BRN Discussion Ongoing
- Thread starter TechGirl
- Start date
Could be a very productive event coming up at IFS.
www.tomshardware.com
OpenAI CEO Sam Altman will be at Intel's next foundry event — and he's currently looking for chip partners
Altman will join Intel CEO Pat Gelsinger at Intel's Direct Connect event in Feb.
Last edited:
AMD announces it has preorders for $3.5 billion of its AI GPUs; stock tumbles in after-hours trading anyway
AMD's results hurt by slowing demand for client and gaming hardware.
Tothemoon24
Top 20
Virtual reality is revolutionising the way we work and helping us move from design concept to full production much faster.
This is why we have developed our very own Virtual Reality Center (VRC) at the Mercedes-Benz Technology Center in Sindelfingen. And one of the most talked about facilities is the “Holodeck” room.
Measuring under 50 square metres, Holodeck helps our designers and engineers to interact with new prototypes like never before. For example, employees can take a seat inside an interior mock-up just as if it was in the room for real. The 1:1 scale model is a simplified representation of the real interior and, when users put on a pair of VR goggles, they immediately feel like they are sitting in a futuristic Mercedes.
As you can imagine, the VR goggles are incredibly high-tech. They are packed with sensors that monitor the movements of the user’s head and eyes. Special hand-tracking technology detects finger movements and hand gestures in real time and transfers them to the VR world. Our current goggles also use what is known as video-see-through technology. The cameras integrated into the glasses film the real surroundings and show them directly on the displays. This creates the impression that you can look through the glasses. The virtual image components generated by the VR software are then superimposed in the correct position. This is referred to as mixed reality (MR) in the field of view.
MR offers numerous benefits. In the early development phase, mixed reality enables users to assess the size and quality of individual components. They can use the tech to see if different objects fit into the car, such as a cardboard box in the boot. And with Holodeck’s haptic feedback, users can, for instance, feel what it’s like to bang into solid surfaces on the vehicle.
In the coming weeks, I will post more insights into how the VRC is enhancing the R&D processes at #MercedesBenz.
Bravo
If ARM was an arm, BRN would be its biceps💪!
Could be a very productive event coming up at IFS.
OpenAI CEO Sam Altman will be at Intel's next foundry event — and he's currently looking for chip partners
Altman will join Intel CEO Pat Gelsinger at Intel's Direct Connect event in Feb.
View attachment 55630
View attachment 55631
Chances are pretty high IMO that Sam Altman already knows about us via Mercedes....
- #72,350
- Blog mentioning BrainChip by Shyamal Anadkt (Open AI) dated 1 June 2023 https://www.linkedin.com/pulse/frontiers-startups-2023-shyamal-hitesh-anadkat/
Last edited:
Lots of scope to utilize Akida in eye-tracking in the goggles alone. Then there's gestures, I guess voice also ...
Tothemoon24
Top 20
We can't imagine a better way to have kicked off 2024 than by announcing EDGX's first collaboration with the European Space Agency - ESA. Our project, titled
Onboard Neuromorphic Acceleration , partially funded by the ESA ARTES programme, marks a milestone in our quest to redefine satellite capabilities. The entire team is stoked to work on this project, here's why:
Project HighlightsThe project aims to define an onboard neuromorphic, brain-inspired Data Processing Unit (DPU) tailored for satellite communication constellations in Low Earth Orbit (LEO). The DPU will be suitable for small satellites (smallsats) weighing up to 500 kg, with a seven-year planned operational lifetime. Our DPU aims to enhance the capabilities of communication satellites, making them more adaptable, flexible, and intelligent.
The project encompasses three core activities:
Identification of Potential Neuromorphic Satcom Applications and Scenarios
Performance Benchmarking and Demonstration of Neuromorphic Algorithms vs Classical Algorithms
Defining the Product Architecture, User Requirements, and Technical Specifications
Customer-Centric InnovationOur commitment to aligning technological advancements with our customers' needs and desires is central to the project. We focus on creating a solution that pushes the boundaries of technology in space and resonates with market demands. Hence, communication with industry stakeholders is vital in this project.
Shaping the FutureWe envision a world where thousands of AI-powered satellites, inspired by the human brain, enable unparalleled real-time connectivity, rapid response to global crises, and direct access to vital earth observation data. Satellite infrastructure will provide enormous societal and economic value to man and machines here on earth. This project is our first step towards building that future.
A Key PartnershipOur collaboration with ESA symbolises a union of ambition and expertise, emphasising trust in our idea and vision. We're on a mission to transform the satellite communication industry, and together, we can build a product that can achieve that. We can't wait to share more of our journey with you. What would you like to see come out of the project?
Tothemoon24
Top 20
Eyes on the Road: Enabling Real-Time Traffic Camera Analysis with BrainChip Akida
EDGE AIBy Nick BildJan 30, 2024
Smart camera systems designed to monitor and optimize traffic flow and enhance public safety are becoming more common components of modern urban infrastructure. These advanced systems leverage cutting-edge technologies, such as artificial intelligence and computer vision to analyze and respond to real-time traffic conditions. By deploying these smart camera systems at strategic locations throughout cities, municipalities can address a variety of challenges and significantly improve overall urban efficiency.
One of the primary issues smart camera systems address is traffic congestion. These systems can monitor traffic patterns, identify bottlenecks, and dynamically adjust traffic signal timings to optimize the flow of vehicles. By intelligently managing traffic signals based on the current demand and congestion levels, these systems can reduce delays, shorten travel times, and minimize fuel consumption, thereby contributing to a more sustainable and eco-friendly transportation system.
In addition to alleviating congestion, smart camera systems also play a crucial role in enhancing public safety. They can be equipped with features such as license plate recognition, facial recognition, and object detection to identify and respond to potential security threats or criminal activities. These capabilities enable law enforcement agencies to quickly and proactively address security concerns, providing a force multiplier for urban safety.
Despite the benefits that they can offer, the widespread adoption of smart traffic camera systems has been hindered by some nagging technical issues. In order to be effective, real-time processing of video streams is required, which means powerful edge computing hardware is needed on-site. Moreover, each system generally needs multiple views of the area which further taxes the onboard processing resources. Considering that many of these processing units are needed throughout a city, some just an intersection away from one another, problems of scale quickly emerge.
The Challenge: Real-Time Traffic Analysis
Being quite familiar with the latest in edge computing hardware and current developments at Edge Impulse, engineer Naveen Kumar recently had an idea that could solve this problem. By leveraging BrainChip’s Akida Development Kit with a powerful AKD1000 neuromorphic processor, it is possible to efficiently analyze multiple video streams in real-time. Pairing this hardware with Edge Impulse’s ground-breaking FOMO object detection algorithm that allows complex computer vision applications to run on resource-constrained hardware platforms, Kumar reasoned that a scalable smart traffic camera system could be produced. The low cost, energy efficiency, and computational horsepower of this combination should result in a device that could be practically deployed throughout a city.
Implementation
As a first step, Kumar decided to focus on a critical component of any traffic camera setup — the ability to locate vehicles in real-time. After setting up the hardware for the project, it was time to build the object detection pipeline with Edge Impulse. To train the model, Kumar sought out a dataset captured by cameras at Shibuya Scramble Crossing, a busy intersection in Tokyo, Japan. Still image frames were extracted from videos posted on YouTube, and those images were then uploaded to a project in Edge Impulse using the CLI uploader tool.From there, Kumar pivoted into the Labeling Queue tool to draw bounding boxes around objects of interest — in this case, vehicles. The object detection algorithm needs this additional information before it can learn to recognize specific objects. This can be a very tedious task for large training datasets, but the Labeling Queue offers an AI-assisted boost that helps to position the bounding boxes. Typically, one only needs to review the suggestions and make an occasional tweak.
Having squared away the training data, the next step involved designing the impulse. The impulse defines exactly how data is processed, all the way from the time it is produced by the sensor until a prediction is made by the machine learning model. In this case, images were first resized, which is important in reducing the computational complexity of downstream processing steps. Following that, the data was forwarded into a FOMO object detection model that has been optimized for use with BrainChip’s Akida neuromorphic processor. Kumar made a few small adjustments to the model’s hyperparameters to optimize it for use with multiple video streams, then the training process was initiated with the click of a button.
After a short time, the training was complete and a set of metrics was presented to help in assessing how well the model was performing. Right off the bat, an average accuracy score of 92.6% was observed. This is certainly more than good enough to prove the concept, but it is important to ensure that the model has not been overfit to the training data. For this reason, Kumar also leveraged the Model Testing tool, which utilizes a dataset that was left out of the training process. This tool revealed an average accuracy rate of 94.85% had been achieved, which added to the confidence given by the training results.
BrainChip’s Akida Development Kit is fully supported by Edge Impulse, which made deployment a snap. By selecting the “BrainChip MetaTF Model” option from the Deployment tool, a compressed archive was automatically prepared that was ready to run on the hardware. This code is aware of how to utilize the Akida PCIe card, which allows it to make the most of the board’s specialized hardware.
