Shulou(Shulou.com)11/24 Report--

CTOnews.com August 22 news, August 11, Xiaomi held a new autumn product conference, Xiaomi's first full-size humanoid bionic robot CyberOne officially unveiled. According to O'Figuang, the Mi-Sense depth vision module carried by CyberOne is designed by Xiaomi and co-developed by Ofeiguang; combined with the AI interaction algorithm, it not only has a complete three-dimensional space perception ability, but also can realize character identity recognition, gesture recognition, and expression recognition. CyberOne can not only see it, but also understand it.

Xiaomi full-size humanoid bionic robot CyberOne height 177cm, weight 52kg, stage name "Tieda". Xiaomi said that Tieda uses a variety of technologies to perceive 45 human semantic emotions and distinguish 85 environmental semantics; it is equipped with Xiaomi's self-developed whole-body control algorithm, which can coordinate the movement of 21 joints; it is equipped with a Mi Sense visual space system, which can reconstruct the real world in three dimensions; and five joints are driven by the whole body, with peak torque 300Nm. Xiaomi said that the intelligence and mechanical capabilities of CyberOne were all developed by Xiaomi Robotics Lab. Behind this, there are countless software, hardware and algorithm development work.

Recently, Ofeiguang simultaneously released the self-developed machine vision depth camera module, which is mainly composed of iToF module, RGB module and optional IMU module. The product has an accuracy of up to 1% in the measurement range and has a wide range of applications. It can pass the third-party laboratory IEC 60825-1 certification and meet the laser safety Class1 standard. IToF technology is one of the mainstream 3D visual perception technologies. Ofeiguang develops a 3D intelligent depth camera based on iToF+RGB depth measurement technology.

In fact, machine vision as the eye of the machine, ToF depth camera is one of the best options to make smart devices understand the world and have the ability to perceive and understand the environment. The depth camera can recognize the 3D coordinate information of each point in the field of vision, so that the computer can get the 3D data of the space and restore the complete 3D world and realize all kinds of intelligent 3D positioning.

The 3D intelligent depth camera released by Ofeiguang is mainly composed of three parts: iToF module, RGB module and optional IMU module.

CTOnews.com learned that in terms of external interface, this intelligent depth camera has a USB 3.0 Type-C interface for the transmission of depth, IR and RGB,IMU data. The bandwidth of USB 3.0 can theoretically support the transmission of point cloud data and is highly scalable. At the same time, considering the synchronization between other sensors and the depth camera, the depth camera retains the synchronization signal interface, part of the GPIO interface and power supply interface, which makes the user multi-sensor fusion easier.

According to O'Figuang, the intelligent depth camera has a powerful SoC platform, which integrates ISP, ARM CPU, embedded GPU and NPU and other IP. Later, you can consider releasing computing power for users, so that users can make better use of the computing power of depth cameras. At present, depth decoding takes up part of the GPU computing power and part of the CPU computing power, and the NPU computing power can be completely released in the later stage.

The maximum depth resolution of iToF-RGBD released this time is VGA (640x480) with a frame rate of 30fps. In the future, higher frame rate mode and binning mode will be available.

At the same time, the FoV of the depth is 76 °horizontally and 61 °vertically, and the laser wavelength is 940nm. The RGB uses a 1.3 megapixel sensor with a global shutter. The FoV is 93 °horizontally and 82 °vertically.

In terms of depth measurement performance, it currently supports a measurement range of 0.1m to 5m indoor (test environment: indoor illuminance no more than 1w Lux,90% reflectivity white wall) and outdoor measurement requirements of 0.1m to 3m (test environment: outdoor reflectivity of no more than 5W Lux,90%), with an accuracy of up to 1% in the measurement range.

In the field of face recognition, it is mainly used in facial scanning payment, authentication facial scanning access control, facial scanning attendance and so on; in the robot field, it is mainly used in obstacle avoidance, SLAM, AI recognition, and other scenes; in the field of 3D scanning, it is mainly used in indoor scanning modeling; in the industrial field, it is mainly used in industrial automation parts scanning and sorting. R / AR, access control, intelligent transportation and many other areas of development bottlenecks.

Welcome to subscribe "Shulou Technology Information " to get latest news, interesting things and hot topics in the IT industry, and controls the hottest and latest Internet news, technology news and IT industry trends.