Upload
gallia
View
42
Download
0
Embed Size (px)
DESCRIPTION
Learning to Associate: HybridBoosted Multi-Target Tracker for Crowded Scene. Present by 陳群元. review. A ssociation. First round input tracklet association l k is the number of tracklets in S k . corresponding trajectory of S k tracklet association set. MAP problem. - PowerPoint PPT Presentation
Citation preview
Learning to Associate: HybridBoosted Multi-Target Tracker
for Crowded Scene
Present by 陳群元
review
Association
• First round• input• tracklet association
– lk is the number of tracklets in Sk.
• corresponding trajectory of Sk
• tracklet association set.
MAP problem
How to associate
• Bruce force?
Hungarian Algorithm(1)
• Arrange your information in a matrix with the "people" on the left and the "activity" along the top, with the "cost" for each pair in the middle.
Hungarian Algorithm(2)
• Ensure that the matrix is square by the addition of dummy rows/columns if necessary.
Hungarian Algorithm(3)
• Reduce the rows by subtracting the minimum value of each row from that row.
Hungarian Algorithm(4)
• Reduce the columns by subtracting the minimum value of each column from that column.
Hungarian Algorithm(5)
• Cover the zero elements with the minimum number of lines it is possible to cover them with.
Hungarian Algorithm(6)
• Add the minimum uncovered element to every covered element.
Hungarian Algorithm(7)
• Subtract the minimum element from every element in the matrix.
Hungarian Algorithm(8)
• Cover the zero elements again. If the number of lines covering the zero elements is not equal to the number of rows, return to step 6.
Hungarian Algorithm(9)
• Select a matching by choosing a set of zeros so that each row or column has only one selected.
Hungarian Algorithm(10)
• Apply the matching to the original matrix, disregarding dummy rows. This shows who should do which activity, and adding the costs will give the total minimum cost.
Time Complexity
Tim
e consuming
資料量(number of response)
Data Partition
• 整段影片 (2359frame) :3 hr• 切割時間/空間 (8x8) :3 min
– 時間 (8x8)– 空間 (200frame)
Feature
demo
To do
• Human detection • Build ground truth• Post processing
Thank you for your attention!