Tag Archives: photos
Today’s post comes to us from Cathal Gurrin, Rami Albatal, Dan Berglund, and Daniel Hamngren. Cathal and Rami are researchers at Dublin City University and Daniel and Dan work at Narrative, makers of a small lifelogging camera and application. Together, they led an interesting breakout session at the 2014 Quantified Self Europe Conference on photo lifelogging and how to use analytics and computer vision techniques to make sense of vast amounts of photos. You’re invited to read their description of the session below and then join the discussion on the QS Forum.
Photo Lifelogging as Context for QS Practice
by Cathal Gurrin, Rami Albatal, Dan Berglund, and Daniel Hamngren
Thank you to those that came to the breakout session! It was a lively and excellent session with plenty of audience interaction. There were about fifteen participants who had an interest in photo lifelogging.
The session started with a presentation by the session chairs. The Narrative representatives discussed the Narrative clip and their plans for supporting photo lifelogging. This was followed by the DCU team giving an overview of what is possible with photo lifelogging, covering the technical possibilities of what is reasonable to achieve today.
What came across from these presentations is that photo lifelogging is not difficult, but the computer analytics to mine and extract meaning and knowledge is certainly challenging and even state-of-the-art computer vision analytics techniques can often fail to identify the valuable content of photos.
There were a number of core points of discussion, and these were:
Food and Diet. It seemed to the panel and the audience that food and diet monitoring was a key requirement for photo lifelogging and should be the key challenge to be addressed. It was accepted that this is challenging to do, but it was pointed out that recent academic findings suggest that indeed this is possible to achieve in some circumstances. It was pointed out that the most promising technologies to achieve this required a significant investment in time to label food eating photos and there were a number of willing volunteers to help with this activity. If it is possible to release a dataset of food eating photos, then the QS community will be able to help to label the data and build a large amount of training material for machine learning and AI techniques to utilise to build better food and diet monitoring tools. The organisers have taken this point on-board and will return at the next global meet-up with a plan.
Behavior / Lifestyle. Analysing the behaviour of the individual was discussed in terms of data correlations over time and visual day logs. Visual day logs, being the easiest to achieve today is available from the current generation of lifelogging tools, so this is available to anyone to begin to manually explore today. The extraction automatically of temporal patterns of behaviour was suggested as a valuable tool to begin this analysis.
Media Consumption Analytics. It was suggested that analysing the media that a lifelogger consumed could be very valuable both for organisations and as a context source for better quality search. Once again, the discussion came to the conclusion that this was also difficult to achieve, but that it is a worthy goal for the research teams.
Other discussion points included support for and appropriateness of sharing in real-time. Past experiences were shared of when this can work and when it can go wrong. It was also suggested that a ‘loved-one’ reminder tool could be developed as a form of ‘remembering future intentions’, which was pointed out in the lifelogging talk earlier that day as one of the five use-cases for photo lifelogging.
The session ended with the organisers thanking the attendees and the post-session discussions began and continued for thirty minutes, with some continuing to this day. In summary we found out that both food / diet and behaviour / lifestyle were the most important QS-based automatic monitoring tools that should be refined and made available to the QS community.
If you’re interested in photo lifelogging we invite you to join the discussion on the QS Forum.
Rob Shields has been wearing a phone around his neck since 2012 in order to take one photo per minute. This persistent lifelogging has come with some technological and social hurdles. At the 2013 Quantified Self Global Conference, Rob explained some of the issues he’s been running into as he nears 300,000 photos. He also talked about the interesting data he’s been able to gather because of this practice, such as understanding who he meets and how he spends his time. Watch his talk below to learn more about his practice and other interesting insights lifelogging has provided him.
Typically when the Quantified Self-er talks about using photography and image capture for self-tracking they’re talking about taking pictures of their food. Pictures are a very powerful way to capture information for better understanding, you know, they are worth a thousand words. On the blog here we’ve also highlighted a few really interesting projects that take the idea of using visual images for tracking and decided to turn the lens around such as Jeff Harris and his 13 years of self portraits.
One of the projects that I found super interesting was LifeSlice by Stan James.
For those of you who want to try LifeSlice Stan has put the code online for you to use and possibly tinker with. As a new user I can say that it is pretty interesting to see how my facial characteristics map to what I’m doing on the computer. For examples here’s me looking at a new statistical software package for mac (Wizard).
And here’s me writing this post while listening at a conference on health data.
The last project I want to highlight here is the self-portrait project of Noah Kalina. Noah is a photographer who has been taking self portraits every day for 12.5 years (January 11, 2000 – June 20, 2012). A few months ago he put all 4514 images together into one amazingly insightful video.
Than Tibbetts was so intrigued by this project he decided to work some fancy image processing magic to find out what “Average Noah” looked like and found this:
I’m sure there are more projects out there that involve individuals turning the camera on themselves. We all have cameras with us in our pockets and on our computers. How are you using those image capture technologies to better understand yourself? If you’re working on something interesting let us know!
Last December, Stan James started to wonder how much of every day he spent staring at glowing rectangles, and how he was spending that time. He set up his webcam to take a picture of himself every hour, as well as a screenshot of what he’s working on. In the video below, Stan talks about how he set up his project, shows some of his data, and reveals some interesting tidbits about his learnings. (Filmed by the Bay Area QS Show&Tell meetup group.)
What if you had a movie of your life that was made from a stream of pictures taken one every thirty seconds? Glenn Wolters and Jeroen Bos have built an iPhone app called Lifelapse to do this. They developed it as a school project. I noticed Joost Plattel using it at the recent QS conference – he showed me his entire bike ride across the Golden Gate Bridge as a powerful visual story in less than a minute. (Filmed at the Quantified Self Show&Tell meetup in Amsterdam at Mediamatic)
A lifelog, or lifeblog, is an attempt to fully document every second, every action, every interaction, every keystroke, every conversation of one’s life. In this sense it is quantitative as it accumulates data about a person’s daily activities. But among lifeloggers there is a subgroup of photo lifeloggers who are merely content to photographicly record their life in detail. There are many photologgers who take a portrait of themselves everyday.
One of the longest running of these daily guys, JK, now has a daily 8-year series of himself. He recently turned that series into a wonderful and mesmerizing timelapse animation.
This fellow JK also maintains a list of other maniacal photologgers here. Daily portraits seem to be a big thing in Germany. Some like to keep the photo constant from day to day in an almost clinical uniformity. Others are committed to dressing themselves up to maximize diversity from day to day. But the obsessive nature needed to maintain anything daily for years shows up in a few really obsessive photologgers. One guy takes a picture of whatever is in his right hand for the first time that day. Here is an excerpt from part of his day on December 6, 2007.
It’s an odd collection only because its trouble to take it. Someday when cameras will film our lives 24/7, this degree of documentation won’t be freakish.