Camera SoC targets new class of smart edge devices
The CV28M CVflow processor combines advanced image processing, high-resolution video encoding, and the company’s CVflow computer vision processing in a single, low-power design. The CV28M’s highly efficient artificial intelligence (AI) processing architecture, says the company, provides the flexibility required to enable a new class of smart edge devices for applications including smart home security, retail monitoring, consumer robotics, and occupancy monitoring.
“All around us, devices are becoming smarter, and with our newest CV28M SoC, our customers can develop a new generation of intelligent sensing cameras for a variety of new applications,” says Chris Day, vice president of marketing and business development at Ambarella. “In privacy-sensitive applications – such as monitoring retail stores, workplaces, rental properties, or the elderly at home – edge-based AI processing can support intelligent monitoring and fast decision-making without the requirement to record or stream video to the cloud.”
The CV28M, says the company, provides the AI performance to make all decisions in the camera, preserving privacy and avoiding heavy video processing running on back-end servers. For IP security cameras, the device features AI-based rate control to optimize image quality while reducing video storage and network bandwidth requirements.
In addition, the company’s AI Timelapse scene-aware recording avoids the time needed to scan through video timelines to retrieve moments of interest. In consumer robotics applications, the CV28M can be connected to a wide range of sensors such as visible, structured light, and time-of-flight (ToF) to capture, and then process, the data required for navigation.
The CV28M delivers efficient video encoding in both AVC and HEVC formats. A high-performance image signal processor (ISP) delivers outstanding imaging in low-light conditions, and high dynamic range (HDR) processing extracts maximum image detail in high-contrast scenes, says the company.
The CV28M includes a full suite of advanced cybersecurity features to protect against hacking including secure boot, TrustZone, and I/O virtualization. Fabricated in 10-nm ultralow-power process technology, the CV28M chip is optimized for wire-free camera applications that require long battery life and small form factors.
The CV28M chip shares a common SDK and computer vision (CV) tools with the company’s CV25, CV22, and CV2 CVflow SoC families, simplifying development of cameras with multiple price and performance options. A complete set of CV tools helps users port their own neural networks onto CV28M and includes a compiler, debugger, and support for industry-standard machine learning frameworks such as Caffe and TensorFlow, with extensive guidelines for convolutional neural network (CNN) performance optimizations.
CV28M SoC key features include:
- CVflow architecture with CNN/deep learning support
- 4KP30 AVC and HEVC encoding with multi-stream support
- Dual-core 1 GHz Arm Cortex-A53 with NEON DSP extensions and FPU
- Advanced security features to implement on-device physical security, including secure boot with TrustZone, TRNG, OTP, DRAM scrambling and virtualization
- Lens distortion correction (LDC)
- Multi-channel ISP with up to 320 MPixels/s input pixel rate
- Multi-exposure HDR and wide dynamic range (WDR) processing, with LED flicker mitigation
- SmartAVC and SmartHEVC intelligent rate control for lowest bitrates in security applications
- Triple-sensor video input with high-speed SLVS/MIPI-CSI/LVCMOS interfaces
- Set of interfaces includes Gigabit Ethernet, USB 2.0 host and device, three SD card controllers with SDXC support, and MIPI-DSI/CSI output
- Support for DDR4/LPDDR4/LPDDR4x
- 10 nm process technology
The CV28M is available in a 11 x 12-mm 0.65-pitch BGA. Samples are available now.