Cloud adaboost feedback training machine for outside available parking spaces query service

Jie Qi Huang, Ming-Shi Wang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

A cloud based outside available parking spaces query service system is proposed. The concept of user pay the fee is considered to create the service system. The data available on the system database are collected from both of the active and passive ways. For the active way, detectors installed on a periodically routing vehicle will provide the data. For the passive way, the data is from the feedback of the system users. To increase to recognition rate, a detection method called bi-block size double hits method (BBDH) is proposed to get the rid of the mistaken target area of detection. The system classifier is composed of two strong classifiers based on Adaboost algorithm, each with different detection block sizes. The classifier will be retrained based on the more positive samples to improve the recognition rate of the whole system. The late version of the retrained classifier also used to update the old one on the detector of the routing vehicle. It is shown that the proposed method can improve the detection rate from 73% to 82% and the processing rate up to 20 fps. The entire system has the ability of learning and finally provides the public real-time parking location queries service, could be an effective location based service(LBS) solution to the problem for finding parking spaces of crowded urban areas in city.

Original languageEnglish
Title of host publicationProceeding - COMNETSAT 2012
Subtitle of host publication2012 IEEE International Conference on Communication, Networks and Satellite
Pages177-181
Number of pages5
DOIs
Publication statusPublished - 2012 Dec 1
Event2012 IEEE International Conference on Communication, Networks and Satellite, COMNETSAT 2012 - Bali, Indonesia
Duration: 2012 Jul 122012 Jul 14

Publication series

NameProceeding - COMNETSAT 2012: 2012 IEEE International Conference on Communication, Networks and Satellite

Other

Other2012 IEEE International Conference on Communication, Networks and Satellite, COMNETSAT 2012
CountryIndonesia
CityBali
Period12-07-1212-07-14

Fingerprint

Adaptive boosting
Parking
Classifiers
Feedback
Vehicle routing
Detectors
Location based services
Processing

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Signal Processing

Cite this

Huang, J. Q., & Wang, M-S. (2012). Cloud adaboost feedback training machine for outside available parking spaces query service. In Proceeding - COMNETSAT 2012: 2012 IEEE International Conference on Communication, Networks and Satellite (pp. 177-181). [6380801] (Proceeding - COMNETSAT 2012: 2012 IEEE International Conference on Communication, Networks and Satellite). https://doi.org/10.1109/ComNetSat.2012.6380801
Huang, Jie Qi ; Wang, Ming-Shi. / Cloud adaboost feedback training machine for outside available parking spaces query service. Proceeding - COMNETSAT 2012: 2012 IEEE International Conference on Communication, Networks and Satellite. 2012. pp. 177-181 (Proceeding - COMNETSAT 2012: 2012 IEEE International Conference on Communication, Networks and Satellite).
@inproceedings{65cda4a6c48848caa7ccaa4af0722c48,
title = "Cloud adaboost feedback training machine for outside available parking spaces query service",
abstract = "A cloud based outside available parking spaces query service system is proposed. The concept of user pay the fee is considered to create the service system. The data available on the system database are collected from both of the active and passive ways. For the active way, detectors installed on a periodically routing vehicle will provide the data. For the passive way, the data is from the feedback of the system users. To increase to recognition rate, a detection method called bi-block size double hits method (BBDH) is proposed to get the rid of the mistaken target area of detection. The system classifier is composed of two strong classifiers based on Adaboost algorithm, each with different detection block sizes. The classifier will be retrained based on the more positive samples to improve the recognition rate of the whole system. The late version of the retrained classifier also used to update the old one on the detector of the routing vehicle. It is shown that the proposed method can improve the detection rate from 73{\%} to 82{\%} and the processing rate up to 20 fps. The entire system has the ability of learning and finally provides the public real-time parking location queries service, could be an effective location based service(LBS) solution to the problem for finding parking spaces of crowded urban areas in city.",
author = "Huang, {Jie Qi} and Ming-Shi Wang",
year = "2012",
month = "12",
day = "1",
doi = "10.1109/ComNetSat.2012.6380801",
language = "English",
isbn = "9781467308892",
series = "Proceeding - COMNETSAT 2012: 2012 IEEE International Conference on Communication, Networks and Satellite",
pages = "177--181",
booktitle = "Proceeding - COMNETSAT 2012",

