Detection by detections non parametric detector adaptation for a video
Download
1 / 22

Detection by Detections: Non-parametric Detector Adaptation for a Video - PowerPoint PPT Presentation


  • 127 Views
  • Uploaded on

Detection by Detections: Non-parametric Detector Adaptation for a Video. Outline. Introduction Non-parametric detector adaption Binary codes with a vocabulary tree Similarity measure of the binary codes Transfer classification Identity grouping of detections Experiment Conclusion.

loader
I am the owner, or an agent authorized to act on behalf of the owner, of the copyrighted work described.
capcha
Download Presentation

PowerPoint Slideshow about ' Detection by Detections: Non-parametric Detector Adaptation for a Video' - crwys


An Image/Link below is provided (as is) to download presentation

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.


- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -
Presentation Transcript

Outline
Outline for a Video

  • Introduction

  • Non-parametric detector adaption

    • Binary codes with a vocabulary tree

    • Similarity measure of the binary codes

    • Transfer classification

    • Identity grouping of detections

  • Experiment

  • Conclusion


Introduction
Introduction for a Video


Introduction1
Introduction for a Video

Extend any static-image-based object detector to video object detection.

Needs neither the original training data, nor manually labeled online examples.


Non parametric detector adaption
Non-parametric detector for a Videoadaption

1.Set generic human detector work on high recall low precision point

2.To build a vocabulary tree using hierarchical k-means[19]

3.Encode the set of most confident visual detections as a set of binary vectors

[19] D. Nister and H. Stewenius. Scalable recognition with a vocabulary tree. In CVPR, 2006.



Binary codes with a vocabulary tree1
Binary codes with a vocabulary for a Videotree

Define a mapping T


Similarity measure of the binary codes
Similarity measure of the binary codes for a Video

||c||: the number of non-zero bits in the binary vector c


Transfer classification
Transfer for a Videoclassification

compose positive pool

change

representation

similarity scoring

final classification

decision


Identity grouping of detections
Identity grouping of detections for a Video

Group ID g(u) of any other example u


Experiment
Experiment for a Video

The normalization scheme evaluation


Experiment1
Experiment for a Video

The evaluation on the threshold for positive pool


Experiment2
Experiment for a Video

The tree depth exploration


Experiment3
Experiment for a Video

Performance of video object detection

Data is from the EC Funded CAVIAR project/IST 2001 37540

http://homepages.inf.ed.ac.uk/rbf/CAVIAR/


Experiment4
Experiment for a Video


Experiment5
Experiment for a Video

Present the adaption performance based on [6]

[6] P. Felzenszwalb, D. McAllester, and D. Ramanan. A discriminatively

trained, multiscale, deformable part model. In

CVPR, 2008.


Experiment6
Experiment for a Video


Experiment7
Experiment for a Video

Identity grouping

F(mode(gi)) counts the number of examples in group i with identity mode(gi)


Experiment8
Experiment for a Video

On positive pool

On all detection


Experiment9
Experiment for a Video

Difficult to be detected objects in video


Experiment10
Experiment for a Video

First row by our approach

Second row by k-means clustering


Conclusion
Conclusion for a Video

Simple and effective solution to improve the pure detection accuracy of off-shelf detectors trained from static images on target videos.


ad