Fast Integral Image Estimation at 1

01/27/2016
by   Kuldeep Kulkarni, et al.
0

We propose a framework called ReFInE to directly obtain integral image estimates from a very small number of spatially multiplexed measurements of the scene without iterative reconstruction of any auxiliary image, and demonstrate their practical utility in visual object tracking. Specifically, we design measurement matrices which are tailored to facilitate extremely fast estimation of the integral image, by using a single-shot linear operation on the measured vector. Leveraging a prior model for the images, we formulate a nuclear norm minimization problem with second order conic constraints to jointly obtain the measurement matrix and the linear operator. Through qualitative and quantitative experiments, we show that high quality integral image estimates can be obtained using our framework at very low measurement rates. Further, on a standard dataset of 50 videos, we present object tracking results which are comparable to the state-of-the-art methods, even at an extremely low measurement rate of 1

READ FULL TEXT

page 7

page 8

research
01/26/2016

ReconNet: Non-Iterative Reconstruction of Images from Compressively Sensed Random Measurements

The goal of this paper is to present a non-iterative and more importantl...
research
09/08/2018

Rate-Adaptive Neural Networks for Spatial Multiplexers

In resource-constrained environments, one can employ spatial multiplexin...
research
05/21/2018

Measurement-wise Occlusion in Multi-object Tracking

Handling object interaction is a fundamental challenge in practical mult...
research
09/22/2021

Incorporating Data Uncertainty in Object Tracking Algorithms

Methodologies for incorporating the uncertainties characteristic of data...
research
09/19/2022

HVC-Net: Unifying Homography, Visibility, and Confidence Learning for Planar Object Tracking

Robust and accurate planar tracking over a whole video sequence is vital...
research
02/19/2016

Depth-Based Object Tracking Using a Robust Gaussian Filter

We consider the problem of model-based 3D-tracking of objects given dens...
research
09/16/2019

Inference for multiple object tracking: A Bayesian nonparametric approach

In recent years, multi object tracking (MOT) problem has drawn attention...

Please sign up or login with your details

Forgot password? Click here to reset