BRN Discussion Ongoing
- Thread starter TechGirl
- Start date
Ignorance is bliss huh
The Pope
Regular
Yes there is merit in what you are saying due to synsense and bmw comments via synsense website news in 15 April 2022. Refer link below
University of Groningen to develop applications for SynSense’s Neuromorphic hardware | SynSense
Professor Elisabetta Chicca, colleague Thorben Schoepe and a robot that has a neuromorphic vision processor inspired by the fly brain. (Source: Marleen Annema, University of Groningen) SynSense and CogniGron / University of Groningen are today announcing a collaboration to evaluate the low-power...
www.synsense.ai
Then there is this from TSE forum in 27 Feb 22 with a potential dot join between BRN and BMW
Brainchip + BMW
Hey Folks. Since now I read a few hints that brings Akida together with BMW, but the last presentation was that obvious, that it may need an own Thread. We all saw in this presentation the racecar with its big "BMW Power" in the rear: This could have been a coincidence, because no other race...
thestockexchange.com.au
I recall banter between posters on TSE linked to the above but doubt anyone will try to post links (dot joining) to convince you BRN tech is definitely in BMW upcoming EV range.
Maybe BMW have changed camps in the last 12months with exploring AI tech for their vehicles with BRN. From a quick google there doesn’t appear to be any announcement by BRN they are exploring uses of AI tech with BMW as that noted by synsense in the article above on 15 April 2022
Maybe BRN / Bmw have this under a NDA unlike synsense. Who knows but doesn’t it take a few years to develop tech into products before rolling out to customers
BRN can’t be eveywhere but BRN TSE believers like us wish it will be in BMW and many other car manufactures. Fingers crossed BRN is everywhere for us shareholders.
SharesForBrekky
Regular
Interesting article about differing views on the possibility of fully autonomous (level 5) driving:
www.carexpert.com.au
"Leading Chinese automaker BYD claims completely autonomous driving (AD) is ‘basically impossible’, and that the automation technology would better serve streamlining manufacturing processes.
Translated from Mandarin by CNBC, BYD spokesperson Li Yunfei said “We think self-driving tech that’s fully separated from humans is very, very far away, and basically impossible.”
"Despite Mercedes-Benz having one of the most advanced ADAS systems on the market, with Level 2 autonomous driving systems across its range and the S-Class being offered with Level 3 autonomous technology in Germany, CEO Ola Kallenius said “I think we will surely be deep into the [20]30s before the whole world goes to that (self-driving tech).”
"Elon Musk says Tesla vehicles will soon achieve full self-driving autonomy and will “be able to show to regulators that the car is safer, much more so, than the average human”.
Tesla is yet to receive regulatory approval for its systems, but as Musk says, “we’ve got to prove it to regulators and get the regulatory approvals, which is outside of our control.”
Autonomous driving 'basically impossible' says BYD
BYD has made its position on autonomous driving clear, saying costs and legislation render autonomous technology useless for widespread use.
"Leading Chinese automaker BYD claims completely autonomous driving (AD) is ‘basically impossible’, and that the automation technology would better serve streamlining manufacturing processes.
Translated from Mandarin by CNBC, BYD spokesperson Li Yunfei said “We think self-driving tech that’s fully separated from humans is very, very far away, and basically impossible.”
"Despite Mercedes-Benz having one of the most advanced ADAS systems on the market, with Level 2 autonomous driving systems across its range and the S-Class being offered with Level 3 autonomous technology in Germany, CEO Ola Kallenius said “I think we will surely be deep into the [20]30s before the whole world goes to that (self-driving tech).”
"Elon Musk says Tesla vehicles will soon achieve full self-driving autonomy and will “be able to show to regulators that the car is safer, much more so, than the average human”.
Tesla is yet to receive regulatory approval for its systems, but as Musk says, “we’ve got to prove it to regulators and get the regulatory approvals, which is outside of our control.”
