Sorry, you need to enable JavaScript to visit this website.

facebooktwittermailshare

Fast Keypoint Detection in Video Sequences

Abstract: 

Several computer vision tasks exploit a succinct representation of the visual content in the form of sets of local features. Given an input image, feature extraction algorithms identify key-points and assign to each of them a descriptor, based on the characteristics of the surrounding visual content. Several tasks might require local features to be extracted from a video sequence, on a frame-by-frame basis. Although temporal downsampling has been proven to be an effective solution for mobile augmented reality and visual search, high temporal resolution is a key requirement for time-critical applications such as object tracking, event recognition, pedestrian detection, surveil- lance. In recent years, more and more computationally efficient visual feature detectors and descriptors have been proposed. Nonetheless, such approaches are tailored to still images. In this paper we propose a fast key-point detection algorithm for video sequences, that exploits the temporal coherence of the sequence of key-points. Ac- cording to the proposed method, each frame is preprocessed so as to identify the parts of the input frame for which key-point detection and description need to be performed. Our experiments show that it is possible to achieve a reduction in computational time of up to 40%, without significantly affecting the task accuracy.

up
0 users have voted:

Paper Details

Authors:
Luca Baroffio, Matteo Cesana, Alessandro Redondi, Marco Tagliasacchi, Stefano Tubaro
Submitted On:
24 March 2016 - 5:04am
Short Link:
Type:
Presentation Slides
Event:
Presenter's Name:
Stefano Tubaro
Paper Code:
IVMSP-L10.3
Document Year:
2016
Cite

Document Files

ICASSP2016_Baroffio.pdf

(372)

Subscribe

[1] Luca Baroffio, Matteo Cesana, Alessandro Redondi, Marco Tagliasacchi, Stefano Tubaro, "Fast Keypoint Detection in Video Sequences", IEEE SigPort, 2016. [Online]. Available: http://sigport.org/1021. Accessed: Aug. 10, 2020.
@article{1021-16,
url = {http://sigport.org/1021},
author = {Luca Baroffio; Matteo Cesana; Alessandro Redondi; Marco Tagliasacchi; Stefano Tubaro },
publisher = {IEEE SigPort},
title = {Fast Keypoint Detection in Video Sequences},
year = {2016} }
TY - EJOUR
T1 - Fast Keypoint Detection in Video Sequences
AU - Luca Baroffio; Matteo Cesana; Alessandro Redondi; Marco Tagliasacchi; Stefano Tubaro
PY - 2016
PB - IEEE SigPort
UR - http://sigport.org/1021
ER -
Luca Baroffio, Matteo Cesana, Alessandro Redondi, Marco Tagliasacchi, Stefano Tubaro. (2016). Fast Keypoint Detection in Video Sequences. IEEE SigPort. http://sigport.org/1021
Luca Baroffio, Matteo Cesana, Alessandro Redondi, Marco Tagliasacchi, Stefano Tubaro, 2016. Fast Keypoint Detection in Video Sequences. Available at: http://sigport.org/1021.
Luca Baroffio, Matteo Cesana, Alessandro Redondi, Marco Tagliasacchi, Stefano Tubaro. (2016). "Fast Keypoint Detection in Video Sequences." Web.
1. Luca Baroffio, Matteo Cesana, Alessandro Redondi, Marco Tagliasacchi, Stefano Tubaro. Fast Keypoint Detection in Video Sequences [Internet]. IEEE SigPort; 2016. Available from : http://sigport.org/1021