Proceedings of the 3rd IEEE/ACM International Conference on Big Data Computing, Applications and Technologies 2016
DOI: 10.1145/3006299.3006322
|View full text |Cite
|
Sign up to set email alerts
|

Spatial frequency based video stream analysis for object classification and recognition in clouds

Abstract: The recent rise in multimedia technology has made it easier to perform a number of tasks. One of these tasks is monitoring where cheap cameras are producing large amount of video data. This video data is then processed for object classification to extract useful information. However, the video data obtained by these cheap cameras is often of low quality and results in blur video content. Moreover, various illumination effects caused by lightning conditions also degrade the video quality. These effects present … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
6
0

Year Published

2017
2017
2024
2024

Publication Types

Select...
3
2
1

Relationship

4
2

Authors

Journals

citations
Cited by 7 publications
(6 citation statements)
references
References 21 publications
0
6
0
Order By: Relevance
“…Recent video analytics systems often use shallow networks and hand crafted features to perform object classification [30] [31]. These hand crafted features are combined to generate larger features.…”
Section: Related Workmentioning
confidence: 99%
“…Recent video analytics systems often use shallow networks and hand crafted features to perform object classification [30] [31]. These hand crafted features are combined to generate larger features.…”
Section: Related Workmentioning
confidence: 99%
“…Recently intelligent video analytics systems (IVS) with the aim to analyze video streams without human intervention have emerged which provide constant analysis of a scene [10]. Most of the existing work on intelligent video analysis is based on centralized architecture using a storage-analyze cloud model such as [11] where the data is first transported and stored in the cloud. The analytics is then performed on the stored data using job scheduling [12].…”
Section: Related Workmentioning
confidence: 99%
“…where A t is the algorithm time to process the job and T t is the network time to transfer the record from source to destination. Total cost to process all the jobs with algorithm A will be C T ja = J T jps * C ja (11) where J T jps is the total number of jobs and C ja is the cost time for each job. We also define a percentage gain to show the efficiency of a setup S in terms of time and cost of a reference cloud setup.…”
Section: A Data Pipeline Modelmentioning
confidence: 99%
“…A number of studies worked on multimodal features. They used hidden Markov models, Guassian density functions, and local pattern features in their system.…”
Section: Related Workmentioning
confidence: 99%