Design and Proposal of a Database for Firearms Detection

Advances in Intelligent Systems and Computing（2019）

Speech Technology Group

Cited 4|Views10

Abstract

Closed circuit television (CCTV) surveillance systems that implement monitoring operators have multiple human limitations, these systems usually don’t provide an immediate response in different situations of danger like an armed robbery. To address this security gap, a firearms detection system has been developed through convolutional neural networks (CNNs). For its development a large database of images is necessary. This article presents the creation and characteristics of this database, which is made up of 247,576 images obtained from the web. This article addresses the application of different techniques for the creation of new images from the initial ones to increase the database, obtaining up to 22.7% relative improvement in the accuracy of the network after increasing the database. The database is structured into two classes. The first class is made up of people that have a gun and the second class of people not carrying a gun. The use of this database in the development of the detection system obtained up to 90% in “Precision” and “Recall” metrics in a convolutional neural network configuration based on “VGG net”, through the use of grayscale images.

Translated text

Key words

Convolutional neural network,Database,Detection,Firearm

求助PDF

上传PDF

Bibtex

AI Read Science

AI Summary

AI Summary is the key point extracted automatically understanding the full text of the paper, including the background, methods, results, conclusions, icons and other key content, so that you can get the outline of the paper at a glance.

Example

Background

Key content

Introduction

Methods

Results

Related work

Fund

Key content

Pretraining has recently greatly promoted the development of natural language processing (NLP)
We show that M6 outperforms the baselines in multimodal downstream tasks, and the large M6 with 10 parameters can reach a better performance
We propose a method called M6 that is able to process information of multiple modalities and perform both single-modal and cross-modal understanding and generation
The model is scaled to large model with 10 billion parameters with sophisticated deployment, and the 10 -parameter M6-large is the largest pretrained model in Chinese
Experimental results show that our proposed M6 outperforms the baseline in a number of downstream tasks concerning both single modality and multiple modalities We will continue the pretraining of extremely large models by increasing data to explore the limit of its performance

Upload PDF to Generate Summary

Must-Reading Tree

Example

Generate MRT to find the research sequence of this paper