On-device scalable image-based localization via prioritized cascade search and fast one-many RANSAC

Ngoc-Trung Tran, Dang-Khoa Le Tan, Anh-Dzung Doan, Thanh-Toan Do, Tuan-Anh Bui, Mengxuan Tan, Ngai-Man Cheung

Research output: Contribution to journalArticleResearchpeer-review

27 Citations (Scopus)


We present the design of an entire on-device system for large-scale urban localization using images. The proposed design integrates compact image retrieval and 2D-3D correspondence search to estimate the location in extensive city regions. Our design is GPS agnostic and does not require network connection. In order to overcome the resource constraints of mobile devices, we propose a system design that leverages the scalability advantage of image retrieval and accuracy of 3D model-based localization. Furthermore, we propose a new hashing-based cascade search for fast computation of 2D-3D correspondences. In addition, we propose a new one-many RANSAC for accurate pose estimation. The new one-many RANSAC addresses the challenge of repetitive building structures (e.g. windows and balconies) in urban localization. Extensive experiments demonstrate that our 2D-3D correspondence search achieves the state-of-the-art localization accuracy on multiple benchmark datasets. Furthermore, our experiments on a large Google street view image dataset show the potential of large-scale localization entirely on a typical mobile device.

Original languageEnglish
Pages (from-to)1675-1690
Number of pages16
JournalIEEE Transactions on Image Processing
Issue number4
Publication statusPublished - Apr 2019
Externally publishedYes


  • 2D-3D correspondence search
  • hashing
  • image retrieval
  • Image-based localization
  • on-device localization

Cite this