The main intent of enhancing the present system of object detection is to enhance its productivity and improve the detection accuracy. The method initializes a model in a way to store the background pixels and to compare each frame pixels with the same model background pixels. The intention is to separate the background pixels with the foreground moving pixels to improve the ability to detect the object in the foreground. An improved object detection algorithm based on “Gaussian mixture model” and “three-frame difference method”. This three-frame difference method uses a dynamic segmentation threshold and edge detection technology to solve the problem of illumination mutation and discontinuity of target edge.

Gaussian mixture model, illumination mutation, object detection, pixels, three-frame difference method, dynamic segmentation, edge detection technology

[1]
Chen, Liang-Bi & Su, Jian-Ping & Chen, Ming-Che & Chang, Wan-Jung
& Yang, Ching-Hsiang & Sie, Cheng-You, 
“An Implementation of an Intelligent Assistance System for Visually
Impaired/Blind People”, IEEE Access, 12-Apr-2019.

[2]
Mahajan J.R., C.S. Rawat, “Object Detection and Tracking using Cognitive
Approach”, International Journal of Scientific Research in Network Security and
Communication, ISSN: 2321-3256, Volume:5, Issue.3, pp.136-140,
Jun-217

[3] A.
N. Zereen and S. Corraya, "Detecting real time object along with the moving
direction for visually impaired people", International Conference on
Electrical, Computer & Telecommunication Engineering (ICECTE),  pp.1-4, Dec-2016.

[4] A.
Jinguji, Y. Sada and H. Nakahara, "Real-Time Multi-Pedestrian Detection in
Surveillance Camera using FPGA",   International Conference on Field
Programmable Logic and Applications (FPL), Barcelona, Spain, pp.424-425,
2019.

[5] I.
Akbar and A. F. Misman, "Research on Semantics Used in GPS Based Mobile
Phone Applications for Blind Pedestrian Navigation in an Outdoor
Environment",  International
Conference on Information and Communication Technology for the Muslim World
(ICT4M), pp. 196-2018.

[6] M.
Awad, J. E. Haddad, E. Khneisser, T. Mahmoud, E. Yaacoub and M. Malli,
"Intelligent eye: A mobile application for assisting blind people", IEEE
Middle East and North Africa Communications Conference (MENACOMM), pp.1-6,
2018.

[7] S.
Sharma, S. Jain and Khushboo,  and Kulyukin,
Vladimir & Nicholson, John & Ross, David & Marston, James &
Gaunet, Florence, “The Blind Leading the Blind: Toward Collaborative Online
Route Information Management by Individuals with Visual Impairments”, .
International conference on Social Information Processing, pp.54-59, March
26-28, 2008.

[9] Yu,
Tianming & Yang, Jianhua & Lu, Wei, “Combining Background Subtraction
and Convolutional Neural Network for Anomaly Detection in Pumping-Unit
Surveillance”.

[10]
Baygin, Mehmet & Karakose, Mehmet & Sarimaden, Alisan & Akin, Erhan,
“An Image Processing based Object    Counting
Approach for Machine Vision Application”, International Conference on Advances
and Innovations in Engineering (ICAIE),16-Feb-2018.

[11] S.
L. Joseph, X. Zhang, I. Dryanovski, J. Xiao, C. Yi and Y. Tian, "Semantic
Indoor Navigation with a Blind-User Oriented Augmented Reality", IEEE
International Conference on Systems, Man, and Cybernetics, Manchester,pp.3585-3591,
2013 .

[12] C.
K. Lakde and P. S. Prasad, "Navigation system for visually impaired
people", International Conference on Computation of Power, Energy,
Information and Communication (ICCPEIC), pp.0093-0098, 2015 .

[13] Md.T. . Akhtar, S.T. Razi, K.N. Jaman, A.
Azimusshan, Md.A. Sohel, “Fast and Real Life Object Detection System Using
Simple Webcam”, International Journal of Scientific Research in Computer
Sciences and Engineering, ISSN: 2320-7639, Volume:6, Issue.4, pp.18-23,
Aug-2018.