OverviewIncludes both the powerful Coral Dev Board Mini and the proprietary (and generally not available anywhere else online) CA1 Camera Module.This hardware is increasingly difficult to find since being discontinued. It's the perfect setup for developers, researchers, or hobbyists working on Edge AI projects like object detection, pose estimation, and real-time image classification.What’s Included (all Like New condition)1x Google Coral Dev Board Mini1x Google Coral Camera Module (CA1)1x 24-pin FFC Ribbon Cable:The specific proprietary cable required to connect the CA1 to the Mini.
Camera Features:Sensor:High-quality 5MP OmniVision OV5645 sensorResolution: 2582 × 1933 pixels (5 MP)Video: 1080p @ 30fps / 720p @ 60fps
Board Features● MediaTek 8167s SoC ○ Quad-core ARM Cortex-A35 ○ Imagination PowerVR GE8300 GPU ● Google Edge TPU ML accelerator ○ 4 TOPS peak performance (int8) ○ 2 TOPS per watt ● ARM TrustZone Security ● Wi-Fi 5, Bluetooth 5.0 ● 8 GB eMMC, 2 GB LPDDR3 ● USB 2.0 Type-C OTG ● HDMI 1.4a (micro) ● MIPI DSI display ● MIPI CSI camera ● 3.5 mm headphone jack ● Digital PDM microphone ● 2.54mm 2-pin mono speaker terminal ● 40-pin GPIO expansion header ● Mendel Linux flashed in factoryBoard Description:
The Coral Dev Board Mini is a single-board computer that enables you to quickly prototype and deploy an embedded system with on-device ML inferencing. This board can also serve as an evaluation device for the Coral Accelerator Module , which allows you to integrate the Edge TPU into your custom PCB hardware as a surface-mounted module. The Edge TPU is a small ASIC designed by Google that accelerates TensorFlow Lite models in a power efficient manner: each one is capable of performing 4 trillion operations per second (4 TOPS), using 2 watts of power—that's 2 TOPS per watt. For example, one Edge TPU can execute state-of-the-art mobile vision models such as MobileNet v2 at almost 400 frames per second. This on-device ML processing reduces latency, increases data privacy, and removes the need for a constant internet connection.
