Optical flow research has made significant progress in recent years and it can now be
computed efficiently and accurately for many images. However, complex motions, large …

Independent evaluation of the performance of feature descriptors is an important part of the
process of develo** better computer vision systems. In this paper, we compare the …

We propose modifications to scale-space feature extraction techniques scale-invariant
feature transform (SIFT) and speeded up robust features (SURFs) that make the feature …

This paper presents an automated robotic system for generating semantic maps of inventory
in retail environments. In retail settings, semantic maps are labeled maps of stores where …

In this paper, we present a novel image mosaicking method that is based on Speeded-Up
Robust Features (SURF) of line segments, aiming to achieve robustness to incident scaling …

Visual features constitute compact yet effective representations of visual content, and are
being exploited in a large number of heterogeneous applications, including augmented …

A nested motion descriptor is a spatiotemporal representation of motion that is invariant to
global camera translation, without requiring an explicit estimate of optical flow or camera …

In recent years, local image descriptors based on histograms of oriented gradients (eg, SIFT,
DAISY) and intensity orders (eg, LBP, LIOP) have been popular for the keypoint matching …

Abstract Traditional Feature Detectors and Trackers use information aggregation in 2D
patches to detect and match discriminative patches. However, this information does not …

Binary descriptors have won their place as efficient and effective visual descriptors in
several vision tasks. In this context, one of the most widely used binary descriptors to date is …