Actions
Engagement
  • Author Author: tariq.ahmad
  • Date Created: Date Created
  • Last Updated Last Updated:
  • Views 4033 views
  • Likes 12 likes
  • Comments 57 comments
Related
Recommended

Project14 | Vision Thing: Beaglebone AI Your Vision Thing Project!

image

Vision Thing

Enter Your Project for a chance to win an Oscilloscope Grand Prize Package for the Most Creative Vision Thing Project!

Back to The Project14 homepage image

Project14 Home
Monthly Themes
Monthly Theme Poll

 

 

In the Comments Below: Tell Us How You Would Use the BeagleBone AI for Your Vision Thing Project!

 

We'll Send Out Boards for Project Proposals that Use Them! 

 

 

image

 

 

We are offering up to 20 FREE Beaglebone AI Boards in exchange for Vision Thing projects that use them!

 

Beaglebone AI Cooling Cape Addon Available from :  BB AI cooling Addon board available

image
Buy NowBuy Now
We are offering up to 20 FREE Beaglebone AI Boards in exchange for Vision Thing projects that use them!

 

What is a Vision Thing project and how do you use the BeagleBone AI to do one?

 

There's a lot of variety with how you choose to implement your project.  It's a great opportunity to do something creative that stretches the imagination of what hardware can do.  Your project can be either a vision based project involving anything that is related to Computer Vision and Machine Learning , Camera Vision and AI based projects, Deep Learning, using hardware.  Or, it can be a graphics project involving something graphical such as adding a graphical display to a microcontroller, image processing on a microcontroller, image recognition interface a camera to a microcontroller,  or FPGA - camera interfacing/image processing/graphical display.

 

What makes the Beaglebone AI suitable for Vision Thing  Projects?

 

BeagleBone AI is a high-end board for developers building artificial-intelligence and computer-vision applications. Its main AI features include a Texas Instruments (TI) AM5729 system on chip (SoC), TI C66x digital-signal-processor (DSP) cores and embedded-vision-engine (EVE) cores. The board has the same form-factor as the popular and cheap BeagleBone Black but with much higher specifications.

 

 

The AI-ready board comes with 1GB RAM and 16GB on-board eMMC flash with a high-speed interface, a USB Type-C port for power and a dual-role controller, and a USB Type-A host. There's also Gigabit Ethernet and Wi-Fi. With preinstalled software, the BeagleBone AI also saves buyers from having to download equipment to get the device up and running.

image
The Most Creative Vision Thing Wins a Keysight DSOXO11G Oscilloscope!

Learn more by visiting:

So: what do you have to do to be in the running for one of the brand new Beagleboard AI? Just follow the instructions below!

 

1. Register and/or log-in to the element14 Community

2. Leave a comment on this post or on Project14 | Vision Thing: Build Things Using Graphics, AI, Computer Vision, & Beyond!  telling us what you'd like to build for your Vision Thing project with the new Beagleboard AI!

3.  Once you receive a new board submit your finished Vision Thing  project for a chance to win a Keysight DSOXO11G Oscilloscope!

 

 

The Most Promising Vision Thing Project Proposals Win a Free Beaglebone AI to Use In Your Vision Thing Project!

 

Submit Your Completed Project in Vision Thing  for a Chance to Win a Keysight DSOXO11G Oscilloscope!

  • in reply to chamal82

    It would be good to be able to identify plants in this way. I once tried to identify a Holly Tree. There are only three kinds in the UK and I still couldn't do it.

     

    Dubbie

  • I want to build a portable image classification devices my main focus on low-power, small footprint and high durability in harsh out-door environment development board. The propose device will be a handheld battery powered and able to identify plants specially with high valuable herbs and small species with the built-in camera. By identifying those plants and species we can easily protect and reserve those for next generation. We are Asian countries are having great respect to eastern medicine that solely depend on herbs (by the time only experts can recognize those plants) sometime those Asian medicine has great value over western medicine. So the device will be hit among the medical practitioners around the world. The device is comprise with BeagleBoneAI , TFT display, camera and batteries. I have developed a CNN model to recognized plants and species with Keras(TensorFlow Lite). I want to embed it to the BeagleBoneAI. By pointing my device camera to a plants and species, the device will guess the plant with high accuracy and display the plant details using the TFT display(additionally the user can mark (or flag) the plant location in map using GPS geo-location then other people can spot the plant easily. This is the second phase of my project.). I have tried with other platforms such as Raspberry PI and Nvidia JETSON nano. I would like to see how the model fit with BeagleBoneAI. Ultimately I want to make benchmark all those edge AI boards and pick one for my device to go for production. If you need more information on my research please be kind enough to contact me via chamal.bluesmart@gmail.com. I am software engineer with 15+ years experience and an innovator. Enthusiast and hobbyist in technology. Arduino, Android, Visual studio, Laravel, Linux, python, micorPython, c++, java, kotlin, dart, vb.net, php, js, mysql mssql, mongodb are my knowledge assets. And also this will be my first hands on experience with BeagleBone.

  • Thanks Dubbie, for your insight on the project

     

    Ankur

  • in reply to ankur608

    Sounds like a good idea. I can still remember when glass bottles could be collected and cash deposits returned. Some children used to make pocket money by collecting empty bottles. I regret that I was never involved in this entrepreneurial activity.

