OUR PARTNERS
IMAGE
PROCESSING
Access to Ambarella information and technology is submitted to prior approval from Ambarella.
Aftermarket & Dealer-Fit
CV5A
Featuring 8K image processing, video encoding / decoding, and CVflow® computer vision processing, CV5A targets an array of automotive applications, including multi-channel drive recorders / data loggers and multi-camera aftermarket ADAS systems.
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: multi-exposure line-interleaved HDR, hardware dewarping engine, electronic image stabilization (EIS), multiple camera support, LED flicker mitigation, 3D motion-compensated temporal filtering (MCTF), and superior low-light processing
CV52A
Equipped with 6K image processing, video encoding / decoding, and CVflow® computer vision processing, the CV52A SoC is an ideal solution for the next generation of 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 CV2A SoC includes dedicated stereovision acceleration, 4KP60 / 8MP60 video encoding, and CVflow® computer vision processing in a single, low-power design.
Key features
-
Stereo processing to enable generic obstacle detection, terrain modeling, and more
-
CNN- / DNN-based monocular processing to enable classification, tracking, and more
-
CNN toolkit for easy porting with Caffe, PyTorch, TensorFlow, and ONNX
-
8MP60 video performance
-
Advanced image processing: multi-exposure line-interleaved HDR, hardware dewarping engine, electronic image stabilization (EIS), support for multiple cameras, 3D motion-compensated temporal filtering (MCTF), and exceptional low-light processing
-
Target applications: multi-channel drive recorder, aftermarket ADAS, driver / in-cabin monitoring system (DMS / CMS), and single- / multi-channel electronic mirror
CV22A
The CV22A chip delivers advanced image processing, 12MP30 video encoding, and CVflow® computer vision performance.
Key features
-
CNN- / DNN-based processing to enable detection, classification, tracking, and more
-
Computer vision processor
-
CNN toolkit for easy porting with Caffe, PyTorch, TensorFlow, and ONNX
-
Advanced image processing: multi-exposure line-interleaved HDR, hardware dewarping engine support, electronic image stabilization (EIS), 3D motion-compensated temporal filtering (MCTF), and superior low-light processing
-
12MP30 video performance
-
Target applications: multi-channel drive recorder, single- / multi-channel electronic mirror, aftermarket ADAS, driver / in-cabin monitoring system (DMS / CMS)
CV25A
The CV25A chip delivers advanced image processing, 8MP30 video encoding, and CVflow® computer vision performance, allowing the implementation of computer vision algorithms such as forward collision warning, lane departure warning, driver monitoring, and more.
Key features
-
CNN- / DNN-based processing to enable detection, classification, tracking, and more
-
CNN toolkit for easy porting with Caffe, PyTorch, TensorFlow, and ONNX
-
Advanced image processing: multi-exposure line-interleaved HDR, hardware dewarping engine support, electronic image stabilization (EIS), 3D motion compensated temporal filtering (MCTF), and superior low-light processing
-
8MP30 video performance
-
Target applications: multi-channel drive recorder, aftermarket ADAS, single- / dual-channel electronic mirror, and driver / in-cabin monitoring system (DMS / CMS)
CV28A
The CV28A SoC combines image processing, 8MP30 video encoding, and CVflow® computer vision performance.
Key features
-
CNN- / DNN-based processing to enable detection, classification, tracking, and more
-
CNN toolkit for easy porting with Caffe, PyTorch, TensorFlow, and ONNX
-
Advanced image processing: multi-exposure line-interleaved HDR, hardware dewarping engine support, electronic image stabilization (EIS), 3D motion compensated temporal filtering (MCTF), and superior low-light processing
-
8MP30 video performance
-
Target applications: multi-channel drive recorder, aftermarket ADAS, single- / dual-channel electronic mirror, and driver / in-cabin monitoring system (DMS / CMS)
H22A
H22A delivers a highly efficient 12MP30 encoder / decoder in hardware along with an industry-leading image signal processor (ISP), providing outstanding imaging in low-light conditions along with high dynamic range (HDR) processing for maximum detail in high-contrast scenes.