}

Huang, JQ & Wang, M-S 2012, Cloud adaboost feedback training machine for outside available parking spaces query service. in Proceeding - COMNETSAT 2012: 2012 IEEE International Conference on Communication, Networks and Satellite., 6380801, Proceeding - COMNETSAT 2012: 2012 IEEE International Conference on Communication, Networks and Satellite, pp. 177-181, 2012 IEEE International Conference on Communication, Networks and Satellite, COMNETSAT 2012, Bali, Indonesia, 12-07-12. https://doi.org/10.1109/ComNetSat.2012.6380801

Cloud adaboost feedback training machine for outside available parking spaces query service. / Huang, Jie Qi; Wang, Ming-Shi.

Proceeding - COMNETSAT 2012: 2012 IEEE International Conference on Communication, Networks and Satellite. 2012. p. 177-181 6380801 (Proceeding - COMNETSAT 2012: 2012 IEEE International Conference on Communication, Networks and Satellite).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Cloud adaboost feedback training machine for outside available parking spaces query service

AU - Huang, Jie Qi

AU - Wang, Ming-Shi

PY - 2012/12/1

Y1 - 2012/12/1

N2 - A cloud based outside available parking spaces query service system is proposed. The concept of user pay the fee is considered to create the service system. The data available on the system database are collected from both of the active and passive ways. For the active way, detectors installed on a periodically routing vehicle will provide the data. For the passive way, the data is from the feedback of the system users. To increase to recognition rate, a detection method called bi-block size double hits method (BBDH) is proposed to get the rid of the mistaken target area of detection. The system classifier is composed of two strong classifiers based on Adaboost algorithm, each with different detection block sizes. The classifier will be retrained based on the more positive samples to improve the recognition rate of the whole system. The late version of the retrained classifier also used to update the old one on the detector of the routing vehicle. It is shown that the proposed method can improve the detection rate from 73% to 82% and the processing rate up to 20 fps. The entire system has the ability of learning and finally provides the public real-time parking location queries service, could be an effective location based service(LBS) solution to the problem for finding parking spaces of crowded urban areas in city.

AB - A cloud based outside available parking spaces query service system is proposed. The concept of user pay the fee is considered to create the service system. The data available on the system database are collected from both of the active and passive ways. For the active way, detectors installed on a periodically routing vehicle will provide the data. For the passive way, the data is from the feedback of the system users. To increase to recognition rate, a detection method called bi-block size double hits method (BBDH) is proposed to get the rid of the mistaken target area of detection. The system classifier is composed of two strong classifiers based on Adaboost algorithm, each with different detection block sizes. The classifier will be retrained based on the more positive samples to improve the recognition rate of the whole system. The late version of the retrained classifier also used to update the old one on the detector of the routing vehicle. It is shown that the proposed method can improve the detection rate from 73% to 82% and the processing rate up to 20 fps. The entire system has the ability of learning and finally provides the public real-time parking location queries service, could be an effective location based service(LBS) solution to the problem for finding parking spaces of crowded urban areas in city.

UR - http://www.scopus.com/inward/record.url?scp=84872184934&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84872184934&partnerID=8YFLogxK

U2 - 10.1109/ComNetSat.2012.6380801

DO - 10.1109/ComNetSat.2012.6380801

M3 - Conference contribution

SN - 9781467308892

T3 - Proceeding - COMNETSAT 2012: 2012 IEEE International Conference on Communication, Networks and Satellite

SP - 177

EP - 181

BT - Proceeding - COMNETSAT 2012

ER -

Huang JQ, Wang M-S. Cloud adaboost feedback training machine for outside available parking spaces query service. In Proceeding - COMNETSAT 2012: 2012 IEEE International Conference on Communication, Networks and Satellite. 2012. p. 177-181. 6380801. (Proceeding - COMNETSAT 2012: 2012 IEEE International Conference on Communication, Networks and Satellite). https://doi.org/10.1109/ComNetSat.2012.6380801