1 / 23

Goal

Visual Attention Accelerated Vehicle Detection in Low-Altitude Airborne Video of Urban Environment. Xianbin Cao, Senior Member, IEEE, Renjun Lin, Pingkun Yan, Senior Member, IEEE, and Xuelong Li, Senior Member, IEEE

dolph
Download Presentation

Goal

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. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Visual Attention Accelerated Vehicle Detection in Low-Altitude Airborne Video of Urban Environment Xianbin Cao, Senior Member, IEEE, Renjun Lin, Pingkun Yan, Senior Member, IEEE,andXuelong Li, Senior Member, IEEE IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY MARCH 2012

  2. Goal

  3. Outline • Introduction • Salient region extraction • Obtain regions from saliency map • Classify vehicles • Experiments

  4. Introduction • For improving road safety and reducing urban traffic congestions caused by the increasing number of vehicles. • Most of the AVDSs adopt expensive devices suchasinfrared cameras , GPS, and high resolution satellite cameras for sensing more information • Usesingle optical camera is more efficient.

  5. Introduction

  6. Salient region extraction

  7. Salient region extraction • For color features • r, g,b,R,G,B,Y seven features • R=r-(g+b)/2 ,G=g-(r+b)/2 B=b-(r+g)/2 , Y=(r+g+b)/3

  8. Salient region extraction • For orientation features • Use Gabor filters to generate local orientation feature maps from intensity image I • G(σ, θ, f ) , σ = 2, f = 1 θ as {0°, 45°, 90°, 135°}  four features

  9. Salient region extraction • For motion features • the temporal differences between the current frame and the three previous frames were computed with intervals of {1, 2, 3} • Three features

  10. Salient region extraction • 14 feature maps are computed for salient region extraction

  11. Salient region extraction • i ∈ {0, 1, 2} represents • j ∈ {0, 1, 2 ,…} represents the serial numbers • operator N(*) normalize

  12. Salient region extraction

  13. Difference without N

  14. Obtain regions from saliency map

  15. Obtain regions from saliency map • To effectively obtain the salient regions from the final saliency map, we designed an iterative strategy using inhibition map (IM) and enhancement map (EM). • IM:avoid picking same area again • EM:enhance regions around the detected vehicle.

  16. Obtain regions from saliency map

  17. Obtain regions from saliency map • Filter by size

  18. Classify vehicles • Use cascaded classifier • 4000 vehicle (positive) samples ,2000 for train and 2000 for test. • 6000 non-vehicle (negative) samples • All samples scaled to 32*16

  19. Experiments • Xeon x5660 2.8 GHz computer • 4 GB DDR3-1066 • 3 h of video in both the urban and highway environments • The testing videos of traffic were captured with the height around 90 m. • size of the video frames is 511×286

  20. Experiments

  21. Experiments

  22. Experiments • ratio of recall rate (RR) and salient region percentage (SRP), which represents the efficiency of the salient regions extraction, is used as the evaluation criterion. • High RR/SRP indicates that more vehicles can be covered by less extracted salient regions.

  23. Experiments

More Related