Ambarella
Access to Ambarella information and technology is submitted to prior approval from Ambarella.
- IoT, Industrial and Robotics
- Security
- Consumer
AI-powered applications often rely heavily on vision capabilities, making Ambarella chips an excellent choice. Amberalla’s sophisticated stereovision technology converts the environment into an intricately detailed 3D space, boosting both safety and performance. With Ambarella’s CVflow® architecture, neural networks are executed in real-time, even under challenging conditions such as high-contrast or low-light scenarios. Ambarella provides precise environmental modeling, low latency, and real-time processing, enabling instant decision-making across diverse applications—from autonomous robots and defect detection on production lines to inventory tracking and access control in buildings. The outcome? AI applications that are smarter, faster, safer, and more efficient than ever.
N1
Ambarella’s N1 system on chip (SoC) provides industry-leading AI performance per watt for neural network computation in combination with a GVP, an advanced image processor, a dense stereo and optical flow engine, 16 Arm® Cortex®-A78AE CPUs, and a GPU, in a single SoC.
Key Features
- Neural network (NN)-based processing to support multimodal large language models (LLMs) along with image detection, classification, tracking, and more
- Neural vector processor (NVP) with industry-leading AI performance per watt
- General vector processor (GVP) for offloading classical computer vision, radar processing, and floating-point intensive algorithms
- Fabricated in an advanced 5 nm process technology, the N1 is an ideal platform for implementing industrial robotics, smart cities, intelligent healthcare imaging and diagonostics, multi-camera AI processing hub, edge AI servers running multi-modal LLMs, and autonomous fleet telematics
CV72S
Ambarella’s CV72S system on chip (SoC) provides 4KP60+ image processing, video encoding / decoding, and CVflow® computer vision processing in a single, low-power design. Fabricated in advanced 5 nm process technology, it achieves an industry-leading combination of low power and high performance in both human vision and computer vision applications.
Key Features
- 4KP60+ video performance with flexible multi-streaming capability
- Computer vision toolkit to ease the porting of CNNs trained using frameworks such as Caffe, PyTorch, TensorFlow, or ONNX, as well as traditional computer vision code using Ambarella primitive language
- Target applications include Internet protocol (IP) cameras, consumer and industrial robots, sports / action cameras, video conferencing cameras, and drones
CV5S
Ambarella’s CV5S provides 8K image processing, video encoding / decoding, and CVflow® computer vision processing in a single, low-power design. Fabricated in advanced 5 nm process technology, CV5S achieves power consumption below 4W for 8K video recording at 30 fps—suited for IP, robotics, and machine vision applications.
Key Features
- 8KP30 video encoding performance with multi-streaming capability
- CNN toolkit for easy porting of neural networks implemented in Caffe, TensorFlow, PyTorch, or ONNX frameworks
- Superior low-light processing
CV52S
Ambarella’s CV52S provides 4K image processing, video encoding / decoding, and CVflow® computer vision processing in a single, low-power design while achieving power consumption below 3W for 4KP60 video recording with advanced AI processing at 30 fps.
Key Features
- 4KP60 encoding with multiple substreams video performance
- CNN toolkit for easy porting of neural networks implemented in Caffe, TensorFlow, PyTorch, or ONNX frameworks
- Enhanced secure boot with TrustZone® and secure memory, true random number generator (TRNG), one-time programmable memory (OTP), Arm trusted base system architecture (TBSA) compliance, DRAM scrambling, and virtualization
- 4K IP cameras with advanced artificial intelligence (AI), intelligent traffic systems (ITS) cameras, machine vision and robotics applications
CV2S
Designed for high-performance surveillance cameras with advanced computer vision features, the CV2S chip delivers industry-leading image processing, stereovision capabilities, 4KP60 video encoding, along with CVflow® computer vision architecture.
