The International Conference on Image Processing 2013

After attending my first international conference as a PhD student I thought I'd do a quick review of the event and the content.

Day 0 - Thursday 12th September

Australia is far away. 10,500 miles (16,898 km) that's 3 x 7 hr flights + 2 x flight changes. I can't wait for sub-orbital intercontinental flights to become routine! The +Boeing+ 777-300ER (Extended Range) +Emirates aircraft was impressive nonetheless. Equipped with a ~13" LCD touchscreen with a removal phone-sized touchscreen remote, flanked by a USB port for photo playback on the ICE (Information, Communication & Entertainment) system and a universal (110v/60Hz) power socket provided plenty of things to keep me busy.

+Emirates ICE system 

A view that never gets old

Day 1 - Sunday 15th September

The event kicked off for me on the Sunday afternoon with a tutorial on RGBD Image Processing for 3D Modeling and Texturing. The main focus of this session was depth information from structured light cameras, it was interesting to see some techniques being used to improve depth information from colour cameras. Hopefully I'll be able to use some of this in my research.

Sunday evening was the welcome reception. This was a great chance to mingle, chat and network. An open bar and good food facilitated this very well. Another attraction that provided a good talking point was the addition of a mini petting zoo... This was pretty surreal, I found myself in the middle of a conference center stroking a koala, kangaroo and a wombat. 

Day 2 - Monday 16th September
Now the conference kicks off properly and gets into full swing pretty quickly. There were oral presentations, tech demos and poster presentations all running in parallel. If you have a broad area of research you'll be darting from room-to-room trying to catch talks of interest. I'd recommend having a good look though the technical program and highlighting the ones of most interest and focus on attending those. It sounds obvious but trying to get round everything is impossible.
This is where the poster sessions are possible more useful as they are literally hanging round longer and it's easier to discuss the work face-to-face.

Monday was topped off with a workshop on VP9 from +Google presented by +Debargha Mukherjee. It wasn't really in my field but was an interesting insight into the performance of VP9, where it's going next and the process of software development at the big G!

Day 3 - Tuesday 17th September
There's not much else I can say quickly, other than it was much the same as Monday, a busy schedule and plenty of things to attend. I'm not going to review all the work I saw, it would take far too long and not really provide anything of great use to anyone. If you are interested in the program it can be found here.

Tuesday evening was polished off with a banquet. It started with some pretty stereotypical aboriginal music and dancing being served with the first course which was "a taste of Australia". The main course of steak followed a rather odd combination of dance and technology, not really sure it was right for a geeky audience. Fillet steak is always a welcome meal in my books, but being honest it was overcooked for my liking, it's medium-rare or gtfo. Desert was accompanied by some more stereotypical music, this time by a folk-like band.

Day 4 - Wednesday 18th September

Finally it was almost time to present my work, unfortunately it was toward the end of the last day so inevitably the numbers started to dwindle a bit. This said, I did have some good discussions with quite a few people who I think were interested in the results presented or very good at feigning it. Below is the poster presented.

Summary

With such a broad range of topics being presented from medical imaging, radar, image enhancement, recognition and quality assessment it was easy to get mentally fatigued by trying to take it all in. My hint for anyone yet to attend one of these conferences is just decide on whats of interest and really concentrate on those. However, don't ditch everything else entirely, the poster session are invaluable for gaining insights into other areas of research that may be of interest but at least you can read them and absorb them at your own rate.

Logging Software Done! (Almost)

Ok, so it has been a while since my last post. I've been working on getting some robust logging software working on the logging PC. The software is designed to capture from multiple +Point Grey Research cameras at 1280x960 15fps, a +PrimeSense P1080 depth camera at 15fps, a Phidget IMU and a GPS receiver.

Spot the devices...

