Establishing a More Intelligent World

Smart Vision: A Clear, Insightful, and Responsive Way to See the World

Smart Vision: A Clear, Insightful, and Responsive Way to See the World

To better serve global developers across a wide range of industries, HiSilicon offers a range of high-performance chipsets, as well as cutting-edge technologies such as AI and 8K, enabling the construction of versatile development platforms such as smart vision and smart IoT. HiSilicon provides developers with technical training and empowerment, communication platforms, and ecosystem cooperation services by engaging in independent design house (IDH) collaboration, developer community building, and initiating partnerships with universities, improving application development efficiency and nurturing innovation.

83% of the information humans perceive is acquired through their sense of vision, with only 11% absorbed through hearing, which explains why artificial intelligence (AI) breakthroughs are often related to image recognition. Machine vision has a broad range of applications, from manufacturing and security, to consumer electronics and transportation, and commercial cameras increasingly come equipped with AI image recognition capabilities. Meanwhile, visual data has become the most critical source of big data in the intelligent era, accounting for over 80% of personal applications, and more than 70% of industry applications. HiSilicon has worked tirelessly on visual perception for over a decade, and accumulated industry-leading capabilities in such fields as picture quality (PQ) and AI. Our solutions offer professional-level image quality, while also setting the pace for PQ+AI, helping developers extract a wealth of value from video data, and explore groundbreaking product innovations.

Based on vision, AI, and connectivity, the HiSilicon smart vision development platform offers advanced visual processing, AI inference, and low power consumption capabilities, and integrates them into the HiSpark platform. By leveraging this platform, HiSilicon provides optimal image quality and powerful computing capabilities along with low power consumption, while expanding the availability of efficiency-boosting development tools for use in smart homes, consumer cameras, unmanned aerial vehicles (UAVs), and robotics, among other applications.

High image quality and low bit rate
  • Adaptive image enhancement based on AI-powered scene identification delivers improved imaging effects in complex lighting conditions, and ensures high-quality image output in challenging environments with low illumination and backlight.
  • Smart video coding (SVC) technology lowers operation costs, thanks to reduced backhaul bandwidth and storage usage.

Efficient AI and effortless development
  • Heterogeneous high-performance AI and performance, power and area (PPA) computing engines offer support for 1 TOPS computing power and meet the demanding requirements of mainstream scenarios.
  • End-to end (E2E) AI algorithm development and tuning tools simplify algorithm development and improve efficiency.

Low power consumption and multiple ecosystems
  • A mature platform featuring a multitude of commercial applications, countless successful cases, and accumulated development experience
  • Industry-leading IPC+WiFi low-power design
  • Multi-OS architecture (including Linux and HUAWEI LiteOS) and support for HarmonyOS, allowing developers to quickly import products compatible with the Harmony ecosystem

HiSpark Development Kit

HiSpark Development Kit

Visual processing development kit:
Our development kit supports automatic face detection and human profile tracking with a low false positive rate. It also features a unique SVC policy capable of maintaining image quality while cutting average bit rates for 1080p videos in half, substantially reducing backhaul bandwidth and storage usage. In addition, visual perceptual capabilities are provided for a wide range of smart devices, ideal for home security monitors or vehicle dash cameras. For more information about the development board, see

AI inference development kit:
Combining visual perception with AI edge computing, and equipped with NPUs boasting 1 TOPS of neural network computing power, this kit tackles such processes as intelligent recognition and detection on the device side with ease. Compared with cloud processing which must upload visual data to the cloud, our AI inference development kit greatly reduces processing latency and offers substantially lower security and privacy-related risks. This makes it ideal for use in camera products that require strong AI computing power, such as AI cameras, cameras for smart large screen TVs, robotic vacuum cleaner, and facial recognition-based access controls. For more information about the development board, see

Low-power development kit:
This kit combines the vision module's turbo start function with the WiFi module's keepalive mechanism. It features ultra-long standby times and provides visual perceptual capabilities for battery-powered smart home devices, such as smart doorbells, smart peepholes, and smart locks.

This site uses cookies. By continuing to browse the site you are agreeing to our use of cookies. Read our privacy policy