Artificial intelligent vision chip CV7357/CV7327

Artificial intelligent visual SOC chip for smart driving records, streaming media rear view

2K + 2M professional security imaging quality and 0.5TOPS force @ Int8

Peak performance


Video decoding

H.264 & H.265

Professional security image

Support 2K + 2M, bicompon video processing, HDR wide dynamics, 3D noise reduction, removing, fish eyes



Self-intellectual property tensor processor

Professional security image

Complete Ai Toolchain

Safety chip architecture

High integrated high performance platform

Application Scenarios

Intelligent Security

Intelligent Internet of Things

Intelligent Car

Intelligent New Retail

Smart Robot

Smart Industry

Intelligent Security

Smart camera, wisdom analysis box, face recognition attendance machine, face recognition access control, smart traffic testing provides intelligent visual front end for the security industry.

Intelligent Internet of Things

Smart garbage sorting, smart city, smart campus, wisdom apartment, etc., providing visual calculation target index tracking.

Intelligent Car

Obstacles perception, reverse image, parking unit detection, driver behavior detection warning, rear mounting soft hard integration scheme, etc. For security assist driving to provide immediate power guaranteed.

Intelligent New Retail

Intelligent unmanned retail, product test identification, no blush face payment, etc. Provide key end-side computing links for intelligent retail.

Smart Robot

Educate robots, inspected robots, welcome robots, entertainment robots, etc., providing neural network machine visual capabilities for all industrial automation terminals.

Smart Industry

Intelligent industrial production line defect testing, fault testing warning, smart product sorting, etc., providing safe assistance for intelligent industries, providing production efficiency.


Product Features

CV7357 / CV7327 intelligent driving record, streaming media rear view SOC

Processor core

Single core, Neon accelerated, integrated floating point arithmetic unit (FPU)

Self-developed TPU

Support mainstream neural network frameworks: Caffe, TensorFlow, TensorFlow Lite, Pytorch, ONNX and MXNet

Video encoding performance


H.265 Main Profile

H.264 Baseline/Main/High Profile

JPEG Codec

Support Issue (ROI) Coding

Image video processing

Image Video 90,180,270 degree rotation, Mirror, Flip

Video OSD overlay

3A (AE / AWB / AF) Algorithm

Regional Adaptive Defog

3D Noise Reduction, Detail Enhancement and Sharping

Sensor Belt Wide Diversion and 2 Frame Wide Dynamics

Support 4x4 Pattern RGB-IR sensor

Audio codec performance

Software audio codec protocol(G.711、G.726、ADPCM)

Support audio 3A (AEC, ANR, AGC) function

Video interface


Support for two inputs

Support MIPI, SUB-LVDS, HISPI interface

Support CMOS sensor


Support BT.601 / BT.656 / BT.1120 Output Interface

Support MIPI-DSI output interface

Audio port

Integrated Audio Codec, supports voice input and output

Support I2S / PCM / TDM interface, supports docking external Audio CODEC, providing MCLK clock output


Support security start and upgrade

Hardware plus decryption

Peripheral interface

Integrated POR, RTC,ADC, I2C, SPI, UART, PWM, SDIO 3.0, USB 2.0 Host / Device

Integrated Key Scan, Wiegand

Memory interface

Built-in DRAM



Support EMMC4.5 Interface

Physical specifications

Support multi-level power saving mode

Package form 10mm x 10mm BAG package size,pin spacing: 0.65 mm pitch

About Company


CVTEK is a chip design company that focuses on video surveillance and edge computing technology, with independent research and development of AI TPU operations and SOC chip integration technology. Current research and development field covers SOC chip design, AI TPU processor and tool chain, image Processing algorithms and design, etc., is committed to building a person-purpose intelligent machine visual platform solution to bring enriched value and technological innovation products and services.