V. modeling oflocal binary pattern operator for texture

V.

CONCLUSION & FUTURE WORKMoving object detection is a basis for a number ofimportant applications such as real-time surveillance andvisual tracking. However, it is computationally expensive andresource hungry. Here, two cost-effective algorithmsbackground subtraction and sobel filtering are combined forreal-time moving object detection. The modified motionsegmentation technique considerably reduces the detectiondelay and memory usage, while effectively handling randomnoise. The algorithm do not rely on any special hardware. Sothe combined algorithm is more appropriate for embeddedsystems and portable devices. Also the work is extended formotorcycle recognition in traffic videos. Experimental resultsdemonstrate that the system was capable to identify multiplemotorbikes in normal urban and highway road conditions.

Best services for writing your paper according to Trustpilot

Premium Partner
From $18.00 per page
4,8 / 5
4,80
Writers Experience
4,80
Delivery
4,90
Support
4,70
Price
Recommended Service
From $13.90 per page
4,6 / 5
4,70
Writers Experience
4,70
Delivery
4,60
Support
4,60
Price
From $20.00 per page
4,5 / 5
4,80
Writers Experience
4,50
Delivery
4,40
Support
4,10
Price
* All Partners were chosen among 50+ writing services by our Customer Satisfaction Team

Ourfuture goal is to extend the project for helmet detection onmotorcyclists. We are also looking to build the hardwareprototype to test our software on real world scenarios anddifferent weather conditions instead of testing on pre-recordedvideos.REFERENCES1 O. Barnich and M.

Van Droogenbroeck, “Vibe: A universalbackground subtraction algorithm for video sequences,” IEEETransactions on Image processing, vol. 20, no. 6, pp. 1709–1724, 2011.2 D. Chinchkhede and N. Uke, “Image segmentation in videosequences using modified background subtraction”,International Journal of Computer Science & InformationTechnology, vol.

4, no. 1, 2012, p. 93.3 Piccardi and Massimo “Background subtraction techniques : areview ,” IEEE International Conference on Systems, man andcybernetics., vol. 4, pp. 3099–3104, 2004.4 M.

J. William, “Interactive segmentation with intelligentscissors,” Transactions on Graphical models and imageprocessing , vol. 60, no.

5, pp. 349–384, 1998.5 Saran and G. Sreelekha, “Traffic video surveillance: Vehicledetection and classification”, IEEE International Conferenceon Control Communication & Computing India (ICCC), 2015,pp. 516–521.6 W.

Yangui, Caixia et al., “Research of Vehicle VideoAnalysis System Based on SVM” in IEEE 8th InternationalConference on Information Technology in Medicine andEducation (ITME), 2016, pp. 678–689.7 D. Mohan, “Analysis of Road Traffic Fatality Data for Asia,”Journal of the Eastern Asia Society for TransportationStudies, vol.

9, 2011.8 D. M. W.

Powers, “Evaluation: From Precision, Recall and FFactorto ROC, Informedness, Markedness & Correlation,”School of Informatics and Engineering, Flinders University,Adelaide, Australia, Tech. Rep. SIE-07-001, 2007.9 Christopher D Brown and Herbert T Davis, “Receiveroperating characteristic curves and related decision measures:A tutorial”, Chemometrics and Intelligent LaboratorySystems, vol. 80, no. 1, pp. 24–38, 2006.10 Z.

Guo, Zhang, and L. Zhang, “A completed modeling oflocal binary pattern operator for texture classification,” IEEETrans. Image Processing, vol. 19, no. 6, pp.

1657–1663, 2010.