By a News Reporter-Staff News Editor at Journal of Robotics & Machine Learning -- New research on Pattern Analysis is the subject of a report. According to news reporting originating in Hubei, People’s Republic of China, by VerticalNews journalists, research stated, “Person re-identification (re-id), aiming to search a specific person among a non-overlapping camera network, has attracted plenty of interest in recent years. This task is highly challenging, especially when there exists only single image per person in the database.”
Financial support for this research came from National Natural Science Foundation of China.
The news reporters obtained a quote from the research from the Huazhong University of Science and Technology, “In this paper, we present an algorithm for learning a Mahalanobis distance for person re-identification. Our method has two distinctive features: (1) to obtain the best separability of the training data, we first minimize the intra-class distances to the most extent by forcing intra-class distances to be zero, and (2) to promote the generalization ability of the learned metric, we then maximize the minimum margin between different classes. Inspired by the simple geometric intuition that a regular simplex maximizes its minimum side length, provided the sum of all side length is fixed, our method, called EquiDistance constrained Metric Learning (EquiDML), applies least-square regression technique to map images of the same person to the same vertex of a regular simplex, and images of different persons to different vertices of a regular simplex. Consequently, under the learned metric, images of the same class are collapsed to a single point, while images of different classes are transformed to be equidistant. This simple motivation is further formulated as a convex optimization problem, solved by the projected gradient descent method and proved to be very effective in person re-identification task.”
According to the news reporters, the research concluded: “Although it is fairly simple, our method outperforms the state-of-the-art methods on CUHK01, CUHK03, Market1501 and DukeMTMC-relD datasets, and achieves very competitive performance on the widely used VIPeR dataset.”
For more information on this research see: Equidistance constrained metric learning for person re-identification. Pattern Recognition , 2018;74():38-51. Pattern Recognition can be contacted at: Elsevier Sci Ltd, The Boulevard, Langford Lane, Kidlington, Oxford OX5 1GB, Oxon, England. (Elsevier - www.elsevier.com; Pattern Recognition - http://www.journals.elsevier.com/pattern-recognition/)
Our news correspondents report that additional information may be obtained by contacting J. Wang, Huazhong University of Science & Technology, Sch Automat, Wuhan 430074, Hubei, People’s Republic of China. Additional authors for this research include Z. Wang, C. Liang, C.X. Gao and N. Sang.
The direct object identifier (DOI) for that additional information is: https://doi.org/10.1016/j.patcog.2017.09.014. This DOI is a link to an online electronic document that is either free or for purchase, and can be your direct source for a journal article and its citation.
Our reports deliver fact-based news of research and discoveries from around the world. Copyright 2018, NewsRx LLC
CITATION: (2018-01-08), New Findings from Huazhong University of Science and Technology in Pattern Analysis Provides New Insights (Equidistance constrained metric learning for person re-identification), Journal of Robotics & Machine Learning, 297, ISSN: 1944-186X, BUTTER® ID: 014943701
From the newsletter Journal of Robotics & Machine Learning.
https://www.newsrx.com/Butter/#!Search:a=14943701
NewsRx® offers 195 weekly newsletters providing comprehensive information on all professional topics, ranging from health, pharma and life science to business, tech, energy, law, and finance. Our newsletters report only the most relevant and authoritative information from qualified sources.