RV1126B Datasheet | Rockchip

Overview RV1126B is a high-performance vision processor So C for machine vision application, especially for AI related application. It is based on quad-core ARM Cortex-A53 64-bit core which integrates NEON and FPU. There is a 32KB I-cache and 32KB D-cache for each core and 512KB unified L2 cache. The build-in NPU Support INT8/INT16 hybrid operation and puting power is up to 3.0TOPs. In addition, with its strong patibility, network models based on a series of frameworks such as Tensor Flow/MXNet/Py Torch/Caffe can be easily converted. RV1126B introduces a new generation totally hardware-based maximum 12-Megapixel ISP (image signal processor) and post processor. It implements a lot of algorithm accelerators, such as HDR, 3A, LSC, 3DNR, 2DNR, sharpening, dehaze, fisheye correction, gamma correction, feature points detection and so on. A maximum 8-Megapixel AI-ISP is also introduced as a plement to traditional ISP, which offers superior spatial denoising performance and enhanced image enhancement effects. Cooperating with two MIPI CSI(or LVDS/Sub LVDS) and one DVP(BT.601/BT.656/BT.1120) interface, users can build a system that receives video data from four camera sensors simultaneously. The video encoder embedded in RV1126B support H.265/H.264 video encoding and the multi-stream encoding is supported also. With the help of this feature , the video from camera can be encoded with higher resolution and stored in local memory and transferred another lower resolution video to cloud storage at the same time. The H.264/H.265 video decoder in RV1126B support 4Kp30 for H.264 and H.265. In addition to the previous high-performance multimedia block, RV1126B also contains rich audio, memory and other peripheral interfaces such as I2C, SPI, PWM and so on. These can help users add more sensors or other peripherals into whole system to improve flexibility and expansibility. RV1126B has high-performance external DRAM(DDR3/DDR3L/DDR4/LPDDR3/LPDDR4/4X) capable of sustaining demanding...