We are looking forward to having the split processing computational power of OMAP4 for developing an add-on module which plugs on to a conventional ultrasonography equipment, analyzing video streaming over the video-out ports/network and providing Radiologists/Sonologists with diagnostic assistance based on computer vision and decision support, displayed over an adjunct interactive video display unit (touch screen LCD panel). The final product will have Image Processing apps working on DSP, base OS functioning on ARM and graphics rendering carried out on SGX.
Ultrasonography is an important noninvasive clinical imaging modality preferred for screening and diagnosis of internal organ abnormalities. At the Medical Imaging and PACS Lab, School of Medical Science and Technology, IIT Kharagpur, we are working on an ambition project towards development of "Computer Vision based Approach for Interpretation of Sonomammography".
This work addresses development of a computer vision based approach which seeks to overcome limitations in respect of inter-observer and intra-observer variability of lesion description, feature analysis and final assessment; and resolving overlap of sonomammography features characterizing different grades of tissue abnormality manifested through architectural appearance and sonological nature of the tissue. The developed methods and algorithms being incorporated into an expert system coupled with an ultrasonic equipment will aid in speedy and accurate assessment of breast tissue abnormality, by radiologists’, through quantitative analysis of the images. You can find regular updates about the development at http://debdoot.web.officelive.com/phdthesis.aspx
Currently, we are working with an OMAP-L138 based platform for implementing part of the work on front-end development. Details are available at http://hawkboard.wikispot.org/Front_Page
However our preliminary housekeeping of total computational requirements shows OMAP4 to be optimally satisfactory, and PandaBoard natively provides the minimal hardware resources required to undertake the complete implementation as an embedded solution.
Gesture/vocal interface to help person suffering from handicap (Blindness, paraplegia, quadriplegia) or elder peoples to keep independence:
For different use schemes:
- To locate: a speaking GPS telling location (street name) on request (button or speech recognition).
- Read and tell (OCR and speech synthesis)
- Speech recognition actuators
- Gesture (eye movement or body movements) or speech commands for actuations
- Status of remote or local sensors of equipped home
- Communicate easily (voip and connected link thru wifi/GSM)
Bringing all these features with the help of software:
- Gesture integration, character read OCR: image sensor and image processing
- Voice recognition / speech syntheses : audio processing
- Actuators and sensor (Local : serial / Ethernet link; remote Bluetooth wifi)
- Speech synthesis integrated for reading or locating
- Communication VOIP (start, stop communication with predefined list of contact trigged by voice or gesture)
I know all these functions already exist separately, but want to integrate all these features in one system with all the advantages of the pandaboard :
- Small form factor
- Low power consumption
- Connectivity (video sensors, wifi Bluetooth…..)
- Power for video and audio processing
- Linux and OMAP Community
- Get a fully integrated solution with one small board!!!
- Pandas are peaceful and powerful bears!
Time Frame :
First hardware and software integration (within 6 month):
- Headset /Microphone
- GPS (uart)
- Webcam USB
- Bluetooth sensor/actuator modules
- Gesture recognition (hand, body movement) and set some linked action
- Speech recognition and set some linked action
- Speech synthesis
- Actuator and sensors (got some Bluetooth/serial sensors and actuators)
- Get street position with speech synthesis work
Second hardware and software integration
- Headset /Microphone
- Design of an extension board GPS (external module with uart), image sensor
- Battery pack and case
- Eye movement recognition and set some linked action
- Develop a graphical interface for option settings for helpers
- More integration with person environment (generally home for quadriplegic or old people)
- Affected by persons suffering from handicap, elder peoples…
- Already set up some helping electronic (sensors, actuators)
- Want to develop a open community of helpers around pandaboard
- Work in electronic engineering (software AND hardware !)
- Developed electronic hardware devices (digital cameras, bluetooth sensors and actuators)
- Got a master in signal (audio and image) processing: openCV is my best friend !
- Developed linux driver for image sensors, PCI boards, LCD displays…
- Got some gesture recognition working on my Ubuntu intel inside computer
Will create a wiki directly in OMAPpedia !
my project mail:
New to all this but here is what I want to do.
1. Use the Pandaboard as a 3G/4G Broadband Router. Connection will be shared on WiFi as well as LAN
2. It ofcourse implies there's a DHCP Server somewhere in there
3. Enclose suitably and mount in a vehicle and make a plan for powering the board
4. Plan is to use a modified usb cellphone charger so that 12V to 5V is done on the cheap :)
5. Therefore, I can have WiFi in car.
6. Should be portable so that i can regularly take out and use at home as well.
I am not sure what distribution i'll use. Familiar with ubuntu but might be a little too 'heavy'
Seems MeeGo, Android, Linaro can also step up to the job. Guess it'll depend on what supports all the hardware.
