The Fastest Deformable Part Model for Object Detection

@article{Yan2014TheFD,
  title={The Fastest Deformable Part Model for Object Detection},
  author={Junjie Yan and Zhen Lei and Longyin Wen and Stan Z. Li},
  journal={2014 IEEE Conference on Computer Vision and Pattern Recognition},
  year={2014},
  pages={2497-2504}
}
This paper solves the speed bottleneck of deformable part model (DPM), while maintaining the accuracy in detection on challenging datasets. Three prohibitive steps in cascade version of DPM are accelerated, including 2D correlation between root filter and feature map, cascade part pruning and HOG feature extraction. For 2D correlation, the root filter is constrained to be low rank, so that 2D correlation can be calculated by more efficient linear combination of 1D correlations. A proximal… CONTINUE READING

Similar Papers

Citations

Publications citing this paper.
SHOWING 1-10 OF 138 CITATIONS

Flexible 3D neighborhood cascade deformable part models for object detection

  • 2017 IEEE International Conference on Image Processing (ICIP)
  • 2017
VIEW 18 EXCERPTS
CITES METHODS, BACKGROUND & RESULTS
HIGHLY INFLUENCED

Adaptive cascade threshold learning from negative samples for deformable part models

  • 2017 IEEE International Conference on Image Processing (ICIP)
  • 2017
VIEW 7 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Single-Shot Scale-Aware Network for Real-Time Face Detection

  • International Journal of Computer Vision
  • 2019
VIEW 8 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

A Low Power Hardware Implementation of Multi-Object DPM Detector for Autonomous Driving

  • 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
  • 2018
VIEW 4 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

A Fast and Accurate Unconstrained Face Detector

  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2016
VIEW 9 EXCERPTS
CITES METHODS, BACKGROUND & RESULTS
HIGHLY INFLUENCED

Fast region-based DPM object detection for autonomous vehicles

  • 2016 IEEE 59th International Midwest Symposium on Circuits and Systems (MWSCAS)
  • 2016
VIEW 10 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Robust online face detection and tracking

VIEW 9 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Boosting Speed and Accuracy in Deformable Part Models for Face Image in the Wild

  • 2015 International Conference on Advanced Computing and Applications (ACOMP)
  • 2015
VIEW 6 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2013
2019

CITATION STATISTICS

  • 23 Highly Influenced Citations

  • Averaged 23 Citations per year from 2017 through 2019

References

Publications referenced by this paper.
SHOWING 1-10 OF 37 REFERENCES

Face detection, pose estimation, and landmark localization in the wild

  • 2012 IEEE Conference on Computer Vision and Pattern Recognition
  • 2012
VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

Pedestrian Detection: An Evaluation of the State of the Art

  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2012
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Cascade object detection with deformable part models

  • 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
  • 2010
VIEW 10 EXCERPTS
HIGHLY INFLUENTIAL

The Pascal Visual Object Classes (VOC) Challenge

VIEW 14 EXCERPTS
HIGHLY INFLUENTIAL

Fast Feature Pyramids for Object Detection

  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2014
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL