Open Access
Dimensionality reduction-based building recognition
Jing Li,Nigel M. Allinson +1 more
Reads0
Chats0
TLDR
A building recognition scheme is proposed, which integrates biologically-inspired feature extraction and dimensionality reduction and demonstrates that the proposed scheme can achieve satisfactory results.Abstract:
Object recognition is being paid more and more attention in computer vision research and a variety of algorithms have been put forward to enhance the recognition performance. However, building recognition, a relatively specific recognition task, is still at a preliminary stage of development, because the challenging task includes rotation, scaling, illumination changes, occlusion, etc. A building recognition scheme is proposed in this paper, which integrates biologically-inspired feature extraction and dimensionality reduction. Experiments undertaken on our own constructed building database demonstrate that our proposed scheme can achieve satisfactory results.read more
Citations
More filters
Proceedings Article
Semi-supervised dictionary learning via structural sparse preserving
TL;DR: This paper presents a novel semi-supervised dictionary learning method which utilizes the structural sparse relationships between the labeled and unlabeled samples and proposes an efficient optimization algorithm to solve the problem based on the block coordinate descent method.
Journal ArticleDOI
A computer vision-based perception system for visually impaired
TL;DR: A motion-based, real-time object detection and classification method, dedicated to the autonomous navigation of visually impaired people, and multi-object identification and tracking is applied in order to guide the user to localize such objects of interest.
Proceedings ArticleDOI
Recognition of urban buildings with spatial consistency and a small-sized vocabulary tree
TL;DR: This work exploits a small-sized vocabulary-tree of SIFT descriptors to address the problem of building recognition as a mobile application and shows state of the art accuracy while ensuring reduced memory and computational requirements.
Proceedings ArticleDOI
Semi-Supervised Dictionary Learning Based on Atom Graph Regularization
TL;DR: A novel unified optimization framework for semi-supervised dictionary learning, which optimizes a graph Laplacian component and the dictionary simultaneously simultaneously, and derives an efficient algorithm by combining the block coordinate descent method with the alternating direction method of multipliers to solve the unified optimization problem.
Proceedings ArticleDOI
Structural Dictionary Learning based on Non-convex Surrogate of ℓ₂,₁ Norm for Classification
TL;DR: A general solver is given for the corresponding optimization algorithm of group sparse representation using non-convex surrogate of $\ell_{2,0}$ to solve the issue of over-punishment phenomenon.