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
- Advanced image processing with HDR, dewarping, EIS, MCTF, and more
- Secure boot with TrustZone® and secure memory, true random number generator (TRNG), one-time programmable memory (OTP), DRAM scrambling and virtualization
CV22S
Ambarella’s CV22S SoC combines advanced image processing, 4KP30+ video encoding, powerful CVflow® computer vision performance, and a full suite of cybersecurity features to enable the next generation of intelligent IP camera designs.
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
- High-efficiency video encoding up to 4KP30+ performance
- Support for visual odometry and simultaneous location and mapping (SLAM) algorithm implementation
- Advanced image processing with HDR, dewarping, EIS, MCTF, and more
- Secure boot with TrustZone® and secure memory, true random number generator (TRNG), one-time programmable memory (OTP), DRAM scrambling and virtualization
CV25S
The CV25S chip powers the next generation of affordable and intelligent home monitoring and professional surveillance solutions on the edge, combining advanced image processing, high-resolution video encoding, CVflow® computer vision performance, and a full suite of cybersecurity features.
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
- Advanced image processing with HDR, dewarping, EIS, MCTF, superior low-light imaging, and more
- High-efficiency video encoding up to 4KP30+ performance
- Advanced image processing with HDR, dewarping, EIS, MCTF, and more
- Secure boot with TrustZone® and secure memory, true random number generator (TRNG), one-time programmable memory (OTP), DRAM scrambling and virtualization
CV28M
Ambarella's 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
Ambarella‘s processors drive security cameras around the world, from homes and businesses to airports and intersections. Specifically designed for edge devices, Ambarella chips provide a unique blend of computer vision performance, top-tier image processing, high-resolution low-bitrate streaming, and low power consumption—all within a single embedded architecture.
CV75S
Ambarella’s CV75S system on chip (SoC) provides 4KP30+ image processing, video encoding / decoding, and CVflow® computer vision processing in a single, low-power design. Fabricated in advanced 5 nm process technology, it achieves an industry-leading combination of low power and high performance in both human vision and computer vision applications.
Key Features
- 4KP30+ video performance
- CNN toolkit for easy porting of neural networks implemented in Caffe, TensorFlow, PyTorch, or ONNX frameworks
- Target applications include AI-enabled security cameras, consumer and industrial robots, video conferencing cameras, intercom and access control cameras, and more
CV72S
Ambarella’s CV72S system on chip (SoC) provides 4KP60+ image processing, video encoding / decoding, and CVflow® computer vision processing in a single, low-power design. Fabricated in advanced 5 nm process technology, it achieves an industry-leading combination of low power and high performance in both human vision and computer vision applications.
Key Features
- 4KP60+ video performance with flexible multi-streaming capability
- Computer vision toolkit to ease the porting of CNNs trained using frameworks such as Caffe, PyTorch, TensorFlow, or ONNX, as well as traditional computer vision code using Ambarella primitive language
- Target applications include Internet protocol (IP) cameras, consumer and industrial robots, sports / action cameras, video conferencing cameras, and drones
CV5S
Ambarella’s CV5S provides 8K image processing, video encoding / decoding, and CVflow® computer vision processing in a single, low-power design. Fabricated in advanced 5 nm process technology, CV5S achieves power consumption below 4W for 8K video recording at 30 fps—suited for IP, robotics, and machine vision applications.
Key Features
- 8KP30 video encoding performance with multi-streaming capability
- CNN toolkit for easy porting of neural networks implemented in Caffe, TensorFlow, PyTorch, or ONNX frameworks
- Superior low-light processing
CV52S
Ambarella’s CV52S provides 4K image processing, video encoding / decoding, and CVflow® computer vision processing in a single, low-power design while achieving power consumption below 3W for 4KP60 video recording with advanced AI processing at 30 fps.
