Model complexity about yolo_tracking HOT 2 CLOSED

This has no easy answers. But let's try to brake this down. The tracking algorithm consists of basically four parts: appearance description extraction, camera motion compensation, kalman filter updates and multi-step association.

• The appearance description extraction part is tricky as the complexity of the models do not scale linearly with the input pixels. The complexity of a CNN is more nuanced and depends on several factors: stride, pooling, convolutional layers, their kernels... There is not easy way of calculating this without looking very deep into the specific architecture.

• The Big O notation for camera motion compensation can vary widely depending on the specific algorithm. Methods based on optical flow are slower than feature-based methods

• The Kalman Filter complexity primarily depends on the state and observation vector.

• The association part is solved by the Hungarian Algorithm. Each association subproblem (high confidence, low confidence for example) is solved using the Hungarian algorithm.

from yolo_tracking.

👋 Hello, this issue has been automatically marked as stale because it has not had recent activity. Please note it will be closed if no further activity occurs.
Feel free to inform us of any other issues you discover or feature requests that come to mind in the future. Pull Requests (PRs) are also always welcomed!

from yolo_tracking.