Simple Baseline for Vehicle Pose Estimation: Experimental Validation

Significant progress on human and vehicle pose estimation has been achieved in recent years. The performance of these methods has evolved from poor to remarkable in just a couple of years. This improvement has been obtained from increasingly complex architectures. In this paper, we explore the appli...

Full description

Saved in:
Bibliographic Details
Published in:IEEE access 2020, Vol.8, p.132539-132550
Main Authors: Sanchez, Hector Corrales, Martinez, Antonio Hernandez, Gonzalo, Ruben Izquierdo, Parra, Noelia Hernandez, Alonso, Ignacio Parra, Fernandez-Llorca, David
Format: Article
Language:English
Subjects:
CNNs
Computer networks
Datasets
Detectors
experimental validation
heat maps
human pose estimation
Pose estimation
Solid modeling
Task analysis
Three-dimensional displays
Two dimensional displays
vehicle keypoints detection
Vehicle pose estimation
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Significant progress on human and vehicle pose estimation has been achieved in recent years. The performance of these methods has evolved from poor to remarkable in just a couple of years. This improvement has been obtained from increasingly complex architectures. In this paper, we explore the applicability of simple baseline methods by adding a few deconvolutional layers on a backbone network to estimate heat maps that correspond to the vehicle keypoints. This approach has been proven to be very effective for human pose estimation. The results are analyzed on the PASCAL3D+ dataset, achieving state-of-the-art results. In addition, a set of experiments has been conducted to study current shortcomings in vehicle keypoints labelling, which adversely affect performance. A new strategy for defining vehicle keypoints is presented and validated with our customized dataset with extended keypoints.
ISSN:2169-3536
2169-3536
DOI:10.1109/ACCESS.2020.3010307