Tracking of rotating objects using opencv

Question

I need to track cars on the road from top-view video.

My application contain two main parts:

1. Detecting cars on the frame (Tensorflow trained network)
2. Tracking detected cars (opencv trackers)

I have troubles with opencv trackers. Initially i tried to different trackers, but only MOSSE is fast enough. This tracker works almost perfect for case with straight road, but i faced problems with rotating cars. This situation appears on crossroads.

As i understood, bounding box of rotated object is bigger that bbox of horizontal or vertical object. As result bbox contains big part of static background and the tracker lose target object.

Are there any alternative trackers which can track contours (not bounding boxes)? Can i adjust quality of existing opencv trackers results by any settings or by adjusting picture?

Schema:

Real image:

Answer 1

If your camera is stationary the following scenario is feasible:

1. use ‌background subtraction methods to separate background image from foreground blobs.
2. Improve the foreground results using morphological operations.
3. Detect car blobs and remove other blobs.
4. Track foreground blobs in video i.e. binary track (simply use this or even apply KF).

Answer 2

A very basic but effective approach in this scenario might be to track the center coordinates of the bounding box, if the center coordinates only change along one axis (with a small tolerance for either axis), its a linear motion (not a rotation). If both x and y change, the car is moving in the roundabout.

This only has the weakness that it will detect diagonal motion, but since you are looking at a centered roundabout, that shouldn't be an issue.

It will also be very efficient memory-wise.