Brian Dipert

Infographic-Smart-City

Cloud and Edge Vision Processing Options for Deep Learning Inference

Should deep learning-based computer vision processing take place in the cloud, at the edge, or both? This seemingly simple question has a complicated answer: "it depends." This article provides perspectives on the various factors you should consider, and with what priorities, when making this implementation decision for your particular project's requirements. THe Edge-Centric Inference Evolution […]

Cloud and Edge Vision Processing Options for Deep Learning Inference Read More +

quad-core_vc_cam__sd_card__interface_board_2000px

New Embedded Vision Systems with Quad-core Processors

October 30, 2019 – Vision Components premiered the first prototype of its latest generation of embedded vision systems offering a substantial performance boost at Embedded VISION Europe in Stuttgart, Germany, on October 24, 2019. The onboard quad-core processor, Qualcomm's Snapdragon 410, is clocked at 1.2 GHz. The board camera features a Gbit Ethernet interface, 12

New Embedded Vision Systems with Quad-core Processors Read More +

Horizon Robotics Demonstration of the Company’s Localization and Mapping Technology

George Totolos, business development manager at Horizon Robotics, delivers a product demonstration at the May 2019 Embedded Vision Summit. Totolos showcases Horizon's localization and mapping technology running on top of a Horizon Matrix 1.7 system. Totolos explains that Navnet works while requiring only a mono camera and is generating a point cloud map without the

Horizon Robotics Demonstration of the Company’s Localization and Mapping Technology Read More +

Horizon Robotics Demonstration of the Matrix Perception Platform

George Totolos, business development manager at Horizon Robotics, delivers a product demonstration at the May 2019 Embedded Vision Summit. Totolos showcases Horizon's Matrix perception platform, winner of an Embedded Vision Alliance Vision Product of the Year award. The Matrix is a turnkey detection and classification solution using an FPGA-based implementation of Horizon's proprietary hardware in

Horizon Robotics Demonstration of the Matrix Perception Platform Read More +

“Quantizing Deep Networks for Efficient Inference at the Edge,” a Presentation from Facebook

Raghuraman Krishnamoorthi, Software Engineer at Facebook, delivers the presentation “Quantizing Deep Networks for Efficient Inference at the Edge” at the Embedded Vision Alliance’s September 2019 Vision Industry and Technology Forum. Krishnamoorthi gives an overview of practical deep neural network quantization techniques and tools.

“Quantizing Deep Networks for Efficient Inference at the Edge,” a Presentation from Facebook Read More +

PROPHESEE-HERO-ROBOTICS-Compressed-e1572252962140

Prophesee Closes $28M in Funding

PARIS – October 28, 2019 – Prophesee SA, inventor of the world’s most advanced neuromorphic vision system, today announced it has closed $28 million in funding, bringing its total funding to date to $68 million. Led by the European Investment Bank, the round also includes staged investments from commercial backers, including Prophesee’s existing investors such

Prophesee Closes $28M in Funding Read More +

MediaTek Demonstration of Video Object Detection

Victor Tyan, Deputy Director at MediaTek, delivers a product demonstration at the May 2019 Embedded Vision Summit. Specifically, Tyan demonstrates how MediaTek's mass-market AI image processor, the MT8167, and its higher end variant, the MT8385, can run video object detection. The edge inference is made possible with these processors. Therefore, applications such as security and

MediaTek Demonstration of Video Object Detection Read More +

MediaTek Demonstration of AI Human Pose Tracking

Victor Tyan, Deputy Director at MediaTek, delivers a product demonstration at the May 2019 Embedded Vision Summit. Specifically, Tyan demonstrates how MediaTek's latest AI smartphone processor, the Helio P90, can run complicated human pose tracking without a stereo camera, extracting depth information purely based on the understanding of human body in terms of where limbs

MediaTek Demonstration of AI Human Pose Tracking Read More +

Robotic Materials Demonstration of Its All-in-one Embedded Intelligence for Robotic Manipulation

Austin Miller, lead engineer at Robotic Materials, demonstrates the company's latest embedded vision technologies and products at the 2019 Embedded Vision Summit. Specifically, Miller demonstrates the company's recent SmartHand product, a robotic gripper with embedded 3D perception, computation, and a complete programming environment. Accessible by any Wi-Fi-enabled tablet or computer, the hand can be programmed

Robotic Materials Demonstration of Its All-in-one Embedded Intelligence for Robotic Manipulation Read More +

BlinkAI Technologies Demonstration of Machine Learning Low-Light Enhancement

Bo Zhu, CTO and Co-founder of BlinkAI Technologies, delivers a product demonstration at the May 2019 Embedded Vision Summit. Specifically, Zhu demonstrates the company's real-time low-light video enhancement technology, which can be deployed on low-power embedded systems in smartphone, automotive, and security/surveillance industries. He then presents a sequence of videos showcasing this enhancement in various

BlinkAI Technologies Demonstration of Machine Learning Low-Light Enhancement Read More +

Here you’ll find a wealth of practical technical insights and expert advice to help you bring AI and visual intelligence into your products without flying blind.

Contact

Address

Berkeley Design Technology, Inc.
PO Box #4446
Walnut Creek, CA 94596

Phone
Phone: +1 (925) 954-1411
Scroll to Top