Authors :
Susmitha John; Bino Thomas
Volume/Issue :
Volume 8 - 2023, Issue 4 - April
Google Scholar :
https://bit.ly/3TmGbDi
Scribd :
https://bit.ly/3HoX9vZ
DOI :
https://doi.org/10.5281/zenodo.7878739
Abstract :
In the modern era, usage of video surveillance
has increased which in fact increase the size of data.
Video surveillance is widely using in both public and
private areas for improving the security and safety of
human being. Hence, it is important to identify and
analyse the video in different angle so as to extract the
most important information from the video. The video
may contain both usual or unusual event, mostly the
users need to find out the unusual event from the video
that may affect their security. To differentiate both the
events separately, here we are considering a special
scenario related with vehicle. The vehicles on road can
move in different ways, where they can follow or violate
traffic rules, illegal U-turns, accidents etc. In this paper,
the unusual event considered is the accidents on the
road. The technology used is deep learning and
computer vision. The neural network selected is the
DenseNet. The DenseNet is a convolutional neural
network. The peculiarity of a DenseNet architecture is
that each layer in a network is connected to every other
layer. For each layer, the feature maps of all the
preceding layers are used as inputs, and its own feature
maps are used as input for each subsequent layer. The
deployment of DenseNet along with computer vision
increases the accuracy of the system.
Keywords :
Deep Learning, Computer Vision, Segmentation, Tracking.
In the modern era, usage of video surveillance
has increased which in fact increase the size of data.
Video surveillance is widely using in both public and
private areas for improving the security and safety of
human being. Hence, it is important to identify and
analyse the video in different angle so as to extract the
most important information from the video. The video
may contain both usual or unusual event, mostly the
users need to find out the unusual event from the video
that may affect their security. To differentiate both the
events separately, here we are considering a special
scenario related with vehicle. The vehicles on road can
move in different ways, where they can follow or violate
traffic rules, illegal U-turns, accidents etc. In this paper,
the unusual event considered is the accidents on the
road. The technology used is deep learning and
computer vision. The neural network selected is the
DenseNet. The DenseNet is a convolutional neural
network. The peculiarity of a DenseNet architecture is
that each layer in a network is connected to every other
layer. For each layer, the feature maps of all the
preceding layers are used as inputs, and its own feature
maps are used as input for each subsequent layer. The
deployment of DenseNet along with computer vision
increases the accuracy of the system.
Keywords :
Deep Learning, Computer Vision, Segmentation, Tracking.
