- Novinka
RLX COMPONENTS s.r.o. , Electronic Components Distributor.
RLX COMPONENTS s.r.o. , Electronic Components Distributor.
Raspberry Pi AI Camera, 12MP, IMX500 Intelligent Vision Sensor, Raspberry Pi Neural Network Model
Official Raspberry Pi AI Camera, 12MP, IMX500 Intelligent Vision Sensor, 78.3° FOV
Raspberry Pi AI Camera je malý modul od Raspberry Pi, ktorý využíva inteligentný senzor Sony IMX500. Tento snímač kombinuje 12-megapixelový obrazový snímač CMOS so zabudovanou akceleráciou pre modelovanie neurónových sietí, čo používateľom umožňuje vytvárať aplikácie AI zamerané na videnie bez potreby externého akcelerátora. AI Camera vylepšuje statické snímky alebo video pridaním metadát Tensor, pričom hlavný procesor Raspberry Pi zostáva voľný pre iné úlohy. Vďaka podpore metadát Tensor v knižniciach libcamera a Picamera2 a v balíku aplikácií rpicam-apps je kamera užívateľsky prívetivá pre začiatočníkov a ponúka komplexný výkon a flexibilitu pre pokročilých používateľov. Táto kamera funguje so všetkými modelmi Raspberry Pi a má rovnaké rozloženie dosiek plošných spojov a montážnych skrutiek ako modul Raspberry Pi Camera Module 3, pričom celková hĺbka je väčšia, aby sa do nej zmestil väčší snímač IMX500 a optická zostava.
Parametre
Kamera AI je kompatibilná so všetkými modelmi Raspberry Pi vrátane Raspberry Pi Zero a možno ju pripojiť pomocou štandardných káblov kamery Raspberry Pi. Pomocou nástrojov umelej inteligencie od spoločnosti Sony možno modely neurónových sietí založené na rámcoch, ako sú TensorFlow alebo PyTorch, prispôsobiť tak, aby na kamere AI Camera fungovali efektívne. Prípadne možno vytvoriť nové modely, ktoré budú využívať špecifické možnosti akcelerátora AI.
Integrácia s libcamera Raspberry Pi
Kľúčovou výhodou AI kamery je jej bezproblémová integrácia so softvérovým zásobníkom kamery Raspberry Pi. Na pozadí libcamera spracováva Bayerov snímok pomocou interného ISP Raspberry Pi, rovnako ako akýkoľvek iný senzor. Okrem toho Raspberry Pi spracúva výsledky neurónovej siete na vytvorenie výstupného tenzora a synchronizuje ho so spracovaným Bayerovým rámčekom. Tenzor aj snímka sa potom vrátia aplikácii počas fázy finalizácie požiadavky z libcamera.
Based on the IMX500 Intelligent Vision Sensor
AI compact camera module Designed By Raspberry Pi
The Raspberry Pi AI Camera is a compact camera module from Raspberry Pi, based on the IMX500 Intelligent Vision Sensor. IMX500 combines a 12.3MP CMOS image sensor with onboard inferencing accelerator for a variety of common neural network models, enabling users to develop sophisticated vision-based AI applications without the need for a separate accelerator
The AI Camera transparently augments captured still image or video with tensor metadata, leaving the processor in the host Raspberry Pi free to perform other operations. Support for tensor metadata in the libcamera and Picamera2 libraries, and in the rpicam-apps application suite, make it easy for beginners to use, while offering advanced users unparalleled power and flexibility.
The Raspberry Pi AI Camera is compatible with all Raspberry Pi computers. The PCB outline and mounting hole locations are identical to those of Raspberry Pi Camera Module 3, while the overall depth is greater to accommodate the larger IMX500 sensor and optical subassembly.
Key features include:
Sensor | IMX500 |
---|---|
Resolution | 12.3MP |
Sensor size | 7.857 mm (type 1/2.3) |
Pixel size | 1.55 μm × 1.55 μm |
Horizontal/vertical | 4056 × 3040 pixels |
IR cut filter | Integrated |
Autofocus system | Manual adjustable focus |
Focus range | 20 cm – ∞ |
Focal length | 4.74 mm |
Diagonal FOV | 78.3°±3° |
Horizontal FOV | 66°±3° |
Vertical FOV | 52.3°±3° |
Focal ratio (F-stop) | F1.79 |
Infrared sensitive | No |
Output | Image (Bayer RAW10), ISP output (YUV/RGB), ROI, metadata |
Input tensor maximum size | 640(H) × 640(V) |
Input data type | "int8" or "uint8" |
Memory size | 8388480 bytes for firmware, network weight file, and working memory |
Framerate | 2×2 binned: 2028×1520 10-bit 30fps Full resolution: 4056×3040 10-bit 10fps |
Dimensions | 25 × 24 × 11.9 mm |
Ribbon cable length | 200 mm |
Cable connector | 15pin × 1 mm FPC or 22pin × 0.5 mm FPC |
Operating temperature | 0°C ~ 50°C |
The Raspberry Pi AI Camera works differently from traditional AI-based camera image processing systems, as shown in the diagram below:
The left side demonstrates the architecture of a traditional AI camera system. In such a system, the camera delivers images to the Raspberry Pi. The Raspberry Pi processes the images and then performs AI inference. Traditional systems may use external AI accelerators (as shown) or rely exclusively on the CPU.
The right side demonstrates the architecture of a system that uses IMX500. The camera module contains a small Image Signal Processor (ISP) which turns the raw camera image data into an input tensor. The camera module sends this tensor directly into the AI accelerator within the camera, which produces an output tensor that contains the inferencing results. The AI accelerator sends this tensor to the Raspberry Pi. There is no need for an external accelerator, nor for the Raspberry Pi to run neural network software on the CPU.
Compatible with all Raspberry Pi computers, based on the IMX500 Intelligent Vision Sensor to help users create impressive vision AI applications and neural network models.
The IMX500's tight integration with Raspberry Pi's camera software stack allows users to deploy their own neural network models. To get started, the Raspberry Pi Official has developed a guide to get you running either a pre-packaged or custom-made neural network model on the camera.
Create AI models and applications for the IMX500 Intelligent Vision Sensor and Raspberry Pi, then scale up to an enterprise deployment with AITRIOS.
Local Studio walks you through the necessary steps to efficiently label, train and produce AI models.
* for reference only, the Raspberry Pi 5 is NOT included.