Key Features
- 4KP60 encoding with multiple substreams video performance
- CNN toolkit for easy porting of neural networks implemented in Caffe, TensorFlow, PyTorch, or ONNX frameworks
- Enhanced secure boot with TrustZone® and secure memory, true random number generator (TRNG), one-time programmable memory (OTP), Arm trusted base system architecture (TBSA) compliance, DRAM scrambling, and virtualization
- 4K IP cameras with advanced artificial intelligence (AI), intelligent traffic systems (ITS) cameras, machine vision and robotics applications
CV2S
Designed for high-performance surveillance cameras with advanced computer vision features, the CV2S chip delivers industry-leading image processing, stereovision capabilities, 4KP60 video encoding, along with CVflow® computer vision architecture.
Key Features
- CNN- / DNN-based processing: detection, classification, tracking, and more
- Dedicated CVflow computer vision processor
- Tools for high- and low-level algorithm development
- Dedicated hardware for stereo processing
- CNN toolkit for easy porting with Caffe, TensorFlow, and ONNX
- Advanced image processing, with HDR, dewarping, EIS, MCTF, superior low-light imaging, and more
- High-efficiency video encoding up to 4KP60 performance
- Secure boot with TrustZone® and secure memory, true random number generator (TRNG), one-time programmable memory (OTP), DRAM scrambling and virtualization
CV22S
Ambarella’s CV22S SoC combines advanced image processing, 4KP30+ video encoding, powerful CVflow® computer vision performance, and a full suite of cybersecurity features to enable the next generation of intelligent IP camera designs.
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
- Advanced image processing with HDR, dewarping, EIS, MCTF, superior low-light imaging, and more
- High-efficiency video encoding up to 4KP30+ performance
- Secure boot with TrustZone® and secure memory, true random number generator (TRNG), one-time programmable memory (OTP), DRAM scrambling and virtualization
CV25S
The CV25S chip powers the next generation of affordable and intelligent home monitoring and professional surveillance solutions on the edge, combining advanced image processing, high-resolution video encoding, CVflow® computer vision performance, and a full suite of cybersecurity features.
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
- Advanced image processing with HDR, dewarping, EIS, MCTF, superior low-light imaging, and more
- High-efficiency video encoding up to 4KP30+ performance
- Advanced image processing with HDR, dewarping, EIS, MCTF, and more
- Secure boot with TrustZone® and secure memory, true random number generator (TRNG), one-time programmable memory (OTP), DRAM scrambling and virtualization
CV28M
Ambarella's 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
S6LM
Targeting the next generation of professional and home monitoring applications, including video doorbells and battery-powered cameras, the S6LM includes Ambarella’s latest high dynamic range (HDR) and low-light processing technology, highly efficient 5MP30 + 720p30 + 5MP1 H.264 and H.265 encoding, multi-streaming, on-chip 360-degree dewarping, cyber-security features, and a quad-core Arm® CPU. Fully software compatible with Ambarella’s CVflow® family of chips, the S6LM addresses applications that require the highest image quality, lowest-power operation, and cybersecurity protection, while remaining affordable for cost-conscious markets.
Key Features
- Advanced cybersecurity features
- Up to 400 MPixel/s input rate
- Multi-exposure line-interleaved HDR
- Superior low-light processing
- Flexible low-power platform
S5L
The S5L chip is designed for professional, consumer, and battery-powered IP cameras, offering 4K high dynamic range (HDR) processing, multi-streaming, on-chip lens distortion correction, advanced low-light performance, and dual video inputs.
Key Features
- 64-bit Arm® quad-core Cortex®-A53 CPU up to 1.0 GHz with L2 cache
- Advanced image processing with HDR, lens distortion correction, EIS, MCTF, and more
- H.265 and H.264 video compression up to 4KP30 performance
S3L
Featuring the H.265 compression standard, the S3L SoC targets HD IP cameras up to 5M, while the S3LM SoC is designed for small form-factor consumer H.265 cloud cameras up to 3M.
