Skip main navigation

Video analysis

Video analysis is the most accessible and easy solution to get started with analysing human motion on a computer.
Now we have been looking at different types of motion capture, where we can put markers on the body and capture the motion of people with a very high level of accuracy and precision. And that’s often the preferable way of doing it when we’re doing the type of studies we do. But I would also like to mention that there are many also good reasons for doing regular video recordings and do analysis based on video. And first of all, one of the nice things about video cameras is that they are everywhere. You have them in your mobile phone. So from this you can actually get a quite nice video recording.
At least if you put it on a tripod, so the camera doesn’t move very much. You can also get all sorts of other types of cameras these days. For example, such portable action cameras that are quite nice to put up in different constellations. I often like to put them in the ceiling above a stage, where it’s possible to look at how performers, for example, move on stage. Or you can put them in all the small spots where it’s difficult to get through to be able to look at what’s going on. For example, like looking at the feet of a pianist.
Of course, you can also scale up and have a more, kind of a little bit larger camera that you can put at the front of a stage. Or even go up to more kind of professional type of cameras, like this one, if you really want to get good results. But for many purposes, you can get very good results out of just using a small little camera. So when it comes to recording video for analysis, that’s quite different than recording video for aesthetic reasons or for doing other types of production. Because usually then people would move the cameras a lot, zoom in, pan, tilt, et cetera.
But when you’re doing analysis on video material, that type of movement of the camera is not very good, because that will show up in the video analysis. So when we shoot video for analysis purposes, we always try to have the camera stand still on the tripod or on a table or some other kind of stand, so that it’s possible to only capture the motion within the frame and not the movement of the camera itself. We also try to have, then, good light and also try to remove the background as much as possible so that it’s easy to look at what is in the foreground. For example, a musician or a dancer on stage.
So then if you have made a recording that you think is nice and that you want to use for analysis, then there are different approaches to how to analyse this. And one of them is that of doing a more of a qualitative analysis, which is based on observation. And in that case, you would take a look at the video file, and just by your eyes, observe what is going on. For example, also notate down, or use a computer programme to help in making a notation of the video in question. The next step could be to do more of a quantitative type of analysis, where you run the video through a computer programme that will calculate different types of features.
And it can calculate, for example, the quantity of motion, that is, how much a person is moving in the frame. Look at where in the frame a person is moving. For example, kind of up and down or sideways. And other the types of features. So that’s kind of the qualitative and quantitative type of approaches to video analysis, but there’s also something in between that we have been working on quite a lot here at the University of Oslo. And that is what we call video visualisation. And this is a way of doing a kind of quantitative type of analysis on the video, but made for qualitative purposes. And one such example, here, is what I have behind me here.
And this is what I call a motiongram. And this is a very compact representation of a movement sequence. In this case, it’s the movement of a dancer. And this is the original video file. So we see here that a dancer, she’s moving her arms– And this is from a study we did looking at spontaneous dance movements to music. And, just by looking at this, we get a sense of how the movement is unfolding in time and space. But it’s difficult to really grasp how it looks like over time. So, for example, if you want to put this into a research paper, we need to capture this in one way or another. And that’s when these motiongrams are useful.
Because the motiongram is a representation of the movement we just saw. We can see the hands, her hands, moving up and down here. Here she’s standing more or less still. And then here she’s moving up again. So it’s kind of a way of representing the motion over time. This is just one of many different types of video visualisations. One of the reasons it’s possible to do any type of analysis of a video file to start with is that a video file is actually just a series of numbers. So it’s a kind of a matrix, where you have the grid, where you have the pixels in the image.
And then you have four layers in each of the frames that will correspond to the different colours in the image. So based on these numbers, it’s possible to calculate, for example, the average of what is going on in one of these images. And one technique that we often use is to create what we call a motion image. And here it is that we will start from a normal video recording, then we can crop it a little bit so that you get kind of closer to the image. We can change, for example, the brightness and the contrast so it’s easier to separate the foreground from the background. And then we can calculate what we call the frame difference.
So we take one frame and then the next frame and we subtract them mathematically from each other. And what you end up with is what we call a motion image that is showing what changed between these two frames. And then that is something you can look at as a video, so you can see only the parts in the image that changed over time. And this is a very common way to start to do an analysis. And then from that one, again, we can create what we call this motiongram. That’s this representation over time of a motion sequence that’s based kind of squeezing together each of the motion images and plotting them over time.
It’s also possible to look at what we call a motion history video, where you can see kind of traces of the motion of a person over time as we see here. With different types of philtres on top. So this we can kind of tailor to the particular motion in question. And together then, a motiongram is kind of a representation that can give you a sense of how the body is moving in time and space. While in this case, here, we can look at a continuous video, where we see how the motion is changing spatially. And a course, based on this again, it’s possible to calculate various types of features that can be used in quantitative measurements.
So we often like to work within both quantitative and qualitative video analysis approaches and use these types of visualisation techniques as a guide to help us with finding what is important. So it’s possible to do this type of video analysis on its own, but we often combine it with motion capture so that we can get the best of both worlds. That is, a very high level of accuracy and precision from the motion capture system, and then a more holistic and global view from the video recordings.

Video analysis is the most accessible and easy solution to get started with analysing human motion on a computer.

In this video, Alexander talks about how one can record video for analytical purposes. You’ll also learn about some different video visualization techniques.

This article is from the free online

Motion Capture: The Art of Studying Human Activity

Created by
FutureLearn - Learning For Life

Reach your personal and professional goals

Unlock access to hundreds of expert online courses and degrees from top universities and educators to gain accredited qualifications and professional CV-building certificates.

Join over 18 million learners to launch, switch or build upon your career, all at your own pace, across a wide range of topic areas.

Start Learning now