Video Summarization Using
Mentor: Mr. Avinash Ratre
We have seen YouTube and other media sources pushing the bounds of video
consuming in the past few years. As media sources compete for more of a
viewer’s time everyday, one possible alleviation is a video summarization
system. A movie teaser is an example of a video summary. However, not
everyone has the time to edit their videos for a concise
This presentation highlights a fast and efficient algorithm using k-means
clustering with RGB histograms for creating a video summary. It is aimed
particularly at low quality media, specifically YouTube videos.
Split the input file into time segments of k seconds: f0...fn.
Take the first frame of each segment. Let this frame be
representative of the segment. We assign it
Compute the histograms from x0....xn and assign it y0...yn.
Cluster the histograms(y0....yn) into k groups using K-Means.
Euclidean distance will be the error function.
Round robin for segment selection: Iterate through the k
groups and select a segment randomly from a cluster, add it
to list l until the number of desired segments are chosen.
Join list l of segments together to generate a video summary.
• We selected RGB color histograms for our feature comparator
due to its global nature and speed of processing. Histograms
are a good trade-off between accuracy and speed.
• Histogram is a frequency approach where it compresses the
information of a video frame into a vector.
• The majority of YouTube videos are lower quality so extracting
more challenging features tends to be more difficult.
Histograms can perform well because they do not attempt to
infer any semantic meaning in the actual segments.
Group all the similar histograms into the k clusters. Each
histogram is representative of the corresponding video segment.
K-means algorithm is defined below:
1. Select k random centroid points on our multi-dimensional
2. Compute each histogram against all the cluster centroids
3.Each histogram is assigned to the cluster that minimizes the
4.Recompute cluster centroids.
5.On every iteration, check to see if the centroids converged. If
not, we go to step 2.
We use Euclidean distance as our error function. This is the
general approach when directly comparing histograms.
Additionally, we also experimented with the cosine similarity and
saw no noticeable difference in the clustering output.
• We selected k = 8 as our k-means parameter and use 20
segments for the output video
Following YouTube videos in our system. All of these videos are
•MotoGP: Recent round of the world motorcycle racing series.
This represents a typical sports video.
•Man Vs Wild Episode.
• When we clustered the MotoGP clip, it was able to separate
all the action footage from the pit stand footage. This is
particularly useful for viewers who only want to watch the
race and not the pit stand.
• The Man vs Wild episode was able to correctly cluster
different segments. It particularly helped that the uniquely
identifying segments had much color similarity. When the
Bear(the main actor) was in the desert, the colors are
populated with a higher color intensity. Similarly, when he
was in the Florida everglades, the colors are lower in intensity.
• Repeated segments
When a static image is present for a long time, two or more
segments will be created from this image. During the
clustering, all of the segments with the static image will be
clustered in the same group.
In the MotoGP video clip, the majority of the segments consists
of the road in the background. Our algorithm grouped most of
these shots into one cluster. The intended behavior would be
to capture the different teams into different clusters because
each team has a unique color scheme. However, the
background dominated and grouped most of these segments
together. It would interesting future work to see if two levels
of clustering would be helpful: one for the initial segments
and another sub-clustering for within each set.
We have presented a system to automatically create a
summarized video from a YouTube video.
K-means is a simple and effective method for clustering similar
Our system is modular in design so future work can be developed
by substituting in variouscomponents. Instead of using
histograms, future work can try to use other features suchas
motion vectors or even audio. However, we have demonstrated
that a simple feature with a simple unsupervised learning
technique can be a good starting point for a video summarization
• Video Summarization Using Clustering
Tommy Chheng, Department of Computer Science,University of
• A User Attention Model for Video Summarization
Yu-Fei Ma, Lie Lu, Hong-Jiang Zhang and Mingjing Li
Microsoft Research Asia