Visible to the public Research on Neural Networks Integration for Object Classification in Video Analysis Systems

TitleResearch on Neural Networks Integration for Object Classification in Video Analysis Systems
Publication TypeConference Paper
Year of Publication2020
AuthorsFomin, I., Burin, V., Bakhshiev, A.
Conference Name2020 International Conference on Industrial Engineering, Applications and Manufacturing (ICIEAM)
Date PublishedMay 2020
PublisherIEEE
ISBN Number978-1-7281-4590-7
Keywordsconvolutional neural networks, Deep Neural Network, deep video, direct Python script execution techniques, false detections, image classification, image motion analysis, image sequence, image sequences, Keras, Keras developer-friendly environment, Keras integration, Metrics, moving objects detection, network architectures, network training, neural nets, neural networks integration, object classification, object detection, Object recognition, outdoor video surveillance cameras, pubcrawl, resilience, Resiliency, Scalability, TensorFlow, video analysis, video analysis system, video cameras, video signal processing, video surveillance, video surveillance system
Abstract

Object recognition with the help of outdoor video surveillance cameras is an important task in the context of ensuring the security at enterprises, public places and even private premises. There have long existed systems that allow detecting moving objects in the image sequence from a video surveillance system. Such a system is partially considered in this research. It detects moving objects using a background model, which has certain problems. Due to this some objects are missed or detected falsely. We propose to combine the moving objects detection results with the classification, using a deep neural network. This will allow determining whether a detected object belongs to a certain class, sorting out false detections, discarding the unnecessary ones (sometimes individual classes are unwanted), to divide detected people into the employees in the uniform and all others, etc. The authors perform a network training in the Keras developer-friendly environment that provides for quick building, changing and training of network architectures. The performance of the Keras integration into a video analysis system, using direct Python script execution techniques, is between 6 and 52 ms, while the precision is between 59.1% and 97.2% for different architectures. The integration, made by freezing a selected network architecture with weights, is selected after testing. After that, frozen architecture can be imported into video analysis using the TensorFlow interface for C++. The performance of such type of integration is between 3 and 49 ms. The precision is between 63.4% and 97.8% for different architectures.

URLhttps://ieeexplore.ieee.org/document/9112011
DOI10.1109/ICIEAM48468.2020.9112011
Citation Keyfomin_research_2020