From March 11th to 13th, at the Embedded World 2025 exhibition, Union Image officially launched its first self-developed depth binocular camera.
Relying on a robust global supply chain and lean manufacturing system, Union Image deeply integrates AIbase-driven product development capabilities into the entire design and production process, ensuring efficient iteration and stable quality. With leading intelligent optimization algorithms and cost control advantages, it has created a highly cost-effective depth camera, providing precise, efficient, and reliable solutions for intelligent visual applications.
▲ Union Image’s First Self-Developed Depth Binocular Camera
This camera is equipped with dual image sensors, using 1/4 1.3MP CMOS sensors with a 1280×1080 pixel array; 2.7µm×2.7µm pixel size, combined with an electronically synchronized global shutter, enabling accurate image capture.
In terms of output, it supports resolutions of 2x 1280×1080 @15fps and 2x 640x480 @15/30 (binning 2x2), with rich output formats including point cloud maps, depth maps, and RGB images to meet diverse application needs. It has a maximum signal-to-noise ratio of 38.3dB, a dynamic range of 64.6dB, a sensitivity of 1900mV/Lux-sec, a 63mm baseline, a 1.75mm focal length, a wide field of view of 115° (H)×96° (V)×157° (D), an aperture of 2.0, and less than 20% TV distortion. It can stably output high-quality images in both dim environments and complex scenarios.
▲ Union Image’s First Self-Developed Depth Binocular Camera
In addition to powerful image sensors, the camera integrates a high-performance Inertial Measurement Unit (IMU) and magnetometer. The accelerometer has a measurement range of ±8G, a resolution of 0.244mg, and a noise density of only 3.2mg; the gyroscope has a measurement range of ±1000dps, a resolution of 0.03dps, a noise density of 0.16dps, a sensitivity error controlled within ±0.4%, and an output data rate of 400Hz. The magnetometer has a measurement range of ±2500µT on the Z-axis and ±1300µT on the X/Y axes, a resolution of 0.3µT, and an output data rate of 50Hz, with an accuracy of 1% within a test distance of 1cm - 300cm. These precision sensors work together to provide the camera with more comprehensive and accurate environmental perception capabilities.
Certainly, the core highlight of this camera lies in its built-in AI large model:
The series of self-developed depth binocular cameras by Union Image will also deeply integrate with the development wave of AI, accelerating iterative updates toward miniaturization, low cost, strong performance, and intelligence, matching customers' customized needs and developing adaptability for different scenarios. Stay tuned.
Embedded World 2025 brings together approximately 1,000 global exhibitors and over 32,000 professional visitors, focusing on the entire embedded industry chain and cutting-edge Industry 4.0 technologies. It serves as a core platform for technical exchanges, market expansion, and insight into industry trends.
Union Image has deep expertise in "AIoT visual solutions." During the exhibition, the Union Image booth was bustling with industry partners stopping by for exchanges. The displayed camera modules, visual solutions, and imaging integrated machines can quickly match solutions according to the specific needs of different industries and scenarios.
The exhibition focuses on showcasing two core technical areas: camera modules and AI visual solutions. Static exhibits and dynamic demos enhance the experiential feel for customers to understand and discuss cutting-edge visual technologies. Star products that garnered significant attention include:
The Unimage Pi series is a highly integrated intelligent visual solution designed for AIoT scenarios, equipped with a dual-core RISC-V processor and offering multiple models and flexible memory options. It has rich interfaces, supports industrial control and multi-device expansion, and includes 9 categories of high-precision visual models covering security, transportation, health monitoring, human-computer interaction, and other fields. Balancing high performance and easy deployment, it provides efficient and stable edge-side computing power support for AI+visual applications across all things.
DVS (Dynamic Vision Sensor) uses bionic retinal principles, with optical flow field spatio-temporal event analysis, supporting high-speed motion trajectory reconstruction, behavior analysis, and anomaly detection. It is widely applied in intelligent interaction, autonomous driving, medical monitoring, industrial IoT, and other fields, demonstrating excellent real-time performance, energy efficiency ratio, and environmental adaptability.
The AI camera is a high-performance intelligent visual device with built-in deep learning models, capable of real-time detection of 17 human key points, supporting motion recognition and posture analysis. It is widely used in sports science, rehabilitation training, medical evaluation, human-computer interaction, security, and entertainment. It is suitable for high-precision motion capture and real-time analysis in complex environments, providing stable digital solutions for human movement.
The multispectral camera uses high-precision spectral separation technology, widely applied in industrial inspection (PCB micro-defect recognition, food sorting, color difference control) and agricultural monitoring (crop 3D modeling, pest early warning). Combined with multispectral fusion algorithms, it provides highly reliable visual solutions for smart manufacturing and precision agriculture.
Union Image takes "All Things * Vision" as its core philosophy, helping the Internet of Everything evolve from "seeing" to "understanding," and empowering the intelligent upgrading of thousands of industries. We look forward to collaborating with more industry peers in the broad AIoT markets at home and abroad to explore more cutting-edge visual solutions and create a more "AI"-driven future!