Thanks for your considered post Pope. I would absolutely love to see us in BMW and Merc together - what a coup that would be. We partner with Prophesee but they and BMW state a partnership with SynSense only for their neuromorphic smart cockpits. There is no mention of Brainchip. Why would we be under an NDA and not SynSense (makes NoSense). Astonishingly this opinion is considered 'ignorant' by some but perhaps the dog ate their homework instead. Keep up the good work Pope, I enjoy your balanced contributions hereYes there is merit in what you are saying due to synsense and bmw comments via synsense website news in 15 April 2022. Refer link below
University of Groningen to develop applications for SynSense’s Neuromorphic hardware | SynSense
Professor Elisabetta Chicca, colleague Thorben Schoepe and a robot that has a neuromorphic vision processor inspired by the fly brain. (Source: Marleen Annema, University of Groningen) SynSense and CogniGron / University of Groningen are today announcing a collaboration to evaluate the low-power...
Then there is this from TSE forum in 27 Feb 22 with a potential dot join between BRN and BMW
Brainchip + BMW
Hey Folks. Since now I read a few hints that brings Akida together with BMW, but the last presentation was that obvious, that it may need an own Thread. We all saw in this presentation the racecar with its big "BMW Power" in the rear: This could have been a coincidence, because no other race...
I recall banter between posters on TSE linked to the above but doubt anyone will try to post links (dot joining) to convince you BRN tech is definitely in BMW upcoming EV range.
Maybe BMW have changed camps in the last 12months with exploring AI tech for their vehicles with BRN. From a quick google there doesn’t appear to be any announcement by BRN they are exploring uses of AI tech with BMW as that noted by synsense in the article above on 15 April 2022
Maybe BRN / Bmw have this under a NDA unlike synsense. Who knows but doesn’t it take a few years to develop tech into products before rolling out to customers
BRN can’t be eveywhere but BRN TSE believers like us wish it will be in BMW and many other car manufactures. Fingers crossed BRN is everywhere for us shareholders.
D
Deleted member 118
Guest
Old but new or is it new but old.
www.edgecomputing-news.com
BrainChip, Blue Ridge Envisioneering work on tactical edge devices
BrainChip has partnered with engineering team Blue Ridge Envisioneering to build tactical edge devices for military use cases.
www.edgecomputing-news.com
D
Deleted member 118
Guest
Tobii DMS has been awarded its first design win
Press release Stockholm, April 27, 2023 Tobii has been selected by the world’s largest
D
Deleted member 118
Guest
Oh would you look at that.....dot dot dotThanks for your considered post Pope. I would absolutely love to see us in BMW and Merc together - what a coup that would be. We partner with Prophesee but they and BMW state a partnership with SynSense only for their neuromorphic smart cockpits. There is no mention of Brainchip. Why would we be under an NDA and not SynSense (makes NoSense). Astonishingly this opinion is considered 'ignorant' by some but perhaps the dog ate their homework instead. Keep up the good work Pope, I enjoy your balanced contributions here
Mt09
Regular
Ah yep that confirms, 100% in BMW…..
Any names mentioned from Brainchip?
Yeah I concede - read the fine print. It clearly says AKIDA being incorporated in all BMW vehicles in lieu of SynSense. Rob Telson likes it too which means commercialization is imminent (but shrouded in NDA's). Just like all of his other 'likes' can be traced directly to revenue producing contracts, oh wait.....what?
Labsy
Regular
Yes!!!! Dio you are a beakon of light in the darkness cast over us....Thankyou for your priceless input.
TheDrooben
Pretty Pretty Pretty Pretty Good
This 4C is a joke!!!!!!! But a very bad one!
I cannot vote from Germany but don't you all dare and vote YES to the bonus of Sean and others!!!I will then step into a plane and come over to TALK to you all in person!!! The management DOES NOT DESERVE THEIR SALARY AND THEREFORE ALSO NOT A BONUS!!!!
I am so upset, angry, and pissed that I wasted my time and money with this company. I lost a lot of money on this so selling does not make sense at all. All I can do is wait and hope that BrainChip with its AKIDA technology will be bought by a big company. This could bring us a few stocks of a GOOD and SUCCESSFUL investment.
In my view, it is time for Sean Hehir to step down, and to be replaced. All those cute interviews were just words for money.
By the way, how much cash do they have left before they are bankrupt?
