A Multi-attribute based methodology for vehicle detection & identification

Vinayak Elangovan, Bashir Alsaidi, Amir Shirkhodaie

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

6 Citations (Scopus)

Abstract

Robust vehicle detection and identification is required for the intelligent persistent surveillance systems. In this paper, we present a Multi-attribute Vehicle Detection and Identification technique (MVDI) for detection and classification of stationary vehicles. The proposed model uses a supervised Hamming Neural Network (HNN) for taxonomy of shape of the vehicle. Vehicles silhouette features are employed for the training of the HNN from a large array of training vehicle samples in different type, scale, and color variation. Invariant vehicle silhouette attributes are used as features for training of the HNN which is based on an internal Hamming Distance and shape features to determine degree of similarity of a test vehicle against those it's selectively trained with. Upon detection of class of the vehicle, the other vehicle attributes such as: color and orientation are determined. For vehicle color detection, provincial regions of the vehicle body are used for matching color of the vehicle. For the vehicle orientation detection, the key structural features of the vehicle are extracted and subjected to classification based on color tune, geometrical shape, and tire region detection. The experimental results show the technique is promising and has robustness for detection and identification of vehicle based on their multi-attribute features. Furthermore this paper demonstrates the importance of the vehicle attributes detection towards the identification of Human-Vehicle Interaction events.

Original languageEnglish (US)
Title of host publicationSignal Processing, Sensor Fusion, and Target Recognition XXII
DOIs
StatePublished - Aug 12 2013
EventSignal Processing, Sensor Fusion, and Target Recognition XXII - Baltimore, MD, United States
Duration: Apr 29 2013May 2 2013

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume8745
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Other

OtherSignal Processing, Sensor Fusion, and Target Recognition XXII
CountryUnited States
CityBaltimore, MD
Period4/29/135/2/13

Fingerprint

Vehicle Detection
vehicles
Attribute
methodology
Methodology
Silhouette
Neural Networks
color
Shape Feature
Tire
Hamming Distance
Color
Taxonomy
education
Surveillance
Neural networks
Robustness
Internal
Invariant
taxonomy

All Science Journal Classification (ASJC) codes

  • Electronic, Optical and Magnetic Materials
  • Condensed Matter Physics
  • Computer Science Applications
  • Applied Mathematics
  • Electrical and Electronic Engineering

Cite this

Elangovan, V., Alsaidi, B., & Shirkhodaie, A. (2013). A Multi-attribute based methodology for vehicle detection & identification. In Signal Processing, Sensor Fusion, and Target Recognition XXII [87451E] (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 8745). https://doi.org/10.1117/12.2018091
Elangovan, Vinayak ; Alsaidi, Bashir ; Shirkhodaie, Amir. / A Multi-attribute based methodology for vehicle detection & identification. Signal Processing, Sensor Fusion, and Target Recognition XXII. 2013. (Proceedings of SPIE - The International Society for Optical Engineering).
@inproceedings{4d3491ad2e604cf99037e4ddfd4f26e2,
title = "A Multi-attribute based methodology for vehicle detection & identification",
abstract = "Robust vehicle detection and identification is required for the intelligent persistent surveillance systems. In this paper, we present a Multi-attribute Vehicle Detection and Identification technique (MVDI) for detection and classification of stationary vehicles. The proposed model uses a supervised Hamming Neural Network (HNN) for taxonomy of shape of the vehicle. Vehicles silhouette features are employed for the training of the HNN from a large array of training vehicle samples in different type, scale, and color variation. Invariant vehicle silhouette attributes are used as features for training of the HNN which is based on an internal Hamming Distance and shape features to determine degree of similarity of a test vehicle against those it's selectively trained with. Upon detection of class of the vehicle, the other vehicle attributes such as: color and orientation are determined. For vehicle color detection, provincial regions of the vehicle body are used for matching color of the vehicle. For the vehicle orientation detection, the key structural features of the vehicle are extracted and subjected to classification based on color tune, geometrical shape, and tire region detection. The experimental results show the technique is promising and has robustness for detection and identification of vehicle based on their multi-attribute features. Furthermore this paper demonstrates the importance of the vehicle attributes detection towards the identification of Human-Vehicle Interaction events.",
author = "Vinayak Elangovan and Bashir Alsaidi and Amir Shirkhodaie",
year = "2013",
month = "8",
day = "12",
doi = "10.1117/12.2018091",
language = "English (US)",
isbn = "9780819495365",
series = "Proceedings of SPIE - The International Society for Optical Engineering",
booktitle = "Signal Processing, Sensor Fusion, and Target Recognition XXII",

