Products / AI Cameras

Bringing artificial intelligence to the edge.

AI-powered applications are often highly vision dependent, making them ideally suited for Ambarella chips. Our advanced stereovision processing transforms the environment into a fully 3-dimensional world with exquisite detail, enhancing both safety and performance, while our CVflow® architecture delivers real-time execution of neural networks in a variety of challenging conditions, including high-contrast or low-light scenes. We deliver highly accurate environmental modeling, low latency, and real-time processing for instant decision-making in a wide range of applications—controlling an autonomous robot, identifying a defect on a production line, tracking inventory, managing access to buildings, and much more. The result? AI applications that are simply smarter, faster, safer, and more efficient than ever before.

CV2

Designed for accurate 3D environmental modeling and real-time neural network performance, the CV2 chip enables advanced robotics and industrial applications, including autonomous robots.

Key features

  • CNN / DNN-based processing: detection, classification, tracking, and more
  • Dedicated hardware for stereo processing
  • Dedicated CVflow® computer vision processor
  • Tools for high and low-level algorithm development
  • CNN toolkit for easy porting with Caffe, TensorFlow, and ONNX
  • Support for global shutter sensors and high-frame-rate capture
  • Support for visual odometry and Simultaneous Location And Mapping (SLAM) algorithm implementation
  • Advanced image processing with HDR, dewarping, EIS, MCTF, and more
  • Cybersecurity: Secure Boot, TrustZone™, and I/O Virtualization

CV22

Ambarella’s CV22 SoC combines advanced image processing with our powerful CVflow® computer vision architecture to deliver the next generation of intelligent robotics and industrial applications.

Key features

  • CNN / DNN-based processing: detection, classification, tracking, and more
  • Dedicated CVflow computer vision processor
  • Tools for high and low-level algorithm development
  • CNN toolkit for easy porting with Caffe, TensorFlow, and ONNX
  • Support for global shutter sensors and high-frame-rate capture
  • Support for visual odometry and Simultaneous Location And Mapping (SLAM) algorithm implementation
  • Advanced image processing with HDR, dewarping, EIS, MCTF, and more
  • Cybersecurity: Secure Boot, TrustZone™, and Key Storage

CV25

The CV25 chip combines advanced image processing and real-time CVflow® computer vision performance for intelligent industrial/robotics applications.

Key features

  • CNN / DNN-based processing: detection, classification, tracking, and more
  • Dedicated CVflow computer vision processor
  • Tools for high and low-level algorithm development
  • CNN toolkit for easy porting with Caffe, TensorFlow, and ONNX
  • Support for global shutter sensors and high-frame-rate capture
  • Support for visual odometry and Simultaneous Location And Mapping (SLAM) algorithm implementation
  • Advanced image processing with HDR, dewarping, EIS, MCTF, and more
  • Cybersecurity: Secure Boot, TrustZone™, and Key Storage

CV28M

Our CV28M SoC is designed for intelligent applications at the edge, including smart home security, retail monitoring, consumer robotics, and occupancy monitoring. The chip’s high-performance CVflow® architecture provides deep neural network (DNN) computer vision processing and 4KP30 video encoding, enabling an array of computer vision-based devices.

Key features

  • CVflow® computer vision engine
  • CNN / DNN inference acceleration for detection, classification, and more
  • CNN toolkit for easy porting with Caffe, TensorFlow, and ONNX
  • Up to 4KP30 video performance
  • Advanced image processing with HDR, dewarping, EIS, MCTF, superior low-light imaging, and more
  • Secure boot with TrustZone® and secure memory, TRNG, OTP, DRAM scrambling and virtualization