Multi-Class Object Detection Using 2D Poses

Christopher Mayershofer, Ala Hammami, Johannes Fottner

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

1 Scopus citations

Abstract

Object detection (OD) methods are finding application in various fields. The OD problem can be divided into two sub-problems, namely object classification and localization. While the former aims to answer the question what class a given object belongs to, the latter focuses on locating an object within a given image. For localization, both implicit representations, which border the object and its features (e.g. bounding boxes, polygons and masks), and explicit representations, which describe the object's pose in an image (e.g. 6D pose, keypoints), are used. The 2D pose is a simple, yet effective representation that has so far been overlooked. In this paper, we therefore motivate and formulate the use of 2D poses for object localization. Furthermore, we present RetinaNet-2DP, an anchor-based convolutional neural network (CNN) that is capable of detecting objects using 2D poses. To do so, we propose the idea of Anchor Poses and the Gaussian Kernel Distance as a similarity metric between poses. Experiments on the DOTA dataset and two robotics use cases from industry emphasize the performance of the network architecture and more generally demonstrate the potential of the proposed localization representation. Finally, we critically assess our findings and present an outlook of future work.

Original languageEnglish
Title of host publicationProceedings - 19th IEEE International Conference on Machine Learning and Applications, ICMLA 2020
EditorsM. Arif Wani, Feng Luo, Xiaolin Li, Dejing Dou, Francesco Bonchi
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages647-652
Number of pages6
ISBN (Electronic)9781728184708
DOIs
StatePublished - Dec 2020
Event19th IEEE International Conference on Machine Learning and Applications, ICMLA 2020 - Virtual, Miami, United States
Duration: 14 Dec 202017 Dec 2020

Publication series

NameProceedings - 19th IEEE International Conference on Machine Learning and Applications, ICMLA 2020

Conference

Conference19th IEEE International Conference on Machine Learning and Applications, ICMLA 2020
Country/TerritoryUnited States
CityVirtual, Miami
Period14/12/2017/12/20

Keywords

  • 2D Pose
  • Computer Vision
  • Object Detection

Fingerprint

Dive into the research topics of 'Multi-Class Object Detection Using 2D Poses'. Together they form a unique fingerprint.

Cite this