On Detection of Multiple Object Instances using Hough Transforms
This presentation is the property of its rightful owner.
Sponsored Links
1 / 18

On Detection of Multiple Object Instances using Hough Transforms PowerPoint PPT Presentation


  • 121 Views
  • Uploaded on
  • Presentation posted in: General

On Detection of Multiple Object Instances using Hough Transforms. Olga Barinova Moscow State University. Victor Lempitsky University of Oxford. Pushmeet Kohli Microsoft Research Cambridge. Hough transforms. Object detection → peaks identification in Hough images Beyond lines!!!

Download Presentation

On Detection of Multiple Object Instances using Hough Transforms

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


On detection of multiple object instances using hough transforms

On Detection of Multiple Object Instances using Hough Transforms

Olga Barinova

Moscow State University

Victor Lempitsky

University of Oxford

Pushmeet Kohli

Microsoft Research Cambridge


Hough transforms

Hough transforms

  • Object detection → peaks identification in Hough images

  • Beyond lines!!!

    • Ballard 1983 – Other primitives

    • Lowe, ICCV 1999 – Object detection

    • Leibe, Schiele BMVC 2003 – Object class detection

    • Last CVPR: Maji& Malik, Gall& Lempitsky, Gu et al. …


On detection of multiple object instances using hough transforms

Category-level object detection

Example from Gall &Lempitsky CVPR 2009


Category level object detection

Category-level object detection

?


Multiple lines detection

Multiple lines detection

  • Identifying the peaks in Hough images is highly nontrivial in case of multiple close objects

  • Postprocessing (e.g. non-maximum suppression) is usually used

  • Our framework is similar to Hough Transforms but doesn’t require finding local maxima and suppresses non-maxima automatically


Our framework

Elements space

Hough space

Our framework

Hypotheses

Voting elements


Our framework1

Elements space

Hough space

Our framework

1

2

3

x – labelling of voting elements,

xi = index of hypothesis,

if element votes for hypothesis,

xi = 0, if element votes for background

y – labelling of hypotheses, binary variables:

1 = object is present,

0 = otherwise


Our framework2

Elements space

Hough space

Our framework

x2=1

x3=1

x1=1

1

y1=1

y2=1

x4=2

2

y3=0

3

x8=2

x – labelling of voting elements,

xi = index of hypothesis,

if element votes for hypothesis,

xi = 0, if element votes for background

y – labelling of hypotheses, binary variables:

1 = object is present,

0 = otherwise

x6=2

x7=0

x5=2

Key idea : joint MAP-inference in x and y


Probabilistic derivation

Probabilistic derivation

Likelihood Term

  • Assume that given the existing objects y and the hypotheses assignmentsx, the distributions of the descriptors of voting elements are independent

  • Less crude than the independence assumption implicitly made by the traditional Hough

  • Prior Term

  • Occam razor (or MDL) prior penalizes the number of the active hypotheses


Probabilistic derivation1

Probabilistic derivation

voting elements

0

1

2

3

0

0

1

-∞ if xi = h, and yh = 0

0, otherwise

1

how likely is that voting element belongs to an object

Corresponds to the votes in standard Hough transform: Training stays the same!

2

3

0

0

1

“MDL” prior:

λ, if yh = 1

0, otherwise

1

2

3

0

1

0

2

1

3

Problem known as facility location

hypotheses

0

[Delong et al. CVPR 2010] (today’s poster) looks at facility location with wider set of priors

1

2

3


Probabilistic derivation2

Probabilistic derivation

0

voting elements

1

2

3

  • Tried different methods for MAP-inference

    • belief propagation

    • simulated annealing

  • They work well but don’t allow using large number of hypotheses

    • graph becomes huge and dense

    • sparsification heuristics required

0

0

1

1

2

3

0

0

1

1

2

3

0

1

0

2

1

3

hypotheses

0

1

2

3


Probabilistic derivation3

Probabilistic derivation

0

voting elements

1

2

3

  • If labeling of y is given the values ofxiare independent

  • After maximizing out xwe get:

  • Large-clique, submodular

  • Greedy algorithm is as good as anything else (in terms of the approximation factor)

  • Greedy inference ~ iterative Hough voting

0

0

1

1

2

3

0

0

1

1

2

3

0

1

0

2

1

3

hypotheses

0

1

2

3


Greedy maximization for our energy

Greedy maximization for our energy

Greedily add detections starting from the empty set

For each iteration

do the voting:

Seth0 = the overall maximum of HoughImage

IfHoughImage(h0) > λ, add h0 to detection set, else terminate

“standard” Hough vote for element i

Maximum over Hough votes for the hypotheses g that have already been switched on, including ‘background’

Sum over all voting elements


Inference

Inference

Using the Hough forest trained in [Gall&Lempitsky CVPR09]

Datasets from [Andriluka et al. CVPR 2008](with strongly occluded pedestrians added)


Results for pedestrians detection

Results for pedestrians detection

Hough transform

+ non-maximum suppression

Our framework

White = correct detection

Green = missing object

Red = false positive


Results for pedestrians detection1

Results for pedestrians detection

TUD-crossing

TUD-campus

Precision

Precision

Recall

Recall

Blue = Hough transform + non-maximum suppression

Light-blue = our framework


Results for lines detection

Results for lines detection

York Urban DB, Elder&Estrada ECCV 2008

  • our framework is able to discern very close yet distinct lines, and is in general much less plagued by spurious detections

Our framework

Hough + NMS


Conclusion

Conclusion

  • Framework for detecting multiple objects, greedy inference ~ iterated Hough transform

  • No need to find local maxima and suppress non-maxima – just take the only global maximum

  • Probabilistic model allows for extensions(ECCV paper coming: lines + vanishing points + horizon + zenith)

  • Training stays the same as for the recent Hough-based framework

  • Code available at the project page: http://graphics.cs.msu.ru/en/

    science/research/machinelearning/hough

Thank you for your attention!


  • Login