International Journal of Multimedia and Ubiquitous Engineering Vol. 11, No. 4, (2016) 1 Moving Object Detection and Classification Using Neuro-Fuzzy Approach M. A. Rashidan 1* , Y. M. Mustafah 1 , A. A. Shafie 1 , N. A. Zainuddin 1 , N. N. A. Aziz 1 , and A. W. Azman 2 1 Department of Mechatronics 2 Department of Electrical and Computer Engineering Faculty of Engineering, International Islamic University Malaysia (IIUM) Jalan Gombak, 53100 Kuala Lumpur, Malaysia. ariffrashidan@gmail.com, yasir@iium.edu.my, aashafie@iium.edu.my, fiqahzainuddin@gmail.com, nornadirahaziz89@gmail.com, amy@iium.edu.my Abstract Public surveillance monitoring is rapidly finding its way into Intelligent Surveillance System. Street crime is increasing in recent years, which has demanded more reliable and intelligent public surveillance system. In this paper, the ability and the accuracy of an Adaptive Neuro-Fuzzy Inference System (ANFIS) was investigated for the classification of moving objects for street scene applications. The goal of this paper is to classify the moving objects prior to its communal attributes that emphasize on three major processes which are object detection, discriminative feature extraction, and classification of the target. The intended surveillance application would focus on street scene, therefore the target classes of interest are pedestrian, motorcyclist, and car. The adaptive network based on Neuro-fuzzy was independently developed for three output parameters, each of which constitute of three inputs and 27 Sugeno-rules. Extensive experimentation on significant features has been performed and the evaluation performance analysis has been quantitatively conducted on three street scene dataset, which differ in terms of background complexity. Experimental results over a public dataset and our own dataset demonstrate that the proposed technique achieves the performance of 93.1% correct classification for street scene with moving objects, with compared to the solely approaches of neural network or fuzzy. Keywords: Moving object detection, neural fuzzy systems, object classification, street crime, visual surveillance 1. Introduction Closed-circuit television (CCTV) is popular among law-abiding citizens who perceive it as a preventive measure to feel much safer through public surveillance. Thus, it will be more reliable if it can fit the purpose to prevent, rather than only can detect crime, and as such implementation it would be very useful. At present, it has been served as resourceful assistance in crime investigation; however CCTV is used mostly as post investigation tool, rather than real-time preventive measures tool. Thus, the acquisition visual sensor such CCTV should be truly intelligent and able to capture scenes at where it is installed, as this could facilitate the process of decision making. Inspired by this idea, the development of research in manipulating CCTV data into an automatic decision making system has received much attention in the past decade. One of important measures in developing such system is recognition of moving objects. Among many approaches, Neuro-fuzzy modeling is one of the most recent techniques that able to achieve high accuracy in moving object classification and recognition. The Neuro-fuzzy modeling