Tampere University of Technology

TUTCRIS Research Portal

Visibility-Aware Part Coding for Vehicle Viewing Angle Estimation

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Details

Original languageEnglish
Title of host publication9th International Conference on Information Science and Technology, ICIST 2019
PublisherIEEE
Pages65-70
Number of pages6
ISBN (Electronic)9781728121062
DOIs
Publication statusPublished - 1 Aug 2019
Publication typeA4 Article in a conference publication
EventIEEE International Conference on Information Science and Technology - Hulunbuir, China
Duration: 2 Aug 20195 Aug 2019

Conference

ConferenceIEEE International Conference on Information Science and Technology
CountryChina
CityHulunbuir
Period2/08/195/08/19

Abstract

A number of spatially-localised semantic parts of vehicles sensitive to pose changes are encoded their visible probabilities into a mid-level feature vector. Car pose estimation is then formulated into a regression on concatenated low-and mid-level features to continuously changing viewing angles. Each dimension of our visibility-Aware part codes separates all the training samples into two groups according to its visual existence in images, which provides additional part-specific range constraint of viewing angles. Moreover, the proposed codes can alleviate the suffering from sparse and imbalanced data distribution in the light of modelling latent dependency across angle targets. Experimental evaluation for car pose estimation on the EPFL Multi-View Car benchmark demonstrates significant improvement of our method over the state-of-The-Art regression methods, especially when only sparse and imbalanced data is available.

Keywords

  • Car pose estimation, Coding, Pose-sensitive parts, Regression forests, Visibility-Aware

Publication forum classification

Field of science, Statistics Finland