Feature Calibration Network for Occluded Pedestrian Detection

12/12/2022
by   Tianliang Zhang, et al.
1

Pedestrian detection in the wild remains a challenging problem especially for scenes containing serious occlusion. In this paper, we propose a novel feature learning method in the deep learning framework, referred to as Feature Calibration Network (FC-Net), to adaptively detect pedestrians under various occlusions. FC-Net is based on the observation that the visible parts of pedestrians are selective and decisive for detection, and is implemented as a self-paced feature learning framework with a self-activation (SA) module and a feature calibration (FC) module. In a new self-activated manner, FC-Net learns features which highlight the visible parts and suppress the occluded parts of pedestrians. The SA module estimates pedestrian activation maps by reusing classifier weights, without any additional parameter involved, therefore resulting in an extremely parsimony model to reinforce the semantics of features, while the FC module calibrates the convolutional features for adaptive pedestrian representation in both pixel-wise and region-based ways. Experiments on CityPersons and Caltech datasets demonstrate that FC-Net improves detection performance on occluded pedestrians up to 10 maintaining excellent performance on non-occluded instances.

READ FULL TEXT

page 1

page 3

page 4

page 5

page 7

page 8

page 10

page 11

research
12/12/2022

CircleNet: Reciprocating Feature Adaptation for Robust Pedestrian Detection

Pedestrian detection in the wild remains a challenging problem especiall...
research
04/07/2021

V2F-Net: Explicit Decomposition of Occluded Pedestrian Detection

Occlusion is very challenging in pedestrian detection. In this paper, we...
research
01/25/2020

PSC-Net: Learning Part Spatial Co-occurence for Occluded Pedestrian Detection

Detecting pedestrians, especially under heavy occlusions, is a challengi...
research
10/25/2019

Gated Multi-layer Convolutional Feature Extraction Network for Robust Pedestrian Detection

Pedestrian detection methods have been significantly improved with the d...
research
12/18/2019

Coupled Network for Robust Pedestrian Detection with Gated Multi-Layer Feature Extraction and Deformable Occlusion Handling

Pedestrian detection methods have been significantly improved with the d...
research
03/16/2020

PS-RCNN: Detecting Secondary Human Instances in a Crowd via Primary Object Suppression

Detecting human bodies in highly crowded scenes is a challenging problem...
research
12/02/2018

Pedestrian Detection with Autoregressive Network Phases

We present an autoregressive pedestrian detection framework with cascade...

Please sign up or login with your details

Forgot password? Click here to reset