We propose a technique that neither assumes known scene
geometry nor computes interdependencies between objects.
The main idea is that most human heads in a crowded scene
will appear near a head plane parallel to the ground plane.
If the relationship between the camera and the head plane is
known, and the camera’s intrinsic parameters are known, we
can predict the approximate size of a head’s projection into
the image plane, and we can use this information to reject
inconsistent candidate trajectories or only search for heads at
appropriate scales for each position in the image.
To find the head plane, we run our head detector over one
or more images of a scene at multiple scales, compute the 3D
position of each head based on an assumed real-world head
size and the camera’s intrinsics, and then we find the head
plane using linear least squares.
In an experimental evaluation, we find that at detection time,
using the 3D head plane information improves the accuracy of
pedestrian tracking in dense crowds and reduces false positive
rates while preserving high detection rates.
We propose a technique that neither assumes known scene
geometry nor computes interdependencies between objects.
The main idea is that most human heads in a crowded scene
will appear near a head plane parallel to the ground plane.
If the relationship between the camera and the head plane is
known, and the camera’s intrinsic parameters are known, we
can predict the approximate size of a head’s projection into
the image plane, and we can use this information to reject
inconsistent candidate trajectories or only search for heads at
appropriate scales for each position in the image.
To find the head plane, we run our head detector over one
or more images of a scene at multiple scales, compute the 3D
position of each head based on an assumed real-world head
size and the camera’s intrinsics, and then we find the head
plane using linear least squares.
In an experimental evaluation, we find that at detection time,
using the 3D head plane information improves the accuracy of
pedestrian tracking in dense crowds and reduces false positive
rates while preserving high detection rates.
การแปล กรุณารอสักครู่..
