StreamBuilt‑in AI auto‑repair and sync alignment algorithms process missing data and timing discrepancies in real time, delivering ready‑to‑use data at output – with no need for manual cleaning – significantly improving dataset construction efficiency and data usability.

Consult >

The series come together, offering more choices

Detailed parameters, complete specifications

Pulse3 4-Lens Parameters
	Quantity	Baseline	Pixel (Per Camera)	Resolution @ Frame Rate (Per Camera)	FOV (Per Camera)	Sensor Size	Interface Type	Color	Data Transmission	Power Type	Network Interface
IR Camera	2	144 mm	3.1 MP	2048×1536 @ 120 fps	57° × 44°	1/3.1	RJ45	Monochrome	Marker Data Transmission	POE	2× PoE RJ45, Daisy-Chainable
RGB Camera	2	63 mm	2 MP	1920×1080 @ 60 fps	112° × 80°	1/2.6	RJ45	Color	MJPEG Compressed Image Transmission	POE	2× PoE RJ45, Daisy-Chainable

Pulse Series Optical-Inertial Fusion Glove Parameters
Optical Parameters	Number of active lights	31 per hand	Active light wavelength	850nm
Optical Parameters	Strobe sequence	Supports ID strobe sequence setting	Synchronization mode	Wired synchronization
Inertial Parameters	Number of inertial sensors	12 per hand	Sensor type	6-axis inertial sensor
	Data output frame rate	1000 Hz	Accelerometer range	±16g
	Gyroscope range	±2000dps	Posture measurement range	Yaw, roll, pitch 360° full range
Other Parameters	Data transmission	Wired network	Glove weight(single)	140-190g

Pulse C Main Control Unit Parameters
Number of active lights	5个	Number of Inertial Sensors	1
Power supply	POE	Processor Performance	4-core,1.5GHz
NPU Performance	2.0TOPS	Memory	DDR4 2*256M
USB	USB2.0	FLASH	32MB
Interface Type	Lockable aviation connector	Data Transmission	Wired network
Transmission Protocol	Supports UDP/TCP	Synchronization Protocol	Supports IEEE1588 PTP
Control Box Size	98 mm x 84 mm x 32 mm	Control Box Weight	173.7g

CHINGMU Dynamic Real-time delivery

IROS 2025 Zhejiang University: Research on Dextrous Manipulation of Dual Robots / Industry News

The dexterous operation of dual robots, due to its high degree of freedom coordination, multimodal perception fusion, and complex skill combination, has become an important research direction in the field of robotics.

2025-10-06

CHINGMU × Xiying Group: A New Chapter in Digitalization of Film and Television / Company Updates

In the field of film art, when the movements of characters are smooth and fluid, the expressions of digital characters are vivid and expressive, and the virtual shooting seamlessly integrates with the real scenes, the success of such works is inseparable from the strong support of motion capture technology.

2025-10-06

CHINGMU × UITM: Overseas Empowerment of Sports Science / Company Updates

Under the global trend of upgrading global sports research towards more refined and quantitative analysis, universities and research institutions around the world are accelerating their exploration of the integration path between technology and academic research.

2025-10-06

IROS 2025：CHINGMU Motion Capture Black Technology / Company Updates

As the annual event IROS 2025 of the robotics circle approaches, as the "prominent representative" of motion capture technology in the industry, CHINGMU Qing Tong Vision has already prepared a "full-strength surprise": multiple hardcore workshops, in-depth visits to industrial parks,

2025-10-06

CHINGMU and AMD rewrite the world record: 100-person simultaneous real-time motion capture / Company Updates

Shanghai, May 31 — CHINGMU hosted its “100 People Enter the Digital World Simultaneously” real-time motion capture challenge & digital motion showcase at the CHINGMU MCP Boundless Studio in Shanghai. AMD served as the lead computing partner. The event featured a live performance by 100 motion-capture actors, demonstrating the synergy of large-scale optical motion capture, AI computing, real-time digital character animation, and embodied AI.

2026-06-05

Obtain exclusive case studies and industry solutions

Get the complete case in one click. Our experts will precisely match the most suitable motion capture solution for your industry, helping you reduce costs and increase efficiency.

Obtain exclusive case studies and industry solutions

Name*

Email*

Country*

Enterprise / Institution*

Application fields*

Please leave a message.*