scholarly journals Moving Cast Shadows Detection Methods for Video Surveillance Applications

2012 ◽  
pp. 23-47 ◽  
Author(s):  
Ariel Amato ◽  
Ivan Huerta ◽  
Mikhail G. Mozerov ◽  
F. Xavier Roca ◽  
Jordi Gonzàlez
Keyword(s):  
Video Surveillance ◽  
Detection Methods ◽  
Surveillance Applications

scholarly journals Foreground Segmentation in Depth Imagery Using Depth and Spatial Dynamic Models for Video Surveillance Applications

Sensors ◽  
2014 ◽  
Vol 14 (2) ◽  
pp. 1961-1987 ◽  
Author(s):  
Carlos del-Blanco ◽  
Tomás Mantecón ◽  
Massimo Camplani ◽  
Fernando Jaureguizar ◽  
Luis Salgado ◽  
...  
Keyword(s):  
Video Surveillance ◽  
Dynamic Models ◽  
Foreground Segmentation ◽  
Spatial Dynamic ◽  
Surveillance Applications

scholarly journals Automatic Handgun Detection with Deep Learning in Video Surveillance Images

2021 ◽  
Vol 11 (13) ◽  
pp. 6085
Author(s):  
Jesus Salido ◽  
Vanesa Lomas ◽  
Jesus Ruiz-Santaquiteria ◽  
Oscar Deniz
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Video Surveillance ◽  
Automatic Detection ◽  
Public Spaces ◽  
Detection Methods ◽  
Training Dataset ◽  
Average Precision ◽  
Terrorist Acts

There is a great need to implement preventive mechanisms against shootings and terrorist acts in public spaces with a large influx of people. While surveillance cameras have become common, the need for monitoring 24/7 and real-time response requires automatic detection methods. This paper presents a study based on three convolutional neural network (CNN) models applied to the automatic detection of handguns in video surveillance images. It aims to investigate the reduction of false positives by including pose information associated with the way the handguns are held in the images belonging to the training dataset. The results highlighted the best average precision (96.36%) and recall (97.23%) obtained by RetinaNet fine-tuned with the unfrozen ResNet-50 backbone and the best precision (96.23%) and F1 score values (93.36%) obtained by YOLOv3 when it was trained on the dataset including pose information. This last architecture was the only one that showed a consistent improvement—around 2%—when pose information was expressly considered during training.

A two-step face hallucination approach for video surveillance applications

2013 ◽  
Vol 74 (6) ◽  
pp. 1845-1862 ◽  
Author(s):  
Zhen Jia ◽  
Jianwei Zhao ◽  
Hongcheng Wang ◽  
Ziyou Xiong ◽  
Alan Finn
Keyword(s):  
Video Surveillance ◽  
Face Hallucination ◽  
Surveillance Applications

Bitstream-Based JPEG Encryption in Real-time

2013 ◽  
Vol 5 (3) ◽  
pp. 1-14 ◽  
Author(s):  
Stefan Auer ◽  
Alexander Bliem ◽  
Dominik Engel ◽  
Andreas Uhl ◽  
Andreas Unterweger
Keyword(s):  
Real Time ◽  
Video Surveillance ◽  
Time Operation ◽  
Real Time Operation ◽  
Surveillance Applications

The authors propose a framework to encrypt Baseline JPEG files directly at bitstream level, i.e., without the need to recompress them. The authors’ approach enables encrypting more than 25 pictures per second in VGA resolution, allowing real-time operation in typical video surveillance applications. In addition, their approach preserves the length of the bitstream while being completely format-compliant. Furthermore, the authors show that an attack on the encryption process, which partly relies on AES, is practically infeasible.

Sign in / Sign up

Export Citation Format

Share Document