Beruflich Dokumente
Kultur Dokumente
Video databases
Bidirectional prediction
I B B B P B B B P B B B I
Forward prediction
Properties of objects:
Frame-dependent: valid in a subset of frames.
Frame-independent: valid for the video as a whole.
(d) Given a frame sequence, find all objects (of a certain type) occurring in
some or all of the frames of the segment.
(e) Given a frame sequence, find all activities (of a certain type) occurring in
it.
obj. 1
obj. 2
act. 1
1 0-
0- 5000 3000-
3000 2 3 5000
o1 o2
8 9 10 11 12 a1 13 o2 14 o2 15 o1
a1 a1
0- 500- 2000- 2500- 3000- 3500- 4000- 4500-
500 2000 2500 3000 3500 4000 4500 5000
Indexing:
Obj. 1 6, 9, 15 Note: Actually the intervals are
Obj. 2 4, 10, 13, 14 half-open, e.g. [0, 500) = 0..499
Act. 1 7, 9, 10, 12
R1 R2
obj. 1
obj. 2
act. 1 R3
Keyframes:
Representative frames within shots, containing the essential
elements for retrieval
Scene-level segmentation often uses keyframe features, and
operates e.g. in top-down or bottom-up manner.
Choosing keyframes:
Fuzzy task – no definite optimum
Can be based on the same features as segmentation
Various algoritmic approaches:
Sequential comparison
Clustering
Trajectory-based
Decision in the context of object/event detection
Annotations:
Allocation of semantic concepts to video segments
Means roughly the same as segment classification
Machine-learning tools have been attampted
Human assistance is usually needed in the final recognition, naming
and classification of segments and detected objects within them.
Ref: W. Hu, N. Xie, L. Li, X. Zend, and S. Maybank: ”A Survey of Visual Content-Based
Video Indexing and Retrieval”, IEEE Trans. on Systems, Man, and Cybernetics
41(6), Nov. 2011.