I wonder who these guys actually have contracts with. Their website doesn't elaborate although that could definitely be due to the sensitive nature of defence and intelligence contracts. They're only a small company but it appears they have some traction based on the company blurb.Old but new or is it new but old.
BrainChip, Blue Ridge Envisioneering work on tactical edge devices
BrainChip has partnered with engineering team Blue Ridge Envisioneering to build tactical edge devices for military use cases.
This is the sort of collaboration that gives me hope - defence/national security contracts can be massive and enduring.
Fullmoonfever
Top 20
I see ARM pushing the M85 for computer vision and ML with MCUs.
Obviously including their Helium and NPU but nice we can also now dovetail with it
www.imveurope.com
Technology
Computer vision (CV) has been widely adopted in many Internet of Things (IoT) devices across various use cases, ranging from smart cameras and smart home appliances to smart retail, industrial applications, access control and smart doorbells. As these devices are constrained by size and are often battery powered, they need to wield highly efficient compute platforms.
One such platform is the MCU (microcontroller unit), which has low-power and low-cost characteristics, alongside CV and machine learning (ML) compute capabilities.
However, running CV on the MCU will undoubtedly increase its design complexity due to the hardware and software resource constraints of the platform.
Therefore, IoT developers need to determine how to achieve the required performance, while keeping power consumption low. In addition, they need to integrate the image signal processor (ISP) into the MCU platform, while balancing the ISP configuration and image quality.
One processor that fulfills these requirements is Arm’s Cortex-M85, which is Arm’s most powerful Cortex-M CPU to date. With vector extension of SIMD (single instruction, multiple data) 128-bit vector processing, Cortex-M85 accelerates CV alongside the overall MCU performance. For IoT developers, they can leverage Arm’s software ecosystem, ML embedded evaluation kit and guidance on how to integrate the ISP with the MCU in order to unlock CV and ML easily and quickly on the highly-efficient MCU platform.
Figure 1: The comparison between VLIW and SIMD
Arm’s Helium technology, which is the M-Profile Vector Extension (MVE) for the Cortex-M processor series, brings vector processing to the MCU. Helium is an extension in the Armv8.1-M architecture to significantly enhance performance for CV and ML applications on small, low-power IoT devices. It also utilises the largest software ecosystem available to IoT developers, including optimised sample code and neural networks.
The evaluation kit provides ready-to-use ML applications for the embedded stack. As a result, IoT developers can experiment with the already-developed software use cases and then create their own applications. The example applications with ML networks are listed in the table below.
The Arm ML embedded evaluation kit
For IoT edge devices, there will be a smaller image sensor resolution (<1-2MP; 15-30fps) and even lower frame rate. Also the image signal processing is not always active. Therefore, using a higher quality scaler within the ISP will drop the resolution to sub-VGA, which is 640 x 480, to, for example, minimise the data ingress to the NPU. This means that the ISP only uses the full resolution when needed.
ISP configurations can also affect power, area, and efficiency. Therefore, it is worth asking the following questions to save power and area.
Figure 2: An example of concise ISP configuration
Another consideration when integrating the ISP with the MCU is lowering the frame rate and resolution In many cases, it would be best to consider the convergence speed of the ‘3As’ – auto-exposure, auto-white balance and auto-focus. This will likely require a minimum of five to ten frames before settling. If the frame rate is too slow, it might be problematic for your use case. For example, this could mean a two to five second delay before a meaningful output can be captured and, given the short power-on window, there is a risk of missing critical events. Moreover, if the clock frequency of the image sensor is dropped too low, it is likely to introduce nasty rolling shutter artifacts.
Embedded vision
Computer vision
Artificial intelligence
Obviously including their Helium and NPU but nice we can also now dovetail with it
Unlocking computer vision and machine learning on highly efficient MCU platforms | Imaging and Machine Vision Europe
Stephen Su shares how Arm’s Cortex-M85 processor and software ecosystem can be leveraged to overcome the constraints of microcontroller unit platforms
Unlocking computer vision and machine learning on highly efficient MCU platforms
16 March 2023Technology
Computer vision (CV) has been widely adopted in many Internet of Things (IoT) devices across various use cases, ranging from smart cameras and smart home appliances to smart retail, industrial applications, access control and smart doorbells. As these devices are constrained by size and are often battery powered, they need to wield highly efficient compute platforms.
