V2F-Net: Explicit Decomposition of Occluded Pedestrian Detection

by   Mingyang Shang, et al.

Occlusion is very challenging in pedestrian detection. In this paper, we propose a simple yet effective method named V2F-Net, which explicitly decomposes occluded pedestrian detection into visible region detection and full body estimation. V2F-Net consists of two sub-networks: Visible region Detection Network (VDN) and Full body Estimation Network (FEN). VDN tries to localize visible regions and FEN estimates full-body box on the basis of the visible box. Moreover, to further improve the estimation of full body, we propose a novel Embedding-based Part-aware Module (EPM). By supervising the visibility for each part, the network is encouraged to extract features with essential part information. We experimentally show the effectiveness of V2F-Net by conducting several experiments on two challenging datasets. V2F-Net achieves 5.85 compared to FPN baseline. Besides, the consistent gain on both one-stage and two-stage detector validates the generalizability of our method.



There are no comments yet.


page 1

page 4

page 7

page 8


Mutual-Supervised Feature Modulation Network for Occluded Pedestrian Detection

State-of-the-art pedestrian detectors have achieved significant progress...

Occluded Pedestrian Detection with Visible IoU and Box Sign Predictor

Training a robust classifier and an accurate box regressor are difficult...

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

Detecting pedestrians, especially under heavy occlusions, is a challengi...

Detection of Partially Visible Objects

An "elephant in the room" for most current object detection and localiza...

Semantic Head Enhanced Pedestrian Detection in a Crowd

Pedestrian detection in the crowd is a challenging task because of intra...

On multiple connectedness of regions visible due to multiple diffuse reflections

It is known that the region V(s) of a simple polygon P, directly visible...

NMS by Representative Region: Towards Crowded Pedestrian Detection by Proposal Pairing

Although significant progress has been made in pedestrian detection rece...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.