Machine Learning in Video Surveillance for Fall Detection

Abstract:
The present paper considers the usage of deep learning and transfers learning techniques in fall
detection by means of surveillance camera data processing. As a dataset, an open dataset
gathered by the Laboratory of Electronics and Imaging of the National Center for Scientific
Research in Chalonsur-Saone was used. The architecture of the CNN AlexNet, which was used
as a starting point for the classifier, was adapted to solve fall detection problem. The proposed
method was tested on a dataset of 30 records containing a single fall episode each. We achieved
Cohen’s kappa of 0.93 and 0.60 for the fall – non-fall classification for the known and unknown
for classifier surrounding conditions, respectively.

Existing System:
At present, surveillance cameras are widely used. They are utilized to identify suspicious
persons, as well as persons in a state of alcohol and drug intoxication, which may be dangerous
to a life and health of others. The developers of the closed-circuit television system (CCTV
systems) offer complexes consisting of IP cameras for the automated detection of suspicious
persons. These systems can be based on biometric identification (for example, the NeoFace
system, smart glasses as well as on the recognition of emotions or facial expressions (for
example, DeepFace. The main disadvantage of