The Oak-1 boasts an integrated 12-megapixel camera module that communicates directly with the Myriad X over an on-board 2.1 Gbps MIPI interface. The Myriad X processes this data and performs neural inference, returning the results over USB. This data path offloads the host processor from all this work. For instance, in the common use case of object detection from a 12MP image, your host is now dealing with a 24 Kbps stream of what the objects are and where they are in the image, instead of a 2.1 Gbps stream of video. This results in an 87,500 reduction in the data your host has to manage.
This significant reduction allows even relatively slow hosts to use multiple Luxonis OAK-1 units without overloading the host CPU. For example, when running MobileNet-SSD, the OAK-1 combined with a Raspberry Pi achieves 50+FPS with 0% RPi CPU utilization. In comparison, the NCS2 with a Raspberry Pi only manages 8FPS with a 225% CPU utilization.
The Oak-1 is not just about power and speed; it's also about providing you with the right tools to make the most of it. For more information and support, you can access the DepthAI Product Brief, DepthAI Documentation, DepthAI C++ API Github, DepthAI Python Github, DepthAI Hardware Github, Luxonis Forums, and Luxonis Discord.
Choose the Oak-1 by Sparkfun for a high-performance, efficient, and versatile machine vision solution.
Brand | Sparkfun |
Model | SEN-17769 |
Length | 104 mm |
Width | 130 mm |
Height | 70 mm |
Weight | 327,2 g |