SORT & DeepSORT MCQ
SORT is fast detection + Kalman + Hungarian on IoU; DeepSORT adds CNN embeddings to reduce ID switches after occlusions.
SORT
IoU + KF
Deep
Embedding
Hungarian
Assign
Metric
Cosine
SORT and DeepSORT
SORT demonstrated that a simple Kalman filter + Hungarian assignment on IoU costs achieves surprising MOT speed/accuracy when paired with a strong detector. DeepSORT adds a cosine-distance appearance metric to re-identify tracks after occlusion.
Cascade matching
DeepSORT matches recently seen tracks to high-confidence detections first using appearance, then IoU for remaining—reduces fragmentation.
Practical notes
Cost matrix
1 − IoU or Mahalanobis gate + embedding distance—threshold unassigned pairs.
Age / hits
Track management rules delete stale tracks and confirm new ones after hits.
Gallery
DeepSORT keeps short appearance history per track for robust matching.
Speed
SORT is very fast; embedding extraction adds compute but still real-time on GPU.
Pipeline
Detect → Predict KF → Build costs → Hungarian → Update confirmed tracks