Where, What, Whether: Multi-modal Learning Meets Pedestrian Detection

by   Yan Luo, et al.

Pedestrian detection benefits greatly from deep convolutional neural networks (CNNs). However, it is inherently hard for CNNs to handle situations in the presence of occlusion and scale variation. In this paper, we propose W^3Net, which attempts to address above challenges by decomposing the pedestrian detection task into Where, What and Whether problem directing against pedestrian localization, scale prediction and classification correspondingly. Specifically, for a pedestrian instance, we formulate its feature by three steps. i) We generate a bird view map, which is naturally free from occlusion issues, and scan all points on it to look for suitable locations for each pedestrian instance. ii) Instead of utilizing pre-fixed anchors, we model the interdependency between depth and scale aiming at generating depth-guided scales at different locations for better matching instances of different sizes. iii) We learn a latent vector shared by both visual and corpus space, by which false positives with similar vertical structure but lacking human partial features would be filtered out. We achieve state-of-the-art results on widely used datasets (Citypersons and Caltech). In particular. when evaluating on heavy occlusion subset, our results reduce MR^-2 from 49.3% to 18.7% on Citypersons, and from 45.18% to 28.33% on Caltech.


page 1

page 2

page 3

page 4

page 5

page 6

page 7

page 9


PedHunter: Occlusion Robust Pedestrian Detector in Crowded Scenes

Pedestrian detection in crowded scenes is a challenging problem, because...

3D Random Occlusion and Multi-Layer Projection for Deep Multi-Camera Pedestrian Localization

Although deep-learning based methods for monocular pedestrian detection ...

PCN: Part and Context Information for Pedestrian Detection with CNNs

Pedestrian detection has achieved great improvements in recent years, wh...

The Impact of Partial Occlusion on Pedestrian Detectability

Robust detection of vulnerable road users is a safety critical requireme...

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...

An Objective Method for Pedestrian Occlusion Level Classification

Pedestrian detection is among the most safety-critical features of drive...

NOH-NMS: Improving Pedestrian Detection by Nearby Objects Hallucination

Greedy-NMS inherently raises a dilemma, where a lower NMS threshold will...

Code Repositories


A paper list of object detection using deep learning.

view repo


From Handcrafted to Deep Features for Pedestrian Detection: A Survey

view repo