One such platform is the MCU (microcontroller unit), which has low-power and low-cost characteristics, alongside CV and machine learning (ML) compute capabilities.
However, running CV on the MCU will undoubtedly increase its design complexity due to the hardware and software resource constraints of the platform.
Therefore, IoT developers need to determine how to achieve the required performance, while keeping power consumption low. In addition, they need to integrate the image signal processor (ISP) into the MCU platform, while balancing the ISP configuration and image quality.
One processor that fulfills these requirements is Arm’s Cortex-M85, which is Arm’s most powerful Cortex-M CPU to date. With vector extension of SIMD (single instruction, multiple data) 128-bit vector processing, Cortex-M85 accelerates CV alongside the overall MCU performance. For IoT developers, they can leverage Arm’s software ecosystem, ML embedded evaluation kit and guidance on how to integrate the ISP with the MCU in order to unlock CV and ML easily and quickly on the highly-efficient MCU platform.
Arm brings advanced computing to MCUs
As a first step, being able to run CV compute workloads requires improved performance on the MCU. Focusing on the CPU architecture, there are several ways to enhance the MCU’s performance, including superscalar, VLIW (very long instruction word), and SIMD. For the Cortex-M85, Arm chose to adopt SIMD – which is a single instruction set that can operate multiple data – as it’s the best option for balancing performance and power consumption.
Figure 1: The comparison between VLIW and SIMD
Arm’s Helium technology, which is the M-Profile Vector Extension (MVE) for the Cortex-M processor series, brings vector processing to the MCU. Helium is an extension in the Armv8.1-M architecture to significantly enhance performance for CV and ML applications on small, low-power IoT devices. It also utilises the largest software ecosystem available to IoT developers, including optimised sample code and neural networks.
Software ecosystem on MCUs to facilitate CV and ML
Supporting the Cortex-M CPUs, Arm has published various materials to make it easier to start running CV and ML. This includes the Arm ML embedded evaluation kit.The evaluation kit provides ready-to-use ML applications for the embedded stack. As a result, IoT developers can experiment with the already-developed software use cases and then create their own applications. The example applications with ML networks are listed in the table below.
The Arm ML embedded evaluation kit
Integrating the ISP on the MCU
The ISP is an essential technology to unlock CV, as the image stream is the input source. However, there are certain points that we must consider when integrating ISP on the MCU platform.For IoT edge devices, there will be a smaller image sensor resolution (<1-2MP; 15-30fps) and even lower frame rate. Also the image signal processing is not always active. Therefore, using a higher quality scaler within the ISP will drop the resolution to sub-VGA, which is 640 x 480, to, for example, minimise the data ingress to the NPU. This means that the ISP only uses the full resolution when needed.
ISP configurations can also affect power, area, and efficiency. Therefore, it is worth asking the following questions to save power and area.
- Whether it’s for human vision, computer vision, or both?
- What is the required memory bandwidth?
- How many ISP output channels will be needed?
Figure 2: An example of concise ISP configuration
Another consideration when integrating the ISP with the MCU is lowering the frame rate and resolution In many cases, it would be best to consider the convergence speed of the ‘3As’ – auto-exposure, auto-white balance and auto-focus. This will likely require a minimum of five to ten frames before settling. If the frame rate is too slow, it might be problematic for your use case. For example, this could mean a two to five second delay before a meaningful output can be captured and, given the short power-on window, there is a risk of missing critical events. Moreover, if the clock frequency of the image sensor is dropped too low, it is likely to introduce nasty rolling shutter artifacts.
Summary
Enabling CV and ML on MCU platforms is part of the next wave of the IoT evolution. However, the constraints of the MCU platform can increase the design complexity and difficulty. Enabling vector processing on the MCU through the Cortex-M85 and leveraging Arm’s software ecosystem can provide enough computing and reduce this design complexity. In addition, integrating a concise ISP is a sensible solution for IoT devices to speed up and unlock CV and ML tasks on low-power, highly efficient MCU platforms.Embedded vision
Computer vision
Artificial intelligence
Similar threads
