Mathematical Models Using Artificial Intelligence for Surveillance Systems

2Machine Learning and Artificial Intelligence in the Detection of Moving Objects Using Image Processing

K. Janagi¹*, Devarajan Balaji², P. Renuka¹ and S. Bhuvaneswari³

¹Department of Mathematics, KPR Institute of Engineering and Technology, Coimbatore, Tamil Nadu, India

²Department of Mechanical Engineering, KPR Institute of Engineering and Technology, Coimbatore, Tamil Nadu, India

³Department of Physics, KPR Institute of Engineering and Technology, Coimbatore, Tamil Nadu, India

Abstract

Digital technology plays a major role in various fields like real life, science and engineering. This chapter deals with the uses of digital technology in detecting and tracking of objects. In particular, it applies LBF algorithm, background subtraction algorithm, GMM model (Gaussian Mixture Model), GANN (Generative adversarial neural networks), Kalman filter, Fuzzy c-mean, End-of-Queue (EOQ), Delaunay triangulation, robust approaches, RPCA (Robust Principal Component Analysis), Semi-Automatic Vehicle Detection System (SAVDS), and 3D LiDAR (Light Detection and Ranging). Based on the above-mentioned algorithms one can easily detect the moving object or track the object (in most of the cases a human being) more accurately. Generally, all the algorithms including RPCA, NLTFN (Non-Convex Logarithm Fraction Norms), RNLTFN (Robust Non-Convex Logarithm Fraction Norms) are mostly used to segregate the human images from other images, detection of images in poor weather conditions, monitoring the traffic ...