Direct multichannel tracking

Carlos Jaramillo, Yuichi Taguchi, Chen Feng

Research output: Chapter in Book/Report/Conference proceedingConference contribution


We present direct multichannel tracking, an algorithm for tracking the pose of a monocular camera (visual odometry) using high-dimensional features in a direct image alignment framework. Instead of using a single grayscale channel and assuming intensity constancy as in existing approaches, we extract multichannel features at each pixel from each image and assume feature constancy among consecutive images. High-dimensional features are more discriminative and robust to noise and image variations than intensities, enabling more accurate camera tracking. We demonstrate our claim using conventional hand-crafted features such as SIFT as well as more recent features extracted from convolutional neural networks (CNNs) such as Siamese and AlexNet networks. We evaluate the performance of our algorithm against the baseline case (single-channel tracking) using several public datasets, where the AlexNet feature provides the best pose estimation results.

Original languageEnglish (US)
Title of host publicationProceedings - 2017 International Conference on 3D Vision, 3DV 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Number of pages9
ISBN (Electronic)9781538626108
StatePublished - May 25 2018
Event7th IEEE International Conference on 3D Vision, 3DV 2017 - Qingdao, China
Duration: Oct 10 2017Oct 12 2017

Publication series

NameProceedings - 2017 International Conference on 3D Vision, 3DV 2017


Other7th IEEE International Conference on 3D Vision, 3DV 2017


  • 3D-reconstruction
  • CNN-features
  • Camera-Tracking
  • Camera-pose-estimation
  • Computer-vision
  • Dense-SIFT
  • Direct-method
  • Monocular-vision
  • Multichannel
  • Visual-odometry

ASJC Scopus subject areas

  • Media Technology
  • Computer Vision and Pattern Recognition
  • Signal Processing


Dive into the research topics of 'Direct multichannel tracking'. Together they form a unique fingerprint.

Cite this