University of Surrey

Test tubes in the lab Research in the ATI Dance Research

Manifold-based Visual Object Counting

Wang, Yi, Zou, Yuexian and Wang, Wenwu (2018) Manifold-based Visual Object Counting IEEE Transactions on Image Processing.

[img] Text
Manifold-based Visual Object Counting.pdf - Accepted version Manuscript
Restricted to Repository staff only until 22 January 2020.

Download (4MB)


Visual object counting (VOC) is an emerging area in computer vision which aims to estimate the number of objects of interest in a given image or video. Recently, object density based estimation method is shown to be promising for object counting as well as rough instance localization. However, the performance of this method tends to degrade when dealing with new objects and scenes. To address this limitation, we propose a manifold-based method for visual object counting (M-VOC), based on the manifold assumption that similar image patches share similar object densities. Firstly, the local geometry of a given image patch is represented linearly by its neighbors using a predefined patch training set, and the object density of this given image patch is reconstructed by preserving the local geometry using locally linear embedding. To improve the characterization of local geometry, additional constraints such as sparsity and non-negativity are also considered via regularization, nonlinear mapping, as well as kernel trick. Compared with the state-of-the-art VOC methods, our proposed M-VOC methods achieve competitive performance on seven benchmark datasets. Experiments verify that the proposed M-VOC methods have several favorable properties, such as robustness to the variation in the size of training dataset and image resolution, as often encountered in real-world VOC applications.

Item Type: Article
Divisions : Faculty of Engineering and Physical Sciences > Electronic Engineering
Authors :
Date : 2018
Copyright Disclaimer : © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works
Uncontrolled Keywords : Visual object counting; Object density map estimation; Manifold-based; Locally linear embedding; Manifold assumption; Kernel method
Depositing User : Clive Harris
Date Deposited : 25 Jan 2018 15:13
Last Modified : 25 Jan 2018 15:13

Actions (login required)

View Item View Item


Downloads per month over past year

Information about this web site

© The University of Surrey, Guildford, Surrey, GU2 7XH, United Kingdom.
+44 (0)1483 300800