Tag Archives: Cognitive

Interview: Gathering & analyzing data with drones & IBM Bluemix

Here’s an interview that I recently did with IBM DeveloperWorks TV at the recent World of Watson conference. In it I discuss a project I’ve been working on that analyzes drone imagery to perform automatic damage detection using the Watson Visual Recognition, and generates 3D models from the drone images using photogrammetry processes. The best part – the entire thing runs in the cloud on IBM Bluemix.

It leverages the IBM Watson Visual Recognition service with custom classifiers to detect the presence of hail damage on shingled roofs, Cloudant for metadata/record storage, the IBM Cloud Object Storage cross-region S3 API for massively scalable & distributed image/model/asset storage, and Bare Metal servers for high performance computing.

Bare Metal servers are dedicated machines in the cloud: not shared, and not virtualized. I’ve got mine setup as a linux server with 24 cores (48 threads), 64 Gigs of RAM, a SSD RAID array, multiple GPUs, etc… and it improved my photogrammetry rendering from hours on my laptop down to merely 10 minutes (in my opinion the best part).

I’ve done all of my testing with DJI Phantom and DJI Inspire aircraft, but really, it could work with any images, from any camera that has embedded GPS information.

Check out the video to see it in action.

Drones, Bots, Cognitive Apps, Image Recognition, Motion Analysis, and Photogrammetry (or, what I’ve been up to lately)

It’s been a while since I’ve posted here on the blog…  In fact, I just did the math, and it’s been over 7 months. Lots of things have happened since, I’ve moved to a new team within IBM, built new developer tools, worked directly with clients on their solutions, worked on a few high profile keynotes, built apps for kinetic motion and activity tracking, built a mobile client for a chat bot, and even completed some new drone projects.  It’s been exciting to say the least, but the real reason I’m writing this post is to share a few of the public projects I’ve been involved with from recent conferences.

I recently returned from Gartner Symposium and IBM’s annual World of Watson conference, and it’s been one of the busiest, yet most exciting span of two weeks I’ve experienced in quite a while.

At both events, we showed a project I’ve been working on with IBM’s Global Business Services team that focuses on the use of small consumer drones and drone imagery to transform Insurance use cases. In particular, by leveraging IBM Watson to automatically detect roof damage, in conjunction with photogrammetry to create 3D reconstructions and generate measurements of afflicted areas to expedite and automate claims processing.

This application leverages many of the services IBM Bluemix has to offer… on-demand CloudFoundry runtimes, a Cloudant NoSQL database, scalable Cloud Object Storage (S3 compatible storage), and BareMetal servers on Softlayer. Bare Metal servers are *awesome*… I have a dedicated server in the cloud that has 24 cores (48 threads), 64 GB RAM, RAID array of SSD drives, and 2 high end multi-core GPUs. It’s taken my analysis processes from 2-3 hours on my laptop down to 10 minutes for photogrammetric reconstruction with Watson analysis.

It’s been an incredibly interesting project, and you can check it out yourself in the links below.

World of Watson

World of Watson was a whirlwind of the best kind… I had the opportunity to join IBM SVP of Cloud, Robert LeBlanc, on stage as part of the the Cloud keynote at T-Mobile Arena (a huge venue that seats over 20,000 people) to show off the drone/insurance demo, plus 2 more presentations, and an “ask me anything” session on the expo floor.

wow

The official recording is available on IBM Go, but it’s easier to just see the YouTube videos. There are two segments for my presentation: the “set up” starts at 57:16 here: https://youtu.be/VrZMQZSB_UE?t=57m16s and the “end result” starts at 1:08:00 https://youtu.be/VrZMQZSB_UE?t=1h8m0s. I wasn’t allowed to fly inside the arena, but at least I was able to bring the Inspire up on stage as a prop!

You can also check out my session “Elevate Your apps with IBM Bluemix” on UStream to see an overview in much more detail:

.. and that’s not all. I also finally got to see a complete working version of the Olympic Cycling team’s training app on the expo floor, including cycling/biometric feedback, video, etc… I worked with an IBM JStart team and wrote the video integration layer into for the mobile app using IBM Cloud Object Storage and Aspera for efficient network transmission.

olympics

This app was also showcased in Jason McGee’s general session “Trends & Directions: Digital Innovation in the Era of Cloud and Cognitive”: https://youtu.be/hgd3tbc2eKs?t=11m49s

Gartner Symposium

At the Gartner Symposium event, I showed the end to end workflow for the drone/insurance app…

Drones

On this project we’ve been working with a partner DataWing, who provides drone image/data capture as a service. However, I’ve also been flying and capturing my own data. The app can process virtually any images with appropriate metadata, but I’ve been putting both the DJI Phantom and Inspire 1 to work, and they’re working fantastically.

