RV1106 is a highly integrated vision processor SoC for IPC, especially for AI related application.
It is based on single-core ARM Cortex-A7 32-bit core which integrates NEON and FPU. There is a 32KB I-cache and 32KB D-cache and 128KB unified L2 cache. The build-in NPU supports INT4/INT8/INT16 hybrid operation and computing power is up to 0.5TOPs. In addition, with its strong compatibility, network models based on a series of frameworks such as TensorFlow/MXNet/PyTorch/Caffe can be easily converted.
RV1106 introduces a new generation totally hardware-based maximum 5-Megapixel ISP (image signal processor). It implements a lot of algorithm accelerators, such as HDR, 3A, LSC, 3DNR, 2DNR, sharpening, dehaze, gamma correction and so on. Cooperating with two
MIPI CSI (or LVDS) and one DVP (BT.601/BT.656/BT.1120) interface, users can build a system that receives video data from 3 camera sensors simultaneous. The video encoder embedded in RV1106 supports H.265/H.264 encoding. It also supports multi-stream encoding. 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. To accelerate video processing, an intelligent video engine with 22 calculation units is also embedded.
RV1106 has a build-in 16-bit DRAM DDR3L capable of sustaining demanding memory bandwidths. It also integrated build-in RTC, POR, audio codec and MAC PHY.
45229182-6d51-4a18-99df-7892a6cd24de-1675393009552.png
新一代机器视觉方案RV1106及RV1103,两颗芯片在NPU、ISP、视频编码、音频处理等性能均有显著升级,具有高集成度、高性价比、低待机功耗的特点。RV1106及RV1103为普惠型方案,旨在助力更多行业伙伴高效实现机器视觉产品的研发及落地。
b839ff3e-40dc-4d60-9397-efdf50c0cd34-14d748dc3ca836cdb5fd57fd9f1e473.png