Product Brief
Overview
Block Diagram
Key Features
Flexible Low-Power Platform
10-nm low-power CMOS process
64-bit ARM® Quad Core Cortex™-A53 CPU up to 1GHz
Linux kernel version 4.14 or latest (64-bit)
Linux SDK for standards-based development
CVow™ vector processor with CNN/DNN algorithms
OTP, Secure boot, TrustZone™, IO virtualization
Industry leading image sensors support
Computer Vision Engine
CNN/DNN-based processing: detection, classication,
tracking, and more
Computer Vision Processors
Tools for high and low-level algorithm development
CNN toolkit for easy porting with Cae and
TensorFlow
Open SDK
Advanced Image Processing
More than 800 MPixels input rate
Multi-exposure line-interleaved HDR
Hardware de-warping engine support
Electronic Image Stabilization (EIS)
Dual independent sensor inputs
3D motion compensated noise reduction (MCTF)
Superior low light processing
High-Efficiency Video Encoding
H.265 and H.264 video compression
Flexible multi-streaming capability
Up to 4Kp30+ video performance
Multiple CBR and VBR bit rate control modes
Smart H.264 and H.265 encoder algorithms
°
°
°
The diagram below illustrates a design based on the Ambarella CV22S device.
°
°
°
°
°
32-BIT
LPDDR4x /
LPDDR4 /
SPI
MASTER
DDR
L2 CACHE
ISP
COMPUTER VISION PROCESSOR
QUAD-CORE ARM® CORTEX™
-A53
GDMA
AMBARELLA MEMORY SYSTEM
NAND /
NOR
NAND /
NOR
UART GPIO
AUDIO
I2S
VIDEO
INPUT /
SENSOR
INTERFACE
PWM
HDMI /
PARALLEL
TIMERS
WDT
JTAG
RTC
SENSOR 1
USB 2.0
HOST /
DEVICE
MIPI
DSI / CSI
GIGABIT
ETHERNET
ANALOG
VIDEO OUT
IDC / I2C
SDIO
SDXC
SENSOR 2
CAN /
CAN FD
The CV22S chip targets IP camera designs.
°
°
°
°
°
°
°
°
Ambarella’s CV22S SoC combines image processing, 4Kp30+ video encoding, and
CVow
TM
computer vision processing in a single, low power design. The CV22S’s
CVow
TM
architecture provides the DNN (Deep Neural Network) processing
required for the next generation of intelligent IP cameras. Fabricated in
advanced 10nm process technology, it achieves an industry-leading combination
of low-power and high-performance in both human vision and computer vision
applications.
The CV22S’s CVow
TM
architecture provides computer vision processing at full 4K
@ 30fps, to enable image recognition over long distances and with high
accuracy. It includes ecient 4K encoding in both AVC and HEVC video formats,
delivering high-resolution video streaming with very low bitrates to minimize
cloud storage costs. The CV22S’s next-generation ISP (Image Signal Processor)
provides outstanding imaging in low light conditions while HDR (High Dynamic
Range) processing extracts maximum image detail in high contrast scenes,
further enhancing the computer vision capabilities of the chip. It includes a
suite of advanced security features to implement advanced on-device physical
security, including secure boot, TrustZone™, and I/O virtualization. A complete
set of tools is provided to help customers to easily port their own neural
networks onto the CV22S SoC.
°
°
°
°
°
°
°
°
CV22S - Computer Vision SoC
for IP Cameras
CV INTERNAL MEMORY
VIDEO
CODEC
评论1