This demo is based and tested on the DragonBoard 820c, but should be able to work on varying platforms. In summary, it counts objects by color passing in the same direction through the camera field of view. It can count multiple objects simultaneously. The OpenCV functionality leveraged by this demo includes the following:
- Object segmentation using color
- Valid object identification by size
- Frame stitching to track and count multiple simultaneous moving objects by color
- Provides hooks to monitor performance when algorithm changes to - - OpenCV library calls are made for identification tuning
- Provides hooks to export results to the cloud
Jon Masters is the Computer Architect, Chief Arm Architect with extensive experience at Red Hat with the deeper levels of CPU and Software optimization, adapting and preparing the ecosystem of Cloud, Supercomputing, talks about all the latest Arm Servers, including those coming up with the Marvell ThunderX2, Qualcomm Centriq 2400, Ampere eMag, talking about ARM 10nm vs Intel 14nm, talking about his involvement fighting the industry's Meltdown and Spectre vulnerabilities, explaining some of the latest things done by Linaro in this space.
Mani is an Applications Engineer at 96Boards team of Linaro. He works on improving the user experience with 96Boards by upstreaming it's stadardized software support. He goes over the journey of how he started with 96Boards, what his initial responsibilities were and how it has been evolved over time. He also explains his recent work towards standardizing the software support for 96Boards and stresses the importance of having a unified software layout across all 96Boards of same category. In this video, he mentions his latest work towards standardizing the LED labels/triggers in Linux kernel and how that impacts the user experience on userspace library such as MRAA (https://github.com/intel-iot-devkit/mraa).
96Boards Mezzanine Initiative is a community-led, organized and maintained initiative. This initiative aims to expand the 96boards ecosystem and promote open-hardware.
96Boards Mezzanine-Community GitHub: https://github.com/96boards/mezzanine-community
Open Source Academics (OSA) by 96Boards (https://github.com/osacademics) aims to facilitate and expand the educational experience on a global stage by providing scalable curriculum and standardized course materials through an open source platform. To fully understand the diverse nature of OSA, this summary will be broken down into seven discrete sections: Motivation, Mission, Platform, Stakeholders, Infinity Committee, Incentives and Roadmap.
OSA wants to unite industry and academia to create, and host a fully functional and open sourced educational platform which facilitates consumption and contribution of standardized educational curriculum and incentivized course materials on a global scale (with a current focus on STEAM content). OSA will work with stakeholders to achieve a balanced set of standards and incentives which encourage collaboration and drive content quality and growth.
You can watch more 96Boards videos at https://youtube.com/96boards
Fujitsu A64FX is the new fastest Arm processor in the world, built on 7nm it has 2.7 TFLOPS performance per chip suitable for high-end HPC and AI, they aim to create with it the world's fastest supercomputer with it by 2021. A64FX is the first processor using the new Armv8-A Scalable Vector Extension (SVE) to accelerate a wide range of large-scale scientific computing, including deep learning. Fujitsu is working closely with Linaro to enrich the Arm HPC ecosystem. A64FX will be featured in the post-K computer, a supercomputer being developed by Fujitsu and RIKEN as a successor to the K computer, which achieved the world's highest performance in 2011. The organizations are striving to achieve post-K application execution performance up to 100 times that of the K computer. It offers a number of features, including broad utility supporting a wide range of applications, massive parallelization through the Tofu interconnect, low power consumption, and mainframe-class reliability.
You can watch Fujitsu's keynote at Linaro Connect here
System76 is a computer manufacturer based in Denver Colorado specializing in laptops, desktops and servers running Linux. System76 talks about their upcoming efforts to move manufacturing in-house, and what that may mean for the future of the ARM Powered Linux Laptop and Desktop.
Jem Davies is the General Manager of the Machine Learning Group at Arm, he talks about the new Machine Learning Collaboration with Arm NN and Linaro, where Arm is donating the Arm NN inference engine and software developer kit (SDK) to Linaro’s Machine Intelligence Initiative. As part of this initiative – which aims to be a focal point for collaborative engineering in the ML space – Arm is also opening Arm NN to external contributions.
Linaro’s Machine Learning Initiative will initially focus on inference for Arm Cortex-A SoCs and Arm Cortex-M MCUs running Linux and Android, both for edge compute and smart devices. The team will collaborate on defining an API and modular framework for an Arm runtime inference engine architecture based on plug-ins supporting dynamic modules and optimized shared Arm compute libraries. The work will rapidly develop to support a full range of processors, including CPUs, NPUs, GPUs, and DSPs and it is expected that Arm NN will be a crucial part of this.
You can watch Jem Davies keynote at Linaro Connect here
Chris Benson is an AI & digital transformation strategist, solution architect, and keynote speaker / evangelist who specializes in deep learning – the neural computation technology that is driving the artificial intelligence revolution.
He was a member of Accenture’s first dedicated AI Team, and went on to create and build Honeywell’s first dedicated AI Team.
Chris is the co-host of the Practical AI podcast (https://changelog.com/practicalai) – produced by Changelog Media – which makes artificial intelligence practical, productive, and accessible to everyone.
He is a frequent keynote speaker on artificial intelligence at conferences, broadcasts, and events around the world.
Chris is the Founder & Organizer of the Atlanta Deep Learning Meetup, one of the largest AI communities in the world, with about 2000 members.
You can find out more about Chris Benson at his website: https://chrisbenson.com
You can watch Chris Benson's keynote at Linaro Connect here