Moving object recognition using multi-view three-dimensional convolutional neural networks

Tao He, Hua Mao, Zhang Yi

Research output: Contribution to journalArticlepeer-review

35 Citations (Scopus)
36 Downloads (Pure)

Abstract

Moving object recognition (MOR) is an important but challenging problem in the field of computer vision. The aim of MOR is to recognize moving objects in a given video dataset. Convolutional neural networks (CNNs) have been extensively used for image recognition and video analysis problems. Recently, a 3D-CNN, which contains 3D convolution layers, was proposed to address MOR problems by successfully extracting spatiotemporal features. In this paper, a multi-view (MV) 3D-CNN is proposed for MOR. This model combines 3D-CNNs with a well-known MV learning technique. Because multi-view learning techniques have the ability to obtain more view-related features from videos captured by different cameras, the proposed model can extract more representative features. Moreover, the model contains a special view-pooling layer that can fuse the feature information from previous layers. The proposed MV3D-CNN is applied to both real-world moving vehicle recognition and sign language recognition tasks. The experimental results show that the proposed model possesses good performance.
Original languageEnglish
Pages (from-to)3827-3835
Number of pages9
JournalNeural Computing and Applications
Volume28
Issue number12
Early online date23 Mar 2016
DOIs
Publication statusPublished - Dec 2017

Keywords

  • Moving object recognition
  • Multi-view learning
  • 3D convolutional neural networks
  • Feature extraction
  • Deep learning

Fingerprint

Dive into the research topics of 'Moving object recognition using multi-view three-dimensional convolutional neural networks'. Together they form a unique fingerprint.

Cite this