Allwinner V831 AI Full HD Camera SoC Powers Sochip V831 Development Board

In the last year or so, we’ve started to see several camera SoCs with a built-in NPU or SIMD instructions to accelerate face detection, objects detection and so on, starting with the low-resolution Kendryte K210 processor to the 2.5K Ingenic T31 MIPS video processor, or even the 4K capable iCatch V37 camera SoC.

Allwinner introduces several camera processors (V3, V316, S3…) in the past, but none of them included an NPU aka AI accelerator. This has now changed with Allwinner V831 Cortex-A7 Full HD camera SoC also including a small 200 GOPS NPU.

Sochip / Allwinner V831 AI Camera SoC

Allwinner V831

Specifications:

  • CPU – Single-core Arm Cortex-A7 processor @ up to 800 MHz with
    NEON, 32KB L1 instruction cache and 32KB L1 Data cache, 128KB L2 cache
  • AI Accelerator – 0.2 TOPS (200 GOPS) NPU for face recognition, face detection, and “humanoid detection network”
  • System Memory – 64MB on-chip DDR2 RAM
  • Storage
    • SPI NOR flash, SPI NAND flash, eMMC 5.0
    • Booting from SPI NOR, SPI NAND, eMMC, SD, USB, UART, one-key FEL
      hardware boot select pin or eFuse booting sequence
  • Display I/F
    • RGB output up to 320 x 240 @ 60fps
    • BT656 video output up to 1080p @ 30fps
  • Video Subsystem
    • Encoder
      • H.264 BP/MP/HP up to 1080p60 + VGA @ 60Hz
      • H.265 MP up to 1080p90 or 720p30 + 5M @ 30 fps
      • H.264/H.265 supports I/P frame, dual-P frame
      • JPEG snapshot at 1080p @ 60fps independently
      • Maximum 16 regions of interest(ROIs) without encoding for AI
    • Decoder – H.264 BP/MP/HP, H.265 MP, MJPEG/JPEG MP
  • Camera Support
    • 2-lane MIPI CSI input up to 1080p60
    • ISP with 2688×2688 maximum resolution, 2592×1963 @ 30 fps
    • Electronic Image Stabilization Engine (EISE)
    • Lens distortion correction, fisheye, and PTZ calibration
    • 2 Video channels: one up to [email protected], the other up to [email protected]
    • Adjustable 3A functions, including automatic exposure(AE), automatic white balance(AWB) and automatic focus(AF)
    • Highlight compensation, backlight compensation, gamma correction, and color enhancement
    • Defect pixel correction, 2D/3D denoising
  • Audio – 20-bit audio codec, I2S & TDM interfaces
  • Networking – 10/100M Ethernet port with RMII interface
  • USB – 1x USB 2.0 OTG
  • Other Peripherals
    • Up to 54 GPIO interfaces
    • 4x UART, 3x SPI, 1x PWM, 4x I2C/TWI, One-wire interface
    • 2x SD 3.0/SDIO 3.0 for SDXC cards
    • GPADC
    • RTC
  • Security
    • AES, DES, 3DES, and XTS
    • RSA512/1024/2048/3072/4096bits, ECC160/224/256/384/521bits
    • HASH tamper-proofing algorithms implemented by using hardware, including MD5/SHA/HMAC
    • TRNG) and PRNG
    • Integrated 1Kbits e-Fuse storage space
  • Supply Voltages – Core: 0.9V; I/O: 3.3V
  • Package – QFN88, 9 x 9 mm, 0.35 mm pitch

Allwinner V831 is designed for security monitors, driving recorders, police body cameras, and other camera applications that may leverage AI acceleration.

Note we’ve also been told Allwinner V833 is another similar processor capable of handling 4K, but requiring external DRAM. We were unable to find details at this time. [Update: We’ve had the V831/V833 datasheet drop into our inbox this morning, and V833’s MIPI CSI input supports up to 2592 x 1936 @ 30fps RAW data or 4x [email protected], the encoder is still limited to 1080p90. Cortex-A7 clocked at 1.2 GHz with 400 GOPS NPU]

Sochip V831 development board

Sochip V831 Development BoardThe development board is comprised of four parts with the main PCB powered by Allwinner V831 processor, and featuring a Fast Ethernet port, a Micro USB port, a MicroSD slot, and various header, the camera board, the “light” PCB with IR LEDs, and a 2.4″ LCD.