}

Elangovan, V, Alsaidi, B & Shirkhodaie, A 2013, A Multi-attribute based methodology for vehicle detection & identification. in Signal Processing, Sensor Fusion, and Target Recognition XXII., 87451E, Proceedings of SPIE - The International Society for Optical Engineering, vol. 8745, Signal Processing, Sensor Fusion, and Target Recognition XXII, Baltimore, MD, United States, 4/29/13. https://doi.org/10.1117/12.2018091

A Multi-attribute based methodology for vehicle detection & identification. / Elangovan, Vinayak; Alsaidi, Bashir; Shirkhodaie, Amir.

Signal Processing, Sensor Fusion, and Target Recognition XXII. 2013. 87451E (Proceedings of SPIE - The International Society for Optical Engineering; Vol. 8745).

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

TY - GEN

T1 - A Multi-attribute based methodology for vehicle detection & identification

AU - Elangovan, Vinayak

AU - Alsaidi, Bashir

AU - Shirkhodaie, Amir

PY - 2013/8/12

Y1 - 2013/8/12

N2 - Robust vehicle detection and identification is required for the intelligent persistent surveillance systems. In this paper, we present a Multi-attribute Vehicle Detection and Identification technique (MVDI) for detection and classification of stationary vehicles. The proposed model uses a supervised Hamming Neural Network (HNN) for taxonomy of shape of the vehicle. Vehicles silhouette features are employed for the training of the HNN from a large array of training vehicle samples in different type, scale, and color variation. Invariant vehicle silhouette attributes are used as features for training of the HNN which is based on an internal Hamming Distance and shape features to determine degree of similarity of a test vehicle against those it's selectively trained with. Upon detection of class of the vehicle, the other vehicle attributes such as: color and orientation are determined. For vehicle color detection, provincial regions of the vehicle body are used for matching color of the vehicle. For the vehicle orientation detection, the key structural features of the vehicle are extracted and subjected to classification based on color tune, geometrical shape, and tire region detection. The experimental results show the technique is promising and has robustness for detection and identification of vehicle based on their multi-attribute features. Furthermore this paper demonstrates the importance of the vehicle attributes detection towards the identification of Human-Vehicle Interaction events.

AB - Robust vehicle detection and identification is required for the intelligent persistent surveillance systems. In this paper, we present a Multi-attribute Vehicle Detection and Identification technique (MVDI) for detection and classification of stationary vehicles. The proposed model uses a supervised Hamming Neural Network (HNN) for taxonomy of shape of the vehicle. Vehicles silhouette features are employed for the training of the HNN from a large array of training vehicle samples in different type, scale, and color variation. Invariant vehicle silhouette attributes are used as features for training of the HNN which is based on an internal Hamming Distance and shape features to determine degree of similarity of a test vehicle against those it's selectively trained with. Upon detection of class of the vehicle, the other vehicle attributes such as: color and orientation are determined. For vehicle color detection, provincial regions of the vehicle body are used for matching color of the vehicle. For the vehicle orientation detection, the key structural features of the vehicle are extracted and subjected to classification based on color tune, geometrical shape, and tire region detection. The experimental results show the technique is promising and has robustness for detection and identification of vehicle based on their multi-attribute features. Furthermore this paper demonstrates the importance of the vehicle attributes detection towards the identification of Human-Vehicle Interaction events.

UR - http://www.scopus.com/inward/record.url?scp=84881171570&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84881171570&partnerID=8YFLogxK

U2 - 10.1117/12.2018091

DO - 10.1117/12.2018091

M3 - Conference contribution

AN - SCOPUS:84881171570

SN - 9780819495365

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - Signal Processing, Sensor Fusion, and Target Recognition XXII

ER -

Elangovan V, Alsaidi B, Shirkhodaie A. A Multi-attribute based methodology for vehicle detection & identification. In Signal Processing, Sensor Fusion, and Target Recognition XXII. 2013. 87451E. (Proceedings of SPIE - The International Society for Optical Engineering). https://doi.org/10.1117/12.2018091