View Code? Open in Web Editor NEW

[F2DNet] Fast Focal Detection Network for Pedestrian Detection

License: Apache License 2.0

Python 67.51% C++ 1.73% Cuda 3.41% Shell 0.06% MATLAB 3.86% Jupyter Notebook 23.26% Dockerfile 0.03% Cython 0.15%

f2dnet's Introduction

F2DNet

F2DNet is a Pedestron based repository which implements a novel, two-staged detector i.e. Fast Focal Detection Network for pedestrian detection.

Installation

Please refer to base repository for step-by-step installation.

List of detectors

In addition to configuration for different detectors provided in base repository we provide configuration for F2DNet.

Following datasets are currently supported

Datasets Preparation

Please refer to base repository for dataset preparation.

Benchmarking

Benchmarking of F2DNet on pedestrian detection datasets

Dataset	↓Reasonable	↓Small	↓Heavy
CityPersons	8.7	11.3	32.6
EuroCityPersons	6.1	10.7	28.2
Caltech Pedestrian	2.2	2.5	38.7

Benchmarking of F2DNet when trained using extra data on pedestrian detection datasets

Dataset	Config	Model	↓Reasonable	↓Small	↓Heavy
CityPersons	cascade_hrnet	Cascade Mask R-CNN	7.5	8.0	28.0
CityPersons	ecp_cp	F2DNet	7.8	9.4	26.2
Caltech Pedestrian	cascade_hrnet	Cascade Mask R-CNN	1.7		25.7
Caltech Pedestrian	ecp_cp_caltech	F2DNet	1.7	2.1	20.4

References

Pedestron

Please cite the following work

AxXiv2022

@Article{khan:2022,
  author      = {Khan, Abdul Hannan AND Munir, Mohsin AND Elst, Ludger van AND Dengel, Andreas},
  title       = {F2DNet: Fast Focal Detection Network for Pedestrian Detection},
  version     = {1},
  date        = {2022-03-04},
  eprinttype  = {arxiv},
  eprintclass = {cs.CV, I.2.10; I.4.8; I.5.4},
  eprint      = {http://arxiv.org/abs/2203.02331v1},
  url         = {http://arxiv.org/abs/2203.02331v1}
}

Recommend Projects