To wrap things up, Kumar used the Edge Impulse Linux C++ SDK to run the deployed model. This made it simple to start up a web-based application that marks the locations of vehicles in real-time video streams from traffic cameras. As expected from the performance metrics, the system accurately detected vehicles in the video streams. It was also demonstrated that the predictions could be made in just a few milliseconds, and while slowly sipping on power.
Subscribe to Edge Impulse
Get the free version of our newsletter. No spam ever, unsubscribe anytime.Subscribe
Are you interested in building your own multi-camera computer vision application? If so, Kumar has a great write-up that is well worth reading. The insights will help you to get your own idea off the ground quickly. Kumar has also experimented with single-camera setups if that is more what you had in mind.
More Like This
On the Fast Lane of Innovation: Traffic Monitoring with BrainChip Akida
Benchmarking Akida with Edge Impulse: A Validation of Model Performance on BrainChip's Akida Platform
Edge Impulse and BrainChip Partner to Further AI Development with Support for the Akida Platform
Explore Edge Impulse
Announcing FOMO (Faster Objects, More Objects)
Introducing EON: Neural Networks in Up to 55% Less RAM and 35% Less ROM
Voice Activated Micro:bit with Machine Learning
Subscribe
Frangipani
Top 20
Does he really?
Astrophysicists would strongly disagree…
But I suppose the reincarnation of Lord Byron (“Ye stars! which are the poetry of heaven!”) could always claim poetic license when confusing black with white holes and those self-luminous celestial bodies of gas we mere mortals behold in the night sky…
Now the question of course is: since Akida is already being called science fiction, what shall we call white holes, then?!
Attachments
CHIPS
Regular
Could be a very productive event coming up at IFS.
OpenAI CEO Sam Altman will be at Intel's next foundry event — and he's currently looking for chip partners
Altman will join Intel CEO Pat Gelsinger at Intel's Direct Connect event in Feb.
View attachment 55630
View attachment 55631
The 21st of February will be a very, very successful day because it is my birthday.
It is time for me to buy more stocks.
Fantastic news and likely further validation for Akida. And parenthetically exactly 11 years to this day my surgical career finished....I retired.
So of course to celebrate I bought more shares today. 34k.
Does that make any sense??? Or just a complete non sequitur.
rgupta
Regular
In
On top we all know our involvements with NASA and Ant61.
I assume akida is making life easy for a lot of space agencies to accomplish their missions.
Akida could already be there in space. Renasas supplied a good chunk of hardware to ISRO on their mission to Moon and Sun.
On top we all know our involvements with NASA and Ant61.
I assume akida is making life easy for a lot of space agencies to accomplish their missions.
Also, a doctor. I attended a medical conference in Melbourne on AI in medicine last week. Was fascinating. I'm talking to an Australian company atm that writes your medical notes from as you take history and examine. It was flawless. Even generated very impressive referral letters. But, all has to be sent to server farm and then back. Which makes it less secure and power hungry. Several speakers were aware of brain chip and said the only barrier is more research papers proving its design and results. Which FAct finder had graciously supplied.... hope more to come.
Kachoo
Regular
Ant61 yes they are also one. Nasa well we know nothing of those but its possible that word had beed spread that Akida's efficiency significantly improves project capabilities and comes.
I mean to not take anything away from EDGX its a collaboration but I'm seeing a pattern starting to develop. IMO
Good Morning Chippers ,
1, Just noticed a small ( 1,223 units ) sell order popped up again @ $1.80........ testing the parameters . From memory , over two years ago some one or thing put a sell order in @ $916.21 per unit.
2, Australian first .... Guinea Pig pulls positive GeForces & survives to tell the tail.
Regards,
Esq.
1, Just noticed a small ( 1,223 units ) sell order popped up again @ $1.80........ testing the parameters . From memory , over two years ago some one or thing put a sell order in @ $916.21 per unit.
2, Australian first .... Guinea Pig pulls positive GeForces & survives to tell the tail.
Regards,
Esq.
Earlyrelease
Regular
To the moon
Re your article about Akida and traffic command.
I particularly liked the summary
“ The low cost, energy efficiency, and computational horsepower of this combination should result in a device that could be practically deployed throughout a city.”
Humm one city multiple sets of traffic controls light (100’s). Let’s extrapolate that over the developed world and at low cost at edge. Will enjoy just this one ideas addition to the flow of pennies as I am watching financials.
Re your article about Akida and traffic command.
I particularly liked the summary
“ The low cost, energy efficiency, and computational horsepower of this combination should result in a device that could be practically deployed throughout a city.”
Humm one city multiple sets of traffic controls light (100’s). Let’s extrapolate that over the developed world and at low cost at edge. Will enjoy just this one ideas addition to the flow of pennies as I am watching financials.
Similar threads
