The learning model is created independently! We will introduce examples of AI solutions for edge devices.
We have built an application system using Deep Learning that operates on a Raspberry Pi3 as a proposal for AI solutions for edge devices. At Embedded Technology West 2019 / the Kansai Embedded Technology Exhibition, we conducted a demo using a depth measurement camera to simulate FaceID running on an embedded device. Anticipating various future needs and versatility, we created a unique learning model from a Deep Learning framework without using existing pre-trained models. This allows for flexible responses to various edge devices. The AI solutions proposed by Bee Co., Ltd. can flexibly respond to various edge devices. We provide everything from selecting devices and proposing ideas for services to controlling these devices with embedded technology and operational support. *For more details, please refer to the PDF materials or feel free to contact us.
Inquire About This Product
basic information
【System Contents】 ■Intel Realsense ・Equipped with a depth camera, RGB sensor, and IR projector ・Utilizes RGB + depth information to accurately capture facial data ■Raspberry Pi3 ・For embedded use, keeps the learning model data locally, achieving full local operation ■PyTorch ・Open-source machine learning library for Python ・Uses a Siamese Network for the architecture ■Data Set ・The training data uses a dataset of various people captured from different angles and expressions ■PyQt4 ・Used for creating the GUI ■AWS ・The learning model is trained on AWS GPU instances ・Uses p3.2xlarge on Amazon EC2 P3 instances *For more details, please refer to the PDF document or feel free to contact us.
Price range
Delivery Time
Applications/Examples of results
For more details, please refer to the PDF document or feel free to contact us.
catalog（1）
Download All Catalogs
Company information
At Bee, we handle not only embedded software development but also the development of associated applications and cloud/AI solutions, embracing innovative technologies that go beyond the traditional boundaries of embedded software. We are certified under the information security management system standard "ISO/IEC 27001:2013" in customer requirements as well as in the design, development, and maintenance of our proprietary software. Furthermore, while "DX transformation" is currently emphasized, we have been achieving paperless and cloud-based solutions since our founding in 2006, making improvements to our internal environment a standard practice, not just in terms of information security.