Rock development Board RV1103 RV1106 C Camera 38 Board Module AI Vision

Product Advantages

1. Built-in s-developed 4th generation NPU, up to 0.5TOPs computing powerRV1106 and RV1103 adopt Cortex-A7 CPU and high-performance MCU, built-in fourth-generation NPU s-developed by Rock, which has high operation precision andsupports mixed quantization of int4, in8 and int16, in which int8 computing power is 0.5TOPs and int4 computing power can reach 1.0TOPs.2. Built-in s-developed thireneration ISP3.2 to support a variety of image proceing technologiesRV1106 and RV1103 adopt the third generation ISP3.2 developed by Rock, whichsupports 5 million and 4 million pixelsrespectively, andsupports various image enhancement and correction algorithms such as HDR, WDR, multi-stage noise reduction, and so on. In all kinds of complex light scenes, the effect of black light full color and backlight strong light shooting is visible.RV1106 and RV1103 can support 2-3 MI/DVP inputs, which is the preferred scheme for economical vision products.3. Strong ability, high frame rate, low bit rate, small footprintIn terms of video en, Rock RV1106, and RV1103 have super en performance,support intelligent en, and save code stream according to the scene adaptively, saving more than 50% of the code rate compared with the conventional CBR mode, so that the shooting ture is both high-definition and small in size, double the storage space. It alsosupports rich en functions, such as frame sk reference, custom quantization matrix, subjective factors, etc., tother improve the en quality.4. Intelligent audio and sound are clearerIn terms of audio proceing, Rock RV1106, and RV1103 adopt intelligent audio solutions,support echo cancellation, voice noise reduction, cry , abnormal sound , etc.,support high-definition voice, enhance the sound collection, and long-distance sound kup.5. Fast startup nsient response, high performance, and low power consumptionRV1106 and RV1103 are designed with a built-in RISC-V MCU, whichsupports low-power fast startup, supports 250ms fast snapshot, and loads the AI model library at the same time, which can realize face recognition "within 1 second".6. High integrationRV1106 and RV1103 have the built-in Audio codec, PHY, RTC, etc., and provide the QFN package with built-in and BGA package without built-in .