21
"Person re-identification: a recent issue for the videosurveillance community and a technique for approaching it Loris Bazzani Marco Cristani ? Modena, 17 maggio 2011

Loris Bazzani Marco Cristani

  • Upload
    moya

  • View
    54

  • Download
    0

Embed Size (px)

DESCRIPTION

"Person re-identification: a recent issue for the videosurveillance community and a technique for approaching it. ?. Loris Bazzani Marco Cristani. Modena, 17 maggio 2011. Before we start…. Download code and datasets for the exercises ( iLIDS , VIPeR , CAVIAR) : - PowerPoint PPT Presentation

Citation preview

Page 1: Loris  Bazzani Marco  Cristani

"Person re-identification: a recent issue for the videosurveillance community

and a technique for approaching it

Loris BazzaniMarco Cristani

?Modena, 17 maggio 2011

Page 2: Loris  Bazzani Marco  Cristani

2

Before we start…• Download code and datasets for the exercises

(iLIDS, VIPeR, CAVIAR): http://profs.scienze.univr.it/~bazzani/TMP/S4_SDALF_reid.zip

• [opt.] Check out our CVPR 2010 paper:http://www.lorisbazzani.info/papers/proceedings/FarenzenaetalCVPR10.pdf

• [opt.] Check out the website:http://www.lorisbazzani.info/code-datasets/sdalf-descriptor/

Page 3: Loris  Bazzani Marco  Cristani

Outline of the lesson

1. Person Re-identification (few minutes…)

2. A possible solution: SDALF, Symmetry-Driven Accumulation of Local Features (20 minutes…)

3. Matlab exercises (~1 hour)

Page 4: Loris  Bazzani Marco  Cristani

Person Re-identification

T = 1 T = 23

Different overlapping cameras

T = 222T = 145

Same camera• Goal:

Recognizing an individual in different timings

Different non overlapping cameras

Page 5: Loris  Bazzani Marco  Cristani

Person Re-identification• Issues:

– Many, you will see them in the exercises…

Page 6: Loris  Bazzani Marco  Cristani

A possible solution: SDALF, Symmetry-Driven Accumulation of Local Features

• Overview of the proposed descriptor:

STEP 2: Chromatic

Feature

STEP 3:Per-region

Feature

STEP 4: Texture Feature

STEP 0-1: Axes of Symmetry

and AsymmetryDescriptor

Accumulation

t

For each body part

Page 7: Loris  Bazzani Marco  Cristani

Step 0 – Isolating the silhouette

• We need to focus on the body of the person

• We perform background subtraction or

• We apply a statistical model of the human appearance [Jojic et al. 2009]

Page 8: Loris  Bazzani Marco  Cristani

Step 1 – Axes of (A)simmetry

• We draw axes of symmetry and asymmetry

• Features near the axes of symmetry are more reliable

Page 9: Loris  Bazzani Marco  Cristani

Step 1 – Axes of (A)simmetry

BG subtraction using STEL generative model

Chromatic operator Spatial covering operator

Page 10: Loris  Bazzani Marco  Cristani

Step 2 - Chromatic feature• For each part (no head), we compute a weighted color

histograms• HSV color space• “Gaussian Kernel” for each body part:

• Low-weight to the background clutter• Robust to illumination changes, partial occlusions

Page 11: Loris  Bazzani Marco  Cristani

Step 3 - Per-region feature• Maximally Stable Color Region (MSCR)

detector• Detect “stable blobs”• Look at successive steps of an

agglomerative clustering of image pixels

• Covariant to affine transformations

Clustering of the detected blobs to reduce the computational cost of the matching

Page 12: Loris  Bazzani Marco  Cristani

Step 4 - Texture feature

• Recurrent High-Structured Patches (RHSP) detector

Page 13: Loris  Bazzani Marco  Cristani

Accumulation of features

• Descriptor:– Single-shot: SDALF with only one image (no

accumulation) – Multi-shot: SDALF with multiple images

Page 14: Loris  Bazzani Marco  Cristani

Testing the person re-identification

methodsA (probe) B (gallery)

Pick a selection Rank

Page 15: Loris  Bazzani Marco  Cristani

Matching algorithm

• Distance between two signatures

Bhattacharyya distance between HSV histograms,

Distances between blob descriptors

WHERE

Page 16: Loris  Bazzani Marco  Cristani

How to evaluate

• Cumulative Matching Characteristic (CMC) curve, the expectation of finding the correct match in the top n matches

Page 17: Loris  Bazzani Marco  Cristani

Ex. 1: The Datasets

• Exercise 1: take a look at the datasets and try to find out the challenges of the re-id problem

17

For this, you can use the MATLAB file:DEMO0_dataset.m

Page 18: Loris  Bazzani Marco  Cristani

Ex. 2: SDALF

• Exercise 2: qualitative analysis of the SDALF descriptor: display the weighted HSV hist., MSCR, RHSP

18

For this, you can use the MATLAB file:DEMO1_SDALFextraction.m

Page 19: Loris  Bazzani Marco  Cristani

Ex. 3: Cross-validation

• Exercise 3: try the cross-validation code evaluating CMC, SRR and nAUC– Compare SvsS and MvsM case– Vary the number of images for the MvsM case

19

For this, you can use the MATLAB file:DEMO2_crossvalid.m

[set MAXCLUSTER=1 (SvsS) or >1 (MvsM)]

Page 20: Loris  Bazzani Marco  Cristani

Ex 4: Matching

• Exercise 4: evaluate qualitatively the output of the matching procedure

20

For this, you can use the MATLAB file:DEMO2_crossvalid.m

[set plotMatch=1]And DEMO3_crossvalid.m

Page 21: Loris  Bazzani Marco  Cristani

Take-home Message

• Why this lesson?

– To be able to use our system on new datasets

– Compare your personal methods with SDALF

21

Questions?