Here’s a sample point-cloud scan I did of my office. :)

  • Left-click and drag to rotate
  • Right-click and drag to pan
  • Scroll or pinch/pull to zoom

Or check it out fullscreen in a new window.

Introducing the new Watson iOS SDK (beta)

watson-header
I’ve written here in the past on both the impact of cognitive computing, and how you can integrate IBM Watson services into your mobile apps to add cognitive language processing capabilities and more.  I’m happy to share that IBM has just recently released a new beta SDK that makes integrating more Watson services into your iOS applications easier than ever.

If you aren’t familiar with cognitive computing, or the transformative impact that it is already having on entire industries, then I strongly suggest checking out this video and related article on IBM DeveloperWorks.

IBM Watson services, which are based on machine learning algorithms, give you the ability to handle unstructured data, like text analysis or translation, speech processing, and more.  This makes consumption, mining, or responding to unstructured data or “dark data” faster, more efficient, and more powerful than ever.

The new Watson iOS SDK provides developers with an API to simplify integration of the Watson Developer Cloud services into their mobile apps, including the Dialog, Language Translation, Natural Language Classifier, Personality Insights, Speech To Text, Text to Speech, Alchemy Language, or Alchemy Vision services – all of which are available today, and can now be integrated with just a few lines of code.

The Watson iOS SDK makes integration with Watson services significantly *really* easy. For example, if you want to take advantage of the Language Translation service, you first have to setup a service instance. Once the translation service is setup, then you’ll be able to leverage translation capabilities within your mobile app:

//instantiate the LanguageTranslation service
let service = LanguageTranslation(username: "yourname", password: "yourpass")

//invoke translation methods
service.translate(["Hello","Welcome"],source:"en",target:"es",callback:{(text:[String], error) in
  //do something with the translated text strings
})

I’ve actually put a sample application together that demonstrates the language translation service integration, which you can access at github.com/triceam/Watson-iOS-SDK-Demo.

swift-translator

Be sure to check out the sample’s readme for additional detail and setup instructions. As with all of the Watson services, You must have a service instance properly configured, with authentication credentials in order to be able to consume it within your app.

The new Watson iOS SDK is written in Swift, is open source, and the team encourages you to provide feedback, submit issues, or make contributions.  You can learn more about the Watson iOS SDK, get the source code, and access the open source project here.

Thoughts on Cognitive Computing

You may have heard a lot of buzz coming out of IBM lately about Cognitive Computing, and you might have also wondered “what the heck are they talking about?”  You may have heard of services for data and predictive analytics, services for natural language text processing, services for sentiment analysis, services understand speech and translate languages, but it’s sometimes hard to see the forest through the trees.

I highly recommend taking a moment to watch this video that introduces Cognitive Computing from IBM:

Those services that I mentioned above are all examples of Cognitive Computing systems, and are all available for you to use today.

From IBM Research:

Cognitive computing systems learn and interact naturally with people to extend what either humans or machine could do on their own.

They help human experts make better decisions by penetrating the complexity of Big Data.

Cognitive systems are often based upon massive sets of data and powerful analytics algorithms that detect patterns and concepts that can be turned into actionable information for the end users.  It’s not “artificial intelligence” in the sense that the services/machines act upon their own; rather a system that provides the user tools or information that enables them to make better decisions.

The benefits of cognitive systems in a nutshell:

  1. They augment the user’s experience
  2. They provide the ability to process information faster
  3. They make complex information easier to understand
  4. They enable you to do things you might not otherwise be able to do

Curious where this will lead?  Now take a moment and watch this video talking about the industry-transforming opportunities that Cognitive Computing is already beginning to bring to life”

So, why is the “mobile guy” talking about Cognitive Computing?

First, it’s because Cognitive Computing is big… I mean, really, really big.  Cognitive systems are literally transforming industries and providing powerful analytics and insight into the hands of both experts and “normal people”.  When I say “into the hands”, I again mean this literally; much of this cognitive ability is being delivered to those end users through their mobile devices.

It’s also because cognitive systems fit nicely with IBM’s MobileFirst product offerings.  It doesn’t matter whether you’re using the MobileFirst Platform Foundation server on-premise, or leveraging the MobileFirst offerings on IBM Bluemix, in both cases you can easily consume IBM Watson cognitive services to augment and enhance the interactions and data for your mobile applications. Check out the Bluemix catalog to see how you might start adding Watson cognitive or big data abilities to your apps today.

Last, and this is purely just personal opinion, I see the mobile MobileFirst offerings themselves as providing somewhat of cognitive service for developing mobile apps.  If you look at it from the operational analytics perspective, you have an immediate insight and a snapshot into the health of your system that you would never have seen otherwise.  You can know what types of devices are hitting your system, what services are being used, how long things are taking, and detect issues, all without any additional development efforts on your end. It’s not predictive analytics, but sure is helpful and gets us moving in the right direction.