Key Features
- Arm® Cortex®-A9 CPU
- Advanced image processing with HDR, hardware dewarp for 180˚ panorama, and more
- H.265 and H.264 video compression
- Flexible multi-streaming
S2L
Designed for both consumer and professional applications, the S2L family brings advanced high dynamic range (HDR) processing, wide-angle viewing, high resolution video up to 5MP30 (3MP30 for S2LM), and on-board analytics into the mainstream.
Key Features
- Arm® Cortex®-A9 CPU
- Advanced image processing
- Smart-AVC streaming as low as 600 Kbps for 1080p30
- Flexible multi-streaming
Ambarella has a long-standing tradition of transforming cutting-edge processors into best-selling, mass-market products. As consumer trends have evolved, Ambarella’s dedication to quality has remained steadfast. Starting with HD and UHD video resolutions, low-power architecture, industry-leading AVC/HEVC encoding, and essential video features like electronic image stabilization (EIS), Ambarella has now advanced to the forefront of computer vision processing. Ambarella’s chips facilitate the creation of affordable consumer devices—drones, wearables, aftermarket dash-cams, and more—offering high-resolution video, efficient compression, low-power operation, and smart onboard features such as intelligent editing and person-of-interest tracking.
CV75A
Ambarella’s CV75A system on chip (SoC) provides 8MP60 image processing, video encoding / decoding, and CVflow® computer vision processing in a single, low-power design. Fabricated in advanced 5 nm process technology, it achieves an industry-leading combination of low power and high performance in both human vision and computer vision applications.
Key Features
- 8MP60 video performance
- CNN toolkit for easy porting of neural networks implemented in Caffe, TensorFlow, PyTorch, or ONNX frameworks
- Target applications include multi-channel drive recorders / data loggers, multi-camera aftermarket advanced driver assistance systems (ADAS), single- / multi-channel electronic mirrors, driver / in-cabin monitoring systems (DMS / CMS)
CV5
With 8K image processing, video encoding / decoding, and CVflow® computer vision processing, the CV5 SoC is an ideal solution for the next generation of high-resolution and high frame-rate action / sports cameras, VR cameras, and consumer / industrial drones.
Key Features
- CNN / DNN-based processing: detection, classification, and more
- CNN toolkit for easy porting of neural networks implemented in Caffe, TensorFlow, PyTorch, or ONNX frameworks
- 8KP60 video performance
- Advanced image processing, including HDR, dewarping, EIS, MCTF, and more
CV52
Equipped with 6K image processing, video encoding / decoding, and CVflow® computer vision processing, the CV52 SoC is an ideal solution for the next generation of sports, robotics, drone, and VR cameras, as well as multi-channel drive recorders and multi-camera aftermarket ADAS systems.
Key Features
- 6KP30 / 4KP90 video performance
- CNN toolkit for easy porting of neural networks implemented in Caffe, TensorFlow, PyTorch, or ONNX frameworks
- CNN / DNN based processing: detection, classification, and more
- Advanced image processing, including HDR, dewarping, EIS, MCTF, and more
CV2A
The CV2 chip delivers industry-leading image processing, 4KP60+ video encoding, and an optimized CVflow® computer vision architecture for high-performance consumer camera systems.
Key Features
- CNN / DNN-based processing: detection, classification, tracking, and more
- Dedicated CVflow computer vision processor
- Tools for high and low-level algorithm development
- Dedicated hardware for stereo processing
- CNN toolkit for easy porting with Caffe, TensorFlow, and ONNX
- Advanced image processing, including HDR, dewarping, EIS, MCTF, and more
- High-efficiency video encoding up to 4KP60+ performance
CV22A
The CV22 chip combines advanced image processing, 4KP60+ video encoding, and CVflow® computer vision performance to enable the next generation of intelligent sports, drone, wearable, and 360° (VR) cameras.