     

    Dubbie

  • I would like to make a POC; 'Reverse Wending with Kiosk for Single use Plastic Bottles', through BeagleBoneAI powered Intelligent machine that would accept plastic bottles and provide coupons or IOTA credits to the donor. The machine would be integrated with a signage display that would showcase paid advertisements of locale brands plus would be equipped with Paid WiFi Hotspot that would all together generate revenue for the 'Incentive Model'.

    -Plastic bottle classification will be based on Transfer Learning

    -'Refuse' classifier for wastes other than Plastic bottles based on "Hotdog'n'NotHotdog Classifier"

    -An exclusive top 3 'Green Citizen of Month' will be showcased to spread awareness among the passerby and the locals against single use plastics.

    The BB-AI powered machine will be equipped with Active Compaction System based on Linear-Array Mechanism as well as it would relay the bin levels to the concerned authorities and recycle pickup facilities.

     

    Ankur

  • in reply to crisdeodates

    Hi ,

     

    There is no announcement for these boards.   These are marketing samples that are being sent out in support of the Vision Thing competition.    The boards are being sent out with the expectation to have projects completed by November 18th.    I will be sending the final boards out momentarily.

  • in reply to crisdeodates

    , when can we expect the announcement for giveaway winners? image

  • AERIAL VISUAL NAVIGATION SYSTEM

     

    The idea of fully autonomous navigation system based on the comparison of the observable surface behind the vehicle and its surroundings can be brought to the completely new level with BB-AI.

     

    It seems that this card has anything for building such system and been added to any drone carrying a suitable camera it can provide the complete widely affordable hardware platform for the proposed solution.

     

    I would like to build this solution and t start exploring the BB-AI capabilities towards visual navigation in different contexts and for different tasks.

     

    Thanks for the proposal and for the attention.

  • AI Apraisia Progression Tester

     

    It would be helpful to have a device that can assist individuals in scoring the progression of Primary progressive aphasia (uh-FAY-zhuh).

     

    Primary progressive aphasia is a rare nervous system (neurological) syndrome that affects the individuals' ability to communicate. People who have it can have trouble expressing their thoughts and understanding or finding words.

    The progression of this condition spans three to ten years.  Requiring ongoing care for the individual, often requiring someone to participate in their daily activities for several years as the indivial reaches end of life.

     

    People with primary progressive aphasia eventually lose the ability to speak and write and to understand written and spoken words. Some people develop substantial difficulty forming sounds to speak (a problem called apraxia of speech), even when their ability to write and comprehend is not significantly impaired.

     

    As the disease progresses, other mental skills, such as memory, can become impaired. Some people develop other neurological symptoms such as problems with movement (turning left when wanting to turn right). With these complications, the affected person eventually will need help with day-to-day care.

     

    People with primary progressive aphasia can also develop depression or behavioral or social problems as the disease progresses. Other problems might include blunted emotions such as unconcern, poor judgment or inappropriate social behavior.

     

    Instructions and scoring system for the Aphasia Rapid Test (source)

    InstructionsScore1a. Execution of simple orders:
    «Open and close your eyes»
    «Give me your left hand»0 = performs both tasks correctly.
    1 = performs one task correctly.
    2 = performs neither task correctly.1b. Execution of a complex order:
    «Put your left hand on your right ear»0 = performs the task in less than 10 s.
    1 = performs the task in more than 10 s or requires the order to be repeated.
    2 = performs the task partially: moves the hand across the median line or performs the task on the wrong side.
    3 = does not perform the task: does not move the hand across the median line or does not move at all.2. Repetition of words:
    2a. « button»
    2b. « macaroon»
    2c. « luggage»Each word scores from 0 to 2 (total 0-6), as follows:
    0 = normal repetition.
    1 = abnormal repetition but the word is correct and recognizable by the examiner *.
    2 = non-repetition or unrecognizable word *.
    *Note: Phonemic, apraxic or pronunciation errors can be scored 1 if the word is recognizable by the examiner, or 2 if the word is unrecognizable.3. Repetition of a sentence:
    «The boy is singing in the woods.»0 = normal repetition.
    1 = abnormal repetition but the sentence is recognizable by the examiner *.
    2 = non-repetition or unrecognizable sentence*.
    *Note: Phonemic, apraxic or pronunciation errors can be scored 1 if the sentence is recognizable by the examiner, or 2 if the sentence is unrecognizable.4. Object naming:
    4a. « watch»
    4b. « pen»
    4c. « coat »0 = normal naming.
    1 = abnormal naming but the word is correct and recognizable by the examiner.*
    2 = wrong naming or unrecognizable word. *
    *Note: Phonemic, apraxic or pronunciation errors can be scored 1 if the word is recognizable by the examiner. An unrecognizable word or lexical error must be scored 2.5. Scoring of dysarthria :0 = normal.
    1 = minor dysarthria.
    2 = moderate dysarthria: patient can be understood.
    3 = severe dysarthria: unintelligible speech.6. Verbal semantic fluency task:
    «Name as many animals as you can in one minute. »0 = more than fifteen words.
    1 = between eleven and fifteen words.
    2 = between six and ten words.
    3 = between three and five words.
    4 = between zero and two words.Total Score/26

  • I would like use the Beaglebone AI board and the fan in my Smart agriculture robot. Currently I am using Raspberry Pi 3B+ to detect plant diseases using computer vision and a custom trained model. After detecting that a plant has disease then it sends notification with pictures to the user. Raspberry Pi was doing it very slow at about 2-3 fps. So I would use the board which is designed for ML to try and improve inferencing time.

    I will also compare it with results of Raspberry pi.

     

    The project link: vimarshshah.blogspot.com/p/smart-agriculture.html