news voir
Chennai (Tamil Nadu) (India), January 4: embedUR Systems, a leader in embedded solutions and edge AI technology, is proud to join STMicroelectronics’ Certified Partner Program.
Also Read | ‘Fas, Thanda’: Kamya Punjabi slams Vivian Zena for underwhelming gameplay in ‘Bigg Boss 18’. Salman Khan tells him ‘game is over’ (watch video).
By leveraging ST’s hardware and software ecosystem, embedUR Systems has developed three advanced edge AI applications for the STM32N6 platform. These applications demonstrate the transformative potential of AI on efficient and compact hardware across a variety of industries.
Through this collaboration, the embedUR system not only optimized the AI model, but also developed, trained, and integrated it to run on ST’s latest STM32N6 microcontroller with the embedded software stack needed for commercialization. . Leveraging STMicroelectronics’ deep platform expertise, embedUR enables innovative edge AI applications that pave the way for innovative industry solutions.
Also read |Bengaluru: A class teacher who had a ‘discord with his wife’ is said to have married a 10th grade girl student and eloped with her. Both have been missing for 40 days.
Edge AI solution
Person detection using image segmentation
embedUR provides a state-of-the-art image segmentation solution for fast detection and classification of individuals. This feature is suitable for applications such as occupancy counting, presence detection, crowd management, and people tracking.
This feature is a combination of:
* Adaptation of YOLACT to the Neural-ART Accelerator™, STM32N6 Neural Processing Unit (NPU): Supporting real-time instance segmentation, YOLACT is optimized for STM32N6 hardware, ensuring low latency and robust performance. Masu.
* Unique optimization technology: embedUR’s advanced quantization strategy reduces model size by nearly 75% while maximizing speed and accuracy, making it ideal for resource-constrained devices.
* Improved image quality with STM32N6’s Image Signal Processor (ISP): This integration ensures reliable performance under varying lighting conditions and allows the solution to run at 71 FPS.
Facial recognition during registration
embedUR’s on-device facial recognition solutions combine security with high speed processing, making them ideal for biometric boarding and keyless entry systems at airports that require rigorous standards of security, privacy, and performance.
Features include:
* embedUR’s UReyeD framework: Enables accurate face detection, keypoint extraction, and embedding generation for fast and accurate recognition.
* Direct enrollment on the device: This feature eliminates the need for external infrastructure, enhancing privacy and simplifying deployment.
* Large database support with rapid identification: Designed for environments with high user throughput, such as access control and public safety.
audio noise removal
embedUR Systems has also created an audio denoising solution that runs on the STM32N6’s Neural-ART accelerator (NPU). It incorporates the superior audio capabilities of the STM32N6 platform and a state-of-the-art audio denoising model to deliver clear audio even in noisy environments. As systems add audio to the text and feed it into the LLM, denoising will increasingly be used to ensure that the LLM is fed the most accurate transcription.
Notable features:
* embedUR selected an award-winning audio denoising model designed to run on the GPU and adapted and optimized it for the STN32N6’s NPU.
*Running models on STM32N6 NPUs reduces power consumption, increases accuracy, and eliminates the latency required to operate audio solutions in a variety of high-demand and low-power environments.
Driving edge AI innovation
“This partnership with STMicroelectronics is a testament to our engineering excellence and ability to quickly and independently stand up AI solutions on literally any edge platform (CPU/GPU/NPU),” said CEO of embedUR Systems. said one Rajesh Subramaniam. “We are proud to demonstrate how efficient and high-performance AI solutions can be delivered on STM32N6 microcontrollers, and the myriad applications they enable.”
“embedUR Systems has demonstrated expertise in creating and optimizing AI technology for STM32N6 microcontrollers with minimal support from our engineering team. Their experience, creativity and efficiency are exceptional. In just a few short weeks, they were able to demonstrate incredible results. The potential of edge AI on STMicroelectronics components will drive innovative AI solutions across the industry. .” Miguel Castro, Head of AI Strategy and Business Development for the Americas at STMicroelectronics, said: “We are pleased to announce that embedUR is our new ST certified partner.”
The embedUR system inspires companies to explore how its expertise and solutions can enable the next generation of edge AI applications. For more information, please visit www.embedur.ai.
embedUR Systems is a Silicon Valley-based leader in embedded systems, AI, and edge computing. With over 20 years of expertise and a track record of accelerating time to market for communications, networking equipment, and silicon vendors, embedUR provides cutting-edge solutions that power millions of devices worldwide. We offer built-in solutions. The company’s ModelNova platform provides pre-trained AI models for seamless integration into intelligent edge systems, allowing AI enthusiasts and hobbyists alike to experiment with AI and have little to no AI modeling expertise. , making it easy to develop proofs of concept in record time. See pre-trained Edge AI models on modelnova.ai today.
(ADVERTORIAL DISCLAIMER: The above press release was provided by NewsVoir. ANI is not responsible for its content)
(This is an unedited, auto-generated article from a syndicated news feed. Current staff may not have modified or edited the content.)