The outline of the program is a multithreaded logger that uses 4 CPU threads (done with OpenMP)
Thread 0 - Point Grey image acquisition and writing data to disk
Thread 1 - Primesense P1080 Depth and Colour image acquisition
Thread 2 - Read new Phidget data
Thread 3 - Read new GPS data

The most important part of the data is the multi-viewpoint camera data from the Point Grey Cameras as synchronisation between these images is key to accurate reliable 3D reconstruction. As soon as all cv::Mat objects from each camera have returned, Thread 0 writes the image data from each camera as well as writing the image data from the primesense camera and logging the phidget and GPS info to CSV files.

A neat feature of the logger is the dynamic delay function that aims to keep a maximum frame rate.
A timer is started at the beginning of image acquisition and stopped at the end of all the file writing. If this processing time is less than the desired frame rate of 66.67ms (15fps) then a dynamic delay is calculated simply as SleepTime = MAX(DesiredDelay-ProcessingTime,2); cv::waitKey(SleepTime); This dynamic delay means the program doesn't query the camera faster than it's configured for and gives us a nice steady frame rate. The MAX(n,2) protects against -'ve' time values and means it always pauses for at least 2ms to allow for video buffer to draw to frames to the screen. Obviously if the ProcessingTime is >= DesiredDelay then it is not possible to obtain the selected frame rate and the program just runs as fast as it can.

There is still a problem that is unresolved. The USB GPS receiver appears to flood the USB bus. Without the GPS connected, two USB Point Grey FireFly cameras happily work at 1280x960 15fps. When the GPS is added to the system it causes errors on the bus causing frames to be dropped. Now the really odd thing is these errors only appear to happen when the cameras auto adjust exposure. Fixing the shutter and gain values programmatically solves the issue. However this isn't a viable solution as the cameras are going to be mounted on a vehicle that will be driven through scenes that have wildly varying lighting conditions.

This image shows the output of three different cameras with identical fixed shutter and gain values. The top left is the high spec Flea2 and the top right/lower left are the lower cost FireFly cameras. It's interesting to note that the Flea2 has wider spectral sensitivity as it can see the structured light pattern from the PrimeSense camera.

Sort of good...

 In this one we can see a boat load of errors coming from cameras 1-2, the FireFly cameras.

...not so good...

 Here the camera shutter and gain values have been fixed independently from one another. While this looks good, it is not a solution due to the varying lighting conditions it will operate it.

...sort of good.

It is almost complete. Just waiting to get a RS-232 GPS device to remove the USB bus from the equation and hopefully that'll just work...

A "quick" Side Project

Since the last post I had my 9 month PhD review, it went pretty smoothly, passed with no problems :)
Shortly after I was asked by my project supervisor if I could help out quickly on another project. I'm always keen to work on a variety of projects.

The task was to simply pull together some already existing code to create a data logging program that logs stereo image from the +Point Grey Research bumblebee camera and log GPS positions, all this was going a remotely operated boat for the +Environment Agency.

I wrote a little C++ class to connect to a COM port and read off GPS data. This worked fine. The bumblebee however proved to be more of a challenge. I consulted a Masters student who had used it more than I had to obtain some code from him to read the images. The logging laptops are +Dell 6400 ATG's, theses are rugged laptops, perfect for use on the boat. Fresh installs of Win7 x64 were on these machines as they'd been hacked to pieces (not in the literal, more in the coding sense) in the past for various projects. So with the code working on a 32bit WinXP machine we ported the source over to +Microsoft Visual Studio (Link) in Win7 installed all the relevant +Point Grey Research drivers and..... nothin'.... 2 days went by of trying every sodding combination of drivers and libraries but none of the laptops were having any of it under x64. So we binned it and went back to trusty old XP.

We had hoped to get out onto the river yesterday (28/05/13) but a morning re-coding session to log grayscale stereo rectified images instead of colour un-rectified images, delays from +Leica Geosystems AG in obtaining a theodolite, problems with a bluetooth 5Hz GPS system that needs a power cycle if something tries to connect at the incorrect baud rate and not forgetting the British weather pissing it down all afternoon.

Student with his boat... finally.

As it was getting on for 6pm by the time everything was up and running we postponed the data logging day until tomorrow (30/05/13). Stay tuned for more....