Multiple Feature Fusion Based on Co-Training Approach and Time Regularization for Place Classification in Wearable Video

Free registration required

Executive Summary

In this paper, the authors focus on the problem of automatic visual place recognition in a weakly constrained environment, targeting the indexing of video streams by topological place recognition. They propose to combine several machine learning approaches in a time regularized framework for image-based place recognition indoors. The framework combines the power of multiple visual cues and integrates the temporal continuity information of video. They extend it with computationally efficient semi-supervised method leveraging unlabeled video sequences for an improved indexing performance. The proposed approach was applied on challenging video corpora. Experiments on a public and a real-world video sequence databases show the gain brought by the different stages of the method.

  • Format: PDF
  • Size: 4537.3 KB