Sochip V831 development board is aimed at companies planning to design an IP camera with AI features and is sold for $440 on Alibaba. The chip itself should just cost a few dollars in volumes.

Software and Documentation

You’ll find some WiP documentation on Sochip’s Wiki. The Linux source code (Tina) is available through the company’s git server, but you’d need to provide an SSH public key (id_rsa.pub), a company name, and email address to Sochip to be able to download the code after approval. Full documents are also available via an FTP server, but again you’d need to obtain a username and password from Sochip.

Thanks to Jon for the tip.

Support CNX Software - Donate via PayPal or become a Patron on Patreon
Advertisements

22
Leave a Reply

avatar
5 Comment threads
17 Thread replies
0 Followers
 
Most reacted comment
Hottest comment thread
5 Comment authors
Jon SmirlmangogeekmangogeekJean-Luc Aufranc (CNXSoft)dgp Recent comment authors
  Subscribe  
newest oldest most voted
Notify of
Member

My sources say V831 $3.00 by the reel and V833 (4K) is $4.50. They also say a more reasonably priced (~$100) V833 dev board is in the works. These chips are brand new and the chip vendors don’t have stock yet. I suspect SDK will be up on github a few weeks from now. Kernel is V4.9. SDK is supposed to be quite similar to the V526 SDK.

This V831 really good bang for the buck at $3.00

The AI unit in the V833 is twice as fast as the one in the V831.

dgp
Guest
dgp

>My sources say V831 $3.00 by the reel and V833 (4K) is $4.50.

I think for context the size of the reel (would have thought these would be a tray..) would be helpful. $3.00 isn’t so good if you have to buy 10,000 of them.

Member

Reels or trays are around 1,000 units. I am not sure how V831/V833 will come from factory. The chip vendors in Shenzhen will buy a reel and then charge you a markup for cutting it into pieces and sending it to you. That markup will be in the range of $0.25/chip in Shenzhen.

I found out that V833 comes in 1,680 chip box and V831 comes in 2,600 unit box. There are ten trays inside each box. So you should be able to get the $3 price by buying a box of 2,600 from Allwinner for $7,800. If that’s too rich, buy from chip vendor in Shenzhen who will break the lots down for you.

dgp
Guest
dgp

>Reels or trays are around 1,000 units.

Trays of similar components are 2080. If you can order 1000 of these and get that price then that’s very good.
Hopefully they didn’t mess around too much and making these work is just a device tree.

Member

V831 SDK is supposed to be very similar to the V536 SDK. You can get the V536 SDK here: https://github.com/lindenis-org?q=536

V831 SDK is only preview, not released yet.

mangogeek
Guest
Member

Has anyone located the pinouts for the V831/V833? They aren’t in the preliminary datasheet.

We are trying to determine if the 1080P BT.656 output on the V831 can be used to drive an LCD. The RGB LCD controller is limited to 240×320. We’re also trying to locate a 480×800 LCD with BT.656 input.

mangogeek
Guest
mangogeek
Guest

I think it can replace K210, it brings us tinalinux, sdio-wifi, 100M net, audio in / out and sd-card, more memory, higher pixel camera(mipi-csi).

Member

The AI unit on both chips (V831/K210) is roughly equal in power (ie not much). I do wish they had made both 64MB and 128MB version like they did with R329.

Have you seen any of the Allwinner AI tools for V831/R329? Can they run a tensorflow model?

mangogeek
Guest

I haven’t found the AI compiler tool

mangogeek
Guest

The new data of V831 shows that the pin definition of the CPU has changed greatly, so it is not recommended to continue to provide the old data to customers. 2020-05-20

Member

When will you have a PCB ready?

mangogeek
Guest

After their announcement, the V831 chip in my hand became a waste product.
I need to be patient and wait for the new official information. :)

Member

Maybe they figured out that this chip needs h.264 decode support. It doesn’t have to be great decode support, just enough to play back saved video.

Advertisements