For its new AI Dashcam announced today, KeepTruckin has selected Ambarella Inc. and its CV22 CVflow edge AI vision system-on-chip (SoC). The fleet management technology company’s latest AI Dashcam uses a single CV22 SoC to provide AI and image processing for the dual-camera system, which integrates one camera for the front advanced driver assistance system (ADAS) and a second RGB-IR camera for the driver-monitoring system (DMS)—both with recording capabilities.

Driver safety is more important than ever for fleets that power the physical economy, according to KeepTruckin, but insurance costs, fatal collisions, and nuclear verdicts are all on the rise. Its pro-active safety platform was engineered to give fleets more control, helping them prevent accidents, protect their drivers, and lower costs.

Founded in 2013 by CEO Shoaib Makani, CTO Ryan Johns, and COO Obaid Khan, KeepTruckin’s hardware and cloud-based software are designed to help companies improve the safety and efficiency of their fleet operations. With one platform spanning video-based driver safety, electronic logging device compliance, GPS tracking, dispatch, and fuel and maintenance, the company provides an integrated fleet management system for customers from small trucking companies to Fortune 500 enterprises. It has raised $450 million from the likes of GV (formerly Google Ventures), Index Ventures, IVP, Scale Venture Partners, Greenoaks, and G2 Venture Partners.

Led by Fermi Wang, President and CEO, Ambarella’s products are used in a variety of human and computer vision applications including video security, ADAS, electronic mirror, drive recorder, driver/cabin monitoring, autonomous driving, and robotics applications. The company’s low-power SoCs offer high-resolution video compression, advanced image processing, and powerful deep neural network processing to enable intelligent cameras to extract valuable data from high-resolution video streams.

For the AI Dashcam, the Ambarella CV22’s edge AI processing enables KeepTruckin to run its proprietary AI algorithms for real-time high-risk behavior detection and active warnings directly on the small form-factor device with minimal heat dissipation needed.

Front ADAS features enabled by the CV22 include warnings for close following, lane departures, forward collisions, speeding, and traffic violations. Using the same SoC, running multiple simultaneous neural network models, the in-cabin camera’s DMS capabilities include monitoring for driver fatigue, distraction, and policy violations such as contextual cell phone use or seatbelt monitoring, in combination with data from the front camera.

“KeepTruckin’s AI Dashcam leverages Ambarella’s industry-leading edge AI and vision processing performance to deliver advanced AI-based features that detect high-risk behavior with outstanding accuracy and efficiency,” said Jairam Ranganathan, SVP of Product at KeepTruckin. “Our continued fleet-management innovation is enabled by Ambarella’s scalable range of CVflow AI vision SoCs, which are all supported by a common, robust SDK, enabling a platform approach to our product development.”

The AI Dashcam is connected to the KeepTruckin Vehicle Gateway, which uploads the pre-analyzed data, video, and still images to the company’s cloud-based fleet management software in real-time. The CV22 SoC integrates Ambarella’s image signal processor, which provides 1440-pixel videos across all lighting conditions. Its on-chip H.264/H.265 encoding reduces transmission bandwidth and storage costs.

KeepTruckin can easily upload additional features to the CV22 via over-the-air software updates to deliver incremental value to clients that invest in the platform. In addition, its model training becomes increasingly more precise due to its in-house safety team assessing quality in real-time, adding additional risk context and providing input that makes development cycles shorter.

“Maximizing fleet safety and productivity is one of the keys to a successful, growing global economy,” said Ambarella’s Wang. “By partnering with KeepTruckin to add more intelligence into commercial vehicles, we can help these businesses prevent accidents, protect drivers, and lower operating costs.”

Ambarella says it has engineered the CVflow AI architecture to provide significant computer-vision performance with very low power consumption, which increases reliability and efficiency to run more models in parallel—leading to greater detection and visibility all around. The architecture’s set of CV tools helps customers like KeepTruckin port their own neural networks and includes support for industry-standard machine learning frameworks such as PyTorch, ONNX, Caffe, and TensorFlow.