Latent Constrained Correlation Filters for Object Localization

06/07/2016
by   Shangzhen Luan, et al.
0

There is a neglected fact in the traditional machine learning methods that the data sampling can actually lead to the solution sampling. We consider this observation to be important because having the solution sampling available makes the variable distribution estimation, which is a problem in many learning-related applications, more tractable. In this paper, we implement this idea on correlation filter, which has attracted much attention in the past few years due to its high performance with a low computational cost. More specifically, we propose a new method, named latent constrained correlation filters (LCCF) by mapping the correlation filters to a given latent subspace, in which we establish a new learning framework that embeds distribution-related constraints into the original problem. We further introduce a subspace based alternating direction method of multipliers (SADMM) to efficiently solve the optimization problem, which is proved to converge at the saddle point. Our approach is successfully applied to two different tasks inclduing eye localization and car detection. Extensive experiments demonstrate that LCCF outperforms the state-of-the-art methods when samples are suffered from noise and occlusion.

READ FULL TEXT
research
11/11/2017

Latent Constrained Correlation Filter

Correlation filters are special classifiers designed for shift-invariant...
research
06/11/2018

Object detection and tracking benchmark in industry based on improved correlation filter

Real-time object detection and tracking have shown to be the basis of in...
research
12/16/2016

Output Constraint Transfer for Kernelized Correlation Filter in Tracking

Kernelized Correlation Filter (KCF) is one of the state-of-the-art objec...
research
11/10/2014

Zero-Aliasing Correlation Filters for Object Recognition

Correlation filters (CFs) are a class of classifiers that are attractive...
research
08/15/2018

Joint & Progressive Learning from High-Dimensional Data for Multi-Label Classification

Despite the fact that nonlinear subspace learning techniques (e.g. manif...
research
07/24/2017

Extremely Low Bit Neural Network: Squeeze the Last Bit Out with ADMM

Although deep learning models are highly effective for various learning ...
research
08/04/2022

A Sequential MUSIC algorithm for Scatterers Detection 2 in SAR Tomography Enhanced by a Robust Covariance 3 Estimator

Synthetic aperture radar (SAR) tomography (TomoSAR) is an appealing tool...

Please sign up or login with your details

Forgot password? Click here to reset