VoNet: Vehicle orientation classification using convolutional neural network

Ratanaksamrith You, Jang Woo Kwon

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

4 Scopus citations

Abstract

This paper presents a novel convolution neural network for classifying the orientation (or viewpoint) of a vehicle in a given image. Current equipping sensors in self-driving car is able to produce bounding box of vehicles in the proximity, but it does not recognize the viewpoint of them. Analyzing surrounding cars' direction in very complex environment has a significant role for autonomous driving. Utilizing nothing but a captured image, the purpose of this research is to classify viewpoint of vehicle: (1) front; (2) rear; (3) side; (4) front-side; and (5) rear-side. Deep convolutional neural network is used as the tool in performing classification task. The approach involves examining different CNN architectures using a large scale car dataset. In addition to that, the goal of the model is to be small and fast enough for limited hardware resource. We are able to achieve 95% accuracy, 57ms inference time on NVIDIA GRID K520 GPU, and 1.6 MB Caffe model size.

Original languageEnglish
Title of host publicationProceedings of 2016 the 2nd International Conference on Communication and Information Processing, ICCIP 2016
PublisherAssociation for Computing Machinery
Pages195-199
Number of pages5
ISBN (Electronic)9781450348195
DOIs
StatePublished - 26 Nov 2016
Event2nd International Conference on Communication and Information Processing, ICCIP 2016 - Singapore, Singapore
Duration: 26 Nov 201629 Nov 2016

Publication series

NameACM International Conference Proceeding Series

Conference

Conference2nd International Conference on Communication and Information Processing, ICCIP 2016
Country/TerritorySingapore
CitySingapore
Period26/11/1629/11/16

Bibliographical note

Publisher Copyright:
© 2016 ACM.

Keywords

  • Autonomous vehicle
  • Deep convolutional neural network
  • Orientation classification

Fingerprint

Dive into the research topics of 'VoNet: Vehicle orientation classification using convolutional neural network'. Together they form a unique fingerprint.

Cite this