Person tracking algorithm based on convolutional neural network for indoor video surveillance

Abstract

In this paper, a person tracking algorithm for indoor video surveillance is presented. The algorithm contains the following steps: person detection, person features formation, features similarity calculation for the detected objects, postprocessing, person indexing, and person visibility determination in the current frame. Convolutional Neural Network (CNN) YOLO v3 is used for person detection. Person features are formed based on H channel in HSV color space histograms and a modified CNN ResNet. The proposed architecture includes 29 convolutional and one fully connected layer. As the output, it forms a 128-feature vector for every input image. CNN model was trained to perform feature extraction. Experiments were conducted using MOT methodology on stable camera videos in indoor environment. Main characteristics of the presented algorithm are calculated and discussed, confirming its effectiveness in comparison with the current approaches for person tracking in an indoor environment. Our algorithm performs real time processing for object detection and tracking using CUDA technology and a graphics card NVIDIA GTX 1060.

An algorithm for detecting events in video EEG monitoring data of patients with craniocerebral injuries

“…The results of the analysis showed the efficiency of the proposed algorithm for differentiating epileptic seizures from moving and chewing. Further research will be aimed at combining EEG channels and applying patient tracking techniques like [12] for improving the reliability of the proposed algorithm.…”

Detection of Appearance and Behavior Anomalies in Stationary Camera Videos Using Convolutional Neural Networks

“…To detect behavior anomalies, it is required to construct individual trajectories of each person in a frame. For this purpose, we propose an algorithm that uses tracking-by-detection as in [ 1 ] and, upon detecting a person, evaluates the corresponding features. At the first stage, the procedure of people detection in the current frame is carried out.…”

“…To track people and construct individual motion trajectories, we propose a composite descriptor that includes the geometric and CNN features of the entire image of a person and its top portion, which are obtained using the CNN architecture of 29 convolutional layers and one fully connected layer [ 1 ]. The composite descriptor also includes a person index, which remains constant in subsequent frames if tracking is carried out properly.…”

Algorithm Research of Neural Network for Feature Target Tracking

“…Currently widely used manual features such as HOG features, color features, etc. can only deal with some challenging scenarios [4]. In order to improve the adaptability of the algorithm in various scenarios, many algorithms fuse features.…”