|
- The problem of elucidating the functional significance of genes
is a key challenge of modern science. Solving this problem can lead
to fundamental advancements across multiple areas such starting
from pharmaceutical drug discovery to agricultural sciences. A commonly
used approach in this context involves studying genetic influence
on model organisms. These influences can be expressed at behavioral,
morphological, anatomical, or molecular levels and the expressed
patterns are called phenotypes. Unfortunately, detailed studies
of many phenotypes, such as the behavior of an organism, is highly
complicated due to the inherent complexity of the phenotype pattern
and because of the fact that it may evolve over long time periods.
Standard methods of current biologists for studying the behavioral
patterns of model organism rely on human observation and are therefore
subjective and imprecise. In this paper, we propose applying color
and motion based tracking to study Ecdysis in the hornworm and odor
sense response in the mouse. These are biologically significant
phenotypes whose complexity had thus far, prevented application
of automated approaches for quantitative analysis. We present a
vision-based algorithm for robust tracking that can be easily applicable
to multiple organisms. The experimental results demonstrate the
accuracy of tracking and phenotype determination under conditions
of complex body movement, partial occlusions, and body deformations.
- Paper
“Automated Behavioral Phenotype Detection and Analysis”,
IEEE Canadian Conference on Computer and Robot Vision,
|
