Object detection techniques

overview and performance comparison

Research output: Contribution to conferencePaper

3 Downloads (Pure)

Abstract

Object detection algorithms are improving by the minute. There are many common libraries or application program interface (APIs) to use. The most two common techniques ones are Microsoft Azure Cloud object detection and Google Tensorflow object detection. The first is an online-network based API, while the second is an offline-machine based API. Both have their advantages and disadvantages. A direct comparison between the most common object detection methods help in finding the best solution for advance system integration. This paper will discuss both methods and compare them in terms of accuracy, complexity and practicality. It will show advantages and also limitations of each method, and possibilities for improvement.
Original languageEnglish
Number of pages4
Publication statusAccepted/In press - 4 Nov 2019
Event2019 IEEE International Symposium on Signal Processing and Information Technology - Ajman University Conference Center, Ajman, United Arab Emirates
Duration: 10 Dec 201912 Dec 2019
https://www.isspit.org/isspit/2019/

Conference

Conference2019 IEEE International Symposium on Signal Processing and Information Technology
Abbreviated titleISSPIT
CountryUnited Arab Emirates
CityAjman
Period10/12/1912/12/19
Internet address

Fingerprint

Application programs
Interfaces (computer)
Object detection

Keywords

  • object detection
  • Tensorflow
  • Azure Cloud

Cite this

Noman, M., Stankovic, V., & Tawfik, A. (Accepted/In press). Object detection techniques: overview and performance comparison. Paper presented at 2019 IEEE International Symposium on Signal Processing and Information Technology, Ajman, United Arab Emirates.
Noman, Mohammed ; Stankovic, Vladimir ; Tawfik, Ayman. / Object detection techniques : overview and performance comparison. Paper presented at 2019 IEEE International Symposium on Signal Processing and Information Technology, Ajman, United Arab Emirates.4 p.
@conference{5803c972c23343fd989658c4dd408aa0,
title = "Object detection techniques: overview and performance comparison",
abstract = "Object detection algorithms are improving by the minute. There are many common libraries or application program interface (APIs) to use. The most two common techniques ones are Microsoft Azure Cloud object detection and Google Tensorflow object detection. The first is an online-network based API, while the second is an offline-machine based API. Both have their advantages and disadvantages. A direct comparison between the most common object detection methods help in finding the best solution for advance system integration. This paper will discuss both methods and compare them in terms of accuracy, complexity and practicality. It will show advantages and also limitations of each method, and possibilities for improvement.",
keywords = "object detection, Tensorflow, Azure Cloud",
author = "Mohammed Noman and Vladimir Stankovic and Ayman Tawfik",
note = "{\circledC} 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.; 2019 IEEE International Symposium on Signal Processing and Information Technology, ISSPIT ; Conference date: 10-12-2019 Through 12-12-2019",
year = "2019",
month = "11",
day = "4",
language = "English",
url = "https://www.isspit.org/isspit/2019/",

}

Noman, M, Stankovic, V & Tawfik, A 2019, 'Object detection techniques: overview and performance comparison' Paper presented at 2019 IEEE International Symposium on Signal Processing and Information Technology, Ajman, United Arab Emirates, 10/12/19 - 12/12/19, .

Object detection techniques : overview and performance comparison. / Noman, Mohammed; Stankovic, Vladimir; Tawfik, Ayman.

2019. Paper presented at 2019 IEEE International Symposium on Signal Processing and Information Technology, Ajman, United Arab Emirates.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Object detection techniques

T2 - overview and performance comparison

AU - Noman, Mohammed

AU - Stankovic, Vladimir

AU - Tawfik, Ayman

N1 - © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

PY - 2019/11/4

Y1 - 2019/11/4

N2 - Object detection algorithms are improving by the minute. There are many common libraries or application program interface (APIs) to use. The most two common techniques ones are Microsoft Azure Cloud object detection and Google Tensorflow object detection. The first is an online-network based API, while the second is an offline-machine based API. Both have their advantages and disadvantages. A direct comparison between the most common object detection methods help in finding the best solution for advance system integration. This paper will discuss both methods and compare them in terms of accuracy, complexity and practicality. It will show advantages and also limitations of each method, and possibilities for improvement.

AB - Object detection algorithms are improving by the minute. There are many common libraries or application program interface (APIs) to use. The most two common techniques ones are Microsoft Azure Cloud object detection and Google Tensorflow object detection. The first is an online-network based API, while the second is an offline-machine based API. Both have their advantages and disadvantages. A direct comparison between the most common object detection methods help in finding the best solution for advance system integration. This paper will discuss both methods and compare them in terms of accuracy, complexity and practicality. It will show advantages and also limitations of each method, and possibilities for improvement.

KW - object detection

KW - Tensorflow

KW - Azure Cloud

UR - https://www.isspit.org/isspit/2019/

M3 - Paper

ER -

Noman M, Stankovic V, Tawfik A. Object detection techniques: overview and performance comparison. 2019. Paper presented at 2019 IEEE International Symposium on Signal Processing and Information Technology, Ajman, United Arab Emirates.