Other desired applications:
While in car:
1. Would like to see if i can hook it to the On Board Diagnostics port and make it do some logging?
2. Hook maybe a camera to it somehow. Useful for fun random pictures :D
3. Maybe get the interface onto my android phone somehow. VNC maybe?
4. Maybe make it a car entertainment system?
While at home:
1. Use as low power media center to play FullHD hopefully but at least 720p?
2. Network switch/router as in car
So ya I'm totally open to suggestions since I am new and there are a lot of people who know this stuff way better than me!!
Thinking I should maybe blog to Tumblr or something as I go along?
The goal of this project is to build a Slackware ARM optimized for the Pandaboard.
The starting point is Slackware ARM: http://armedslack.org/
Slackware ARM has been already installed successfully on the Pandaboard.
Here are some useful info: http://giovanni.wordpress.com/pandaboard/
The next steps are to recompile kernel and packages for Pandaboard optimization.
Note: at the moment this is an unofficial porting of Slackware to Pandaboard.
This is a USB based boot utility for OMAP4 Platform. And allows you to boot OMAP4 platform over USB interface.
Usage: ./usbboot ./aboot.bin u-boot.bin
where: usbboot is the PC side utility listening on USB bus for asic-id from omap
aboot.bin is the second-stage loader getting loaded to internal sram of omap
The second-stage loader loads u-boot.bin to external ddr
(u-boot.bin can be replaced by any binary that one wishes to execute from ddr)
Project is maintained by Brian Swetland.
Porting Arch Linux to the PandaBoard, a continuation of what's already done over at PlugApps - we have ported Arch Linux to Marvell's Sheeva platform, and the Pandaboard is a much more powerful platform.
We're really excited and hope we can get our hands on a PandaBoard. The possibilities are endless. Whether it be a home storage server, a small-business's NAS, or even a set-top box, PlugApps can make it happen.
The goal of this project is to port Qi bootloader to the PandaBoard. Qi is a tiny, fast, "no frills" bootloader for ARM architectures. It permits direct loading of Linux kernel without intervention of u-boot. Its aim is to stay at the minimum needed to load and boot Linux kernel (without boot-menus or additional peripheral init).
At the moment there are Qi's versions for Samsung s3c* and omap3 (in a different branch) but there is no omap4 version. This project will try to develop and maintain a working version for omap4.
This bootlader will give feedback to the user by turning on/off LEDs on the PandaBoard in a way similar to FreeRunner GTA02 (for example turn on LED on successful kernel pull). It will also accept input from the user by pressing some buttons (for example adding debugging parameters to the kernel command line). To this end maybe I will need to add some push-buttons or LEDs connected to GPIOs
In a second phase I'm planning to add JTAG support to PandaBoard to debug early stages of boot. In this phase I will implement, configure and document a complete open source based JTAG debugging development chain for ARM Cortex A9 in OMAP4 used on PandaBoard. This includes final port of open source JTAG software OpenOCD for OMAP4 on Panda, and then configure and document all software (and hardware) components involved.
The goal of this project is to develop and build an expansion board for the PandaBoard based on FPGA technology.
An FPGA allows to build a very flexible expansion for an ARM based SoC. It's high count of programmable I/O pins combined with the option to create custom hardware blocks inside the configurable logic offer numerous possibilities.
While the Beagle Board only allows for SPI style peripherals inside an FPGA extension, the Panda Board offers the possibility to extend the system bus into the configurable logic, giving the developer much more flexibility and freedom with respect to transfer speed, complexity and number peripherals as well as easier software access because of the direct memory mapping.
Planned features for the expansion board
- expansion board can be attached to top or bottom side of PandaBoard
- FPGA connected to the 16 data/address lines exposed on the Panda Board expansion header
- remaining pins of the FPGA routed to pin headers on the expansion board
- configuration of the FPGA via SPI from within Linux or from serial flash (no need for JTAG cable)
- no BGA parts, so hobbyists can build the board
- if possible only two layers for the PCB
- everything build using Open Source tools where possible (FPGA synthesis will be an exception)
- more to come ...
The aim of the project is to utilize opensource tools and integrate them into a all in one Combo Box for domestic day to day purpose.
Following are the applications currently planned on this.
1) Home Network Gateway :- To provide wireless ( May be Wired access ) Internet access to all Internet devices at home.
2) Provide Advanced Routing and Fail over Internet along with Traffic Shaping and Restricted Internet access for the Kids.
3) Work as a VPN server so that users can connect from anywhere to Home Network
4) Monitor and alert Stock status On the Attched Display and alert ( Either Mail or LED notifications ) on drastic changes in the Stock price
5) Provide and act as a mp3 / OGG music Player and HD Video player on External source attach
6) Plan and include some home automation when necessary
Neuvoo is a project to optimize and apply Gentoo for use on embedded devices. We emphasize the ARMv7a architecture and create a multitude of embedded tools and ebuilds for new and advanced Linux users. We are completely compatible with the Gentoo structure and provide more advanced stages for installation on ARMv7a devices.