Sliding Windows as Segmentation Alyosha Efros Whats in

  • Slides: 15
Download presentation
Sliding Windows as Segmentation Alyosha Efros

Sliding Windows as Segmentation Alyosha Efros

What’s in common? cars faces pedestrians Coincidence?

What’s in common? cars faces pedestrians Coincidence?

Issue #1: Tougher objects Non-rectangular masks?

Issue #1: Tougher objects Non-rectangular masks?

People Detection in the Middle Ages Nuns in Procession. French ms. ca. 1300.

People Detection in the Middle Ages Nuns in Procession. French ms. ca. 1300.

Issue #2: Occlusions

Issue #2: Occlusions

e. g. PASCAL labels

e. g. PASCAL labels

The Right Spatial Support Bounding box 50 window

The Right Spatial Support Bounding box 50 window

The Right Spatial Support Bounding box 50 window Two issues: • Which Features? •

The Right Spatial Support Bounding box 50 window Two issues: • Which Features? • Over what support? Conjecture: getting better spatial support would allow for simpler features

Sliding Windows as Oversergmentation • Describes an image as an overlapping set of segments:

Sliding Windows as Oversergmentation • Describes an image as an overlapping set of segments: • Segments are typically: • Rectangular • Axis parallel • Set of scales Why not search over shape as well? • Too much work…

Mid-level cues (segmentation) Image 12 segmentations (96 overlapping segments) -Tu et al, DD-MCMC 2001,

Mid-level cues (segmentation) Image 12 segmentations (96 overlapping segments) -Tu et al, DD-MCMC 2001, Hoiem et al, Geometric Context, 2005; Russell et al, Object Discovery 2006

Proving my conjecture… Conjecture: getting better spatial support would allow for simpler features 1.

Proving my conjecture… Conjecture: getting better spatial support would allow for simpler features 1. Do multiple segmentations give you better spatial support? 2. Does better support actually help recognition? 3. Very fresh unpublished work with Tomasz

How well do segments cover objects?

How well do segments cover objects?

Object Covergate (NCut on MSRC)

Object Covergate (NCut on MSRC)

Does better spatial support help? Ground Truth Regions vs. Bounding Boxes

Does better spatial support help? Ground Truth Regions vs. Bounding Boxes

Grand Challenge: Image Parsing

Grand Challenge: Image Parsing