Key features
-
12MP30 H.264 / H.265 video compression
-
Flexible multi-stream capability
-
Multi-sensor support
-
Superior image processing: multi-exposure line-interleaved HDR, hardware dewarping engine, electronic image stabilization, 3D motion-compensated noise reduction (MCTF), and exceptional low-light processing
-
Target applications: multi-channel drive recorder and driver monitoring system (driver distraction / drowsiness detection)
H32
The H32 SoC combines image / video processing, 8MP30 video encoding, and a quad-core processor in a single, low-power design, making it an ideal choice for aftermarket dash cameras.
Key features
-
8MP30 video performance
-
Superior image processing: multi-exposure line-interleaved HDR, hardware dewarping engine, electronic image stabilization, 3D motion-compensated noise reduction (MCTF), and exceptional low-light processing
-
Flexible multi-streaming capability
A12A
The A12A chip provides support for video recording through the front windshield, rear window, and inside the vehicle cabin, delivering single-channel quad HD (4MP, 1440p) at 30fps, full 1080p HD at up to 60 fps, and dual-channel quad HD performance.
Key features
-
Full HD @ 60fps or quad HD 4MP @ 30fps
-
Two-channel quad HD @ 30fps
-
Electronic image stabilization (EIS)
-
Superior image quality with advanced night vision for low-light conditions, full-resolution oversampling, WDR, HDR, and more
-
ADAS application support
windshield, rear window, and inside the vehicle cabin, delivering single-channel quad HD (4MP, 1440p) at 30fps, full 1080p HD at up to 60 fps, and dual-channel quad HD performance.
Security
Intelligent devices for enhanced safety
Ambarella processors power the world’s security cameras—in homes, businesses, airports, intersections, and more. Designed specifically for devices at the edge, Ambarella chips offer a unique combination of computer vision performance, industry-leading image processing, low-bitrate streaming at high resolutions, and low power consumption—all on a single, embedded architecture.
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
-
Secure boot with TrustZone® and secure memory, true random number generator (TRNG), one-time programmable memory (OTP), DRAM scrambling and virtualization
CV28M
The 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, true random number generator (TRNG), one-time programmable memory (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 professional 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
Consumer
Delivering smart cameras to the masses
Ambarella has a rich history of turning cutting-edge processors into best-selling, mass-market products. As consumer trends have shifted over time, our commitment to quality has never wavered, starting with HD and UHD video resolutions, low-power architectural designs, industry-leading AVC/HEVC encoding, and must-have video features such as electronic image stabilization (EIS), and continuing with the latest in computer vision processing. Our chips enable the development of affordable consumer devices—drones, wearables, aftermarket dash-cams, and more—with high-resolution video capabilities, efficient compression, low-power operation, and onboard smart features such as intelligent editing and person-of-interest tracking.
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
CV2
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
CV22
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
CV25
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
CV28
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 pipe 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 pipe for drone optical flow, 360° cameras, and other multi-sensor applications
A12S
The A12S sports camera SoC delivers an advanced image sensor pipeline, an H.264 (AVC) encoder, and a powerful Arm® Cortex®-A9 CPU for advanced analytics and user applications, enabling the development of high-performance 360° (VR) and action cameras.
Key Features
-
Arm® Cortex®-A9 CPU up to 792 MHz
-
Fastboot ThreadX / Linux dual OS
-
Up to 32 MPixel/s still picture capture
-
4KP30, 1920x1080p120 and 1280x720p240 encoding (or equivalent)
-
Simultaneous second stream
-
Advanced electronic image stabilization (EIS) and tilt correction
-
Dual processing pipe (for 360° cameras)
-
Wireless connectivity and video streaming options
A12W
Ambarella’s A12W processor is ideal for social and professional wearable camera designs, offering an advanced image sensor processing (ISP), an H.264 encoder, and a powerful Arm® Cortex® -A9 CPU for advanced analytics and user applications.
Key Features
-
Arm® Cortex®-A9 CPU @ 504 MHz
-
Fastboot ThreadX / Linux dual OS
-
Up to 32 MPixel/s still picture capture
-
1080p60, 2560x1440p15 and WVGAp240 encoding
-
Simultaneous 1080p30 + 720p30 encoding
-
Ultra-low-power performance for extended operation
-
Police on-body camera reference kit available
Automotive
If you are interested in Ambarella’s automotive processors, please contact us.