Multi-Person Tracking and Crowd Behavior Detection via Particles Gradient Motion Descriptor and Improved Entropy Classifier

To prevent disasters and to control and supervise crowds, automated video surveillance has become indispensable. In today’s complex and crowded environments, manual surveillance and monitoring systems are inefficient, labor intensive, and unwieldy. Automated video surveillance systems offer promising solutions, but challenges remain. One of the major challenges is the extraction of true foregrounds of pixels representing humans only. Furthermore, to accurately understand and interpret crowd behavior, human crowd behavior (HCB) systems require robust feature extraction methods, along with powerful and reliable decision-making classifiers. In this paper, we describe our approach to these issues by presenting a novel Particles Force Model for multi-person tracking, a vigorous fusion of global and local descriptors, along with a robust improved entropy classifier for detecting and interpreting crowd behavior. In the proposed model, necessary preprocessing steps are followed by the application of a first distance algorithm for the removal of background clutter; true-foreground elements are then extracted via a Particles Force Model. The detected human forms are then counted by labeling and performing cluster estimation, using a K-nearest neighbors search algorithm. After that, the location of all the human silhouettes is fixed and, using the Jaccard similarity index and normalized cross-correlation as a cost function, multi-person tracking is performed. For HCB detection, we introduced human crowd contour extraction as a global feature and a particles gradient motion (PGD) descriptor, along with geometrical and speeded up robust features (SURF) for local features. After features were extracted, we applied bat optimization for optimal features, which also works as a pre-classifier. Finally, we introduced a robust improved entropy classifier for decision making and automated crowd behavior detection in smart surveillance systems. We evaluated the performance of our proposed system on a publicly available benchmark PETS2009 and UMN dataset. Experimental results show that our system performed better compared to existing well-known state-of-the-art methods by achieving higher accuracy rates. The proposed system can be deployed to great benefit in numerous public places, such as airports, shopping malls, city centers, and train stations to control, supervise, and protect crowds.

Mathematical model of an automated video surveillance system for performing special functions.

The mathematical model of the automated video surveillance system is offered. Mathematical models of separate units of the aircraft are considered: quadrocopter dynamics, RC transmitter, RC receiver, HD camera. It is shown that such mathematical models are the most effective for performing key tasks.

Damaged Number Plate Recognition

Around the world every vehicle are identified by its number plate. Number plate detection is one of the existing automated video surveillance systems that are used to detect the number plate. This system fails if the number plates are damaged, no proper illumination, blurry images. Thus here we will be able to recognizeze such damaged number plate. The technique involves four main stages viz. pre-processing, localization, recognition and segmentation. The entire process includes capturing the image, erasing the background details and removing the noise, cropping the number plate and then recognizing the characters followed by segmenting in order to recognize the plate. All this is done in Python because it had better results compared to MATLAB. When done in MATLAB, additional error and noise gets added to the input image and can causes inclusion of a new characters in the number plate and leads to misinterpretation of the number plate. About 100 images were gathered and 98 images of them were detected correctly. The efficiency in recognizing the damaged number plate using our system is about 98%.