Key Features
- 64-bit Arm® quad-core Cortex®-A53 CPU up to 1.0 GHz
- ThreadX and Linux OS support
- CNN / DNN-based processing: detection, classification, tracking, and more
- Dedicated computer vision processor
- Tools for high- and low-level algorithm development
- CNN toolkit for easy porting with Caffe, TensorFlow, and ONNX
- Advanced image / video processing, including HDR, dewarping, EIS, MCTF, low-light imaging, and more
- Multi-sensor and video processing support for 360° (VR) cameras, stereo cameras, and optical flow for drones
- H.265 and H.264 video compression up to 4KP60+ performance
CV25A
Designed for wearable, sports, drone, and 360° (VR) cameras with onboard intelligence, the CV25 chip combines state-of-the-art computer vision technology with advanced image processing in a single, low-power design.
Key Features
- 64-bit Arm® quad-core Cortex®-A53 CPU up to 1.0 GHz
- CNN / DNN-based processing: detection, classification, tracking, and more
- Dedicated computer vision processor
- Tools for high- and low-level algorithm development
- CNN toolkit for easy porting with Caffe, TensorFlow, and ONNX
- Advanced image / video processing, including HDR, dewarping, EIS, MCTF, and more
- H.265 and H.264 video compression up to 4KP30 performance
CV28A
Ambarella’s CV28A SoC combines image processing, 8MP30 video encoding / decoding, and CVflow® computer vision processing in a single, low-power design, making it an ideal choice to power the next generation of intelligent automative devices.
Key Features
- Dual-core Arm® Cortex®-A53 up to 1 GHz
- CNN / DNN-based processing: detection, classification, tracking, and more
- CNN toolkit for easy porting with Caffe, TensorFlow, and ONNX
- 8MP30 maximum encoding / decoding performance
H32
Ambarella’s H32 SoC is ideal for aftermarket dash cameras, wearable applications, and high-performance action cameras, offering advanced image / video processing, 8MP30 video encoding / decoding, and a quad-core processor for the implementation of application code and computer vision algorithms.
Key Features
- Arm® quad-core Cortex®-A53 CPU up to 1 GHz
- Multiple OS support: ThreadX, Linux, ThreadX + Linux
- 8MP30 video encoding (HEVC / AVC)
- Multi-exposure line-interleaved HDR sensors
- Electronic image stabilization (EIS)
H22
Targeting a new generation of connected drones, sports, and 360° (VR) cameras, the H22 delivers up to 4K video recording at 60fps (or equivalent) while streaming a second, live, mobile-resolution video over a WiFi network for preview or sharing.
Key Features
- Arm® quad-core Cortex®-A53 CPU up to 1 GHz
- Fastboot ThreadX / Linux dual OS
- 4KP60 video encoding (HEVC / AVC)
- High dynamic range multi-exposure capture up to 4KP30
- Simultaneous second stream
- 3D electronic image stabilization (EIS) with 6-axis correction (translational, pitch, yaw, and roll) and shutter correction
- Dual processing pipeline for drone optical flow, 360° cameras, and other multi-sensor applications
H2
The H2 SoC is engineered to deliver pristine video during fast action shots as well as smooth slow-motion playback, offering 10-bit high dynamic range (HDR) video processing, high-ISO DSLR-quality photography, and advanced 3D electronic image stabilization, significantly reducing the negative effects of movement during filming.
Key Features
- Arm® quad-core Cortex®-A53 CPU up to 1 GHz
- Fastboot ThreadX / Linux dual OS
- 4KP90 video encoding (AVC)
- 4KP60 10-bit video encoding (HEVC-10)
- High dynamic range multi-exposure capture up to 4KP60
- Simultaneous second stream
- 3D electronic image stabilization (EIS) with 6-axis correction (translational, pitch, yaw, and roll) and shutter correction up to 4KP60
- Dual processing pipeline for drone optical flow, 360° cameras, and other multi-sensor applications
Links
Follow us on social channels
©Copyright 2024 Macnica ATD Europe Inc.