AAEON (stock code: 6579), a leading provider of edge AI platforms, has announced the release of the BOXER-8654AI-KIT, a development kit equipped with either an 8 GB or 16 GB NVIDIA Jetson Orin NX module. While AAEON's BOXER series has become synonymous with NVIDIA-powered embedded AI systems, the BOXER-8654AI-KIT provides its customers with an avenue to develop embedded solutions from the ground up.

The BOXER-8654AI-KIT's module is accompanied by an advanced carrier board featuring a full-function I/O boasting six USB 3.2 Gen 2 ports, an Out-of-Band (OOB) management box header, and four LAN ports with optional power boards for PoE functionality. For display, the kit's carrier board offers one physical HDMI Type-A port, as well as two MIPI CSI connectors, each equipped with four lanes to allow for two MIPI cameras to be installed per interface. Other physical I/O features that stand out are its two DB-9 ports, one of which offers an RS-232 (RX/TX/GND)/422/485 signal, with the other providing a CANBus interface. Additionally, an NVIDIA Jetson-compatible 40-pin header offers I2C, SPI, UART, and other serial interfaces.

Qualcomm Technologies, Inc., today announced the Qualcomm Robotics RB5 platform - the Company's most advanced, integrated, comprehensive offering designed specifically for robotics. Building on the successful Qualcomm Robotics RB3 platform and its broad adoption in a wide array of robotics and drone products available today, the Qualcomm Robotics RB5 platform is comprised of an extensive set of hardware, software and development tools.

The Qualcomm Robotics RB5 platform is the first of its kind to bring together the Company's deep expertise in 5G and AI to empower developers and manufacturers to create the next generation of high-compute, low-power robots and drones for the consumer, enterprise, defense, industrial and professional service sectors - and the comprehensive Qualcomm Robotics RB5 Development Kit helps ensure developers have the customization and flexibility they need to make their visions a commercial reality. To date, Qualcomm Technologies has engaged many leading companies that have endorsed the Qualcomm Robotics RB5 platform, including 20+ early adopters in the process of evaluating the platform.

Intel has submitted the first patches with Vulkan support to their open-source OpenCV library, which is designed to accelerate Computer Vision. The library is widely used for real-time applications as it comes with 1st-class optimizations for Intel processors and multi-core x86 in general. With Vulkan support, existing users can immediately move their neural network workloads to the GPU compute space without having to rewrite their code base.

At this point in time, the Vulkan backend supports Convolution, Concat, ReLU, LRN, PriorBox, Softmax, MaxPooling, AvePooling, and Permute. According to the source code changes, this is just "a beginning work for Vulkan in OpenCV DNN, more layer types will be supported and performance tuning is on the way."

It seems that now, with their own GPU development underway, Intel has found new love for the GPU-accelerated compute space. The choice of Vulkan is also interesting as the API is available on a wide range of platforms, which could mean that Intel is trying to turn Vulkan into a CUDA killer. Of course there's still a lot of work needed to achieve that goal, since NVIDIA has had almost a decade of head start.

NVIDIA today announced CUDA support for OpenCV, the popular Computer Vision library used in developing advanced applications for the robotics, automotive, medical, consumer, security, manufacturing, and research fields.

With the addition of GPU acceleration to OpenCV, developers can run more accurate and sophisticated OpenCV algorithms in real-time on higher-resolution images while consuming less power. This will facilitate the development of scores of new, mainstream Computer Vision applications.