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

Abstract

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.

Intelligent Deep Learning Enabled Crowd Detection and Classification Model in Real Time Surveillance Videos

“…Moving object extraction and Human recognition are the two major parts of human detection method. Human recognition detects an object as human or nonhuman, and object is extracted from the background through moving object extraction that defines the relevant position and size of the objects in an image [2]. The tracking method is capable of predicting the position after and during occlusion since the tracked human or object is occluded probably by other objects while tracked.…”

Recognition of crowd abnormal activities using fusion of handcrafted and deep features

“…In most of the traditional methods [5]- [16], event recognition is performed by analyzing crowd motion. These methods have used different handcrafted features such as motion magnitude and direction [5], [8], [10], [14], [15], and [16], motion vector instersections [6], optical flow manifolds [9], dynamic textures [11] for characterizing the crowd behavior. Classification of events is carried out either in supervised way [5], [8], [14], [15] or unsupervised way [7], [9]- [13].…”

Adaptive Tracking Algorithm for Multiperson Motion Targets Based on Local Feature Similarity

“…The Siam R-CNN algorithm presents a new method of mining instances. The C-COT algorithm is an improvement on deep learning and correlation filtering algorithms that addresses the problem of algorithm training in the continuous space domain by using cubic interpolation and a Hessian matrix to handle the problem of algorithm training in the continuous space domain [28].…”