Research Projects
- Multi-class Object Detection in Video Sequences
- Resource Allocation for Multiple Target Tracking
- The Bowerbird Project
- Detecting Human Actions from Single Images
- Activity Representation in Crowds
- Unusual Event Detection
- Tracking and Identity Maintenance
Multi-class Object Detection in Video Sequences
I am currently working on this project and shall put up some more details in a short while.
Resource Allocation for Multiple Target Tracking
Particle filters have been very widely used to track targets in video sequences. However, they suffer from an exponential
rise in the number of particles needed to jointly track
multiple targets. On the other hand, using multiple independent
filters to track in crowded scenes often leads to erroneous
results. We present a new particle filtering framework
which uses an intelligent resource allocation scheme allowing
us to track a large number of targets using a small set
of particles. First, targets with overlapping posterior distributions
and similar appearance models are clustered into
interaction groups and tracked jointly, but independent of
other targets in the scene. Second, different number of particles
are allocated to different groups based on the following
observations. Groups with higher associations (quantifying
spatial proximity and pairwise appearance similarity) are
given more particles. Groups with larger number of targets
are given a larger number of particles. Finally, groups with
ineffective proposal distributions are assigned more particles.
Our experiments demonstrate the effectiveness of this
framework over the commonly used joint particle filter with
Markov Chain Monte Carlo (MCMC) sampling.
Related Publication:
Resource Allocation for Tracking Multiple Targets using Particle Filters - Aniruddha Kembhavi, William Robson Schwartz,
and Larry S. Davis
(The Eighth International Workshop on Visual Surveillance (VS2008) - Workshop at ECCV 2008)
PDF
The Bowerbird Project
Sociobiologists collect huge volumes of video to study
animal behavior (our collaborators work with 30,000 hours
of video). The scale of these datasets demands the development
of automated video analysis tools. Detecting
and tracking animals is a critical first step in this process.
However, off-the-shelf methods prove incapable of
handling videos characterized by poor quality, drastic illumination
changes, non-stationary scenery and foreground
objects that become motionless for long stretches of time.
We improve on existing approaches by taking advantage of
specific aspects of this problem: by using information from
the entire video we are able to find animals that become
motionless for long intervals of time; we make robust decisions
based on regional features; for different parts of the
image, we tailor the selection of model features, choosing
the features most helpful in differentiating the target animal
from the background in that part of the image. We evaluate
our method, achieving almost 83% tracking accuracy
on a more than 200,000 frame dataset of Satin Bowerbird
courtship videos.
Related Publication:
Tracking Down Under: Following the Satin Bowerbird - Aniruddha Kembhavi, Ryan Farrell,
Yuancheng Luo, David Jacobs, Ramani Duraiswami, and Larry S. Davis
(IEEE 2008 Workshop on Application of Computer Vision (WACV 2008))
PDF
Detecting Human Actions from Single Images
I am unable to provide any more information regarding this, as we currently have a paper in submission regarding the same.
Activity Representation in Crowds
I am unable to provide any more information regarding this, as we currently have a paper in submission regarding the same.
Unusual Event Detection
Defining and detecting unusual events in general is a very
hard problem. What constitutes as being unusual is often
scene and context dependent. In this paper we characterize
an event in terms of the spatial locations of all objects in
the scene over time. This allows us to define an event as
being unusual if the interaction between targets (in terms of
these locations) has not been observed before. We characterize
the locations of all objects at a given time instant by
a single binary image marked with their current positions
in the scene. Projecting a sequence of binary image onto
a lower dimensional subspace yields a representation of an
activity in terms of a trajectory in the eigenspace. A particle
filter framework is used to incrementally match these
temporal trajectories, and build models of all usual activities
seen in the past. Using this framework, we classify an
observed activity as unusual, if it deviates sufficiently from
all the models representing usual activities.
Tracking and identity maintenance
We develop algorithms to improve the tracking and recognition of humans in a single
as well as multiple camera framework. We incorporate motion and appearance models as well
as learned priors on traffic movements between cameras. Our appearance models include
subjective descriptions of appearance of individuals that we obtain from a detailed clothing
segmentation. We are also working on incorporating coupling information between targets in
the scene.
I shall be putting up some more information in the upcoming weeks.
|