Revision history [back]

I have a working object detection and tracking system already implemented. It detects, tracks and maps the objects in the world frame. However, since my camera is mounted on a moving vehicle, it tilts therefore the coordinates of the tracked objects are changing drastically, which results in wrong mapping of objects in the world coordinate.

Is there a way to understand how much the camera tilts between frames, so that I can add or subtract the amount of tilting for the coordinates of the detected objects? Keep in mind that I do not have many keypoints in my images, therefore suggetions including keypoint tracking or something similar can be skipped.

Thanks in advance.

I have a working object detection and tracking system already implemented. It detects, tracks and maps the objects in the world frame. However, since my camera is mounted on a moving vehicle, it tilts therefore the coordinates of the tracked objects are changing drastically, which results in wrong mapping of objects in the world coordinate.

Is there a way to understand how much the camera tilts between frames, so that I can add or subtract the amount of tilting for the coordinates of the detected objects? Keep in mind that I do not have many keypoints in my images, therefore suggetions including keypoint tracking or something similar can be skipped.

Thanks in advance.

I have a working object detection and tracking detection&tracking system already implemented. implemented in OpenCV. It detects, tracks and maps the objects in the world frame. However, since my camera is mounted on a moving vehicle, it tilts and therefore the coordinates of the tracked objects are changing drastically, drastically in the image frame, which results in wrong mapping of objects in the world coordinate. frame.

Is there a way to understand how much the camera tilts between frames, so that I can add or subtract the amount of tilting for the coordinates of the detected objects? Keep in mind that I do not have many keypoints in my images, therefore suggetions including keypoint tracking or something similar can be skipped.

Things to keep in mind:

• I do not have a gyroscope or anything like tilt-sensor, I cannot make use of additional hardware. I am looking for a vision solution.
• I am using only single camera (No stereovision).

What I tried so far:

• I have my horizon line detected, I tried to take that as a reference point, but horizon also tilts, therefore this did not work.
  • Same goes for keypoints, their coordinates change when the tilt happens, this did not work either.

Thanks in advance.

I have a working object detection&tracking system already implemented in OpenCV. It detects, tracks and maps the objects in the world frame. However, since my camera is mounted on a moving vehicle, it tilts and therefore the coordinates of the tracked objects are changing drastically in the image frame, which results in wrong mapping of objects in the world frame.

Is there a way to understand how much the camera tilts between frames, so that I can add or subtract the amount of tilting for the coordinates of the detected objects? Keep in mind that I do not have many keypoints in my images, therefore suggetions including keypoint tracking or something similar can be skipped.

Things to keep in mind:

• I do not have a gyroscope or anything like tilt-sensor, I cannot make use of additional hardware. I am looking for a vision solution.
• I am using only single camera (No stereovision).

What I tried so far:

• I have my horizon line detected, I tried to take that as a reference point, but horizon also tilts, therefore this did not work.
  • Same goes for keypoints, their coordinates change when the tilt happens, this did not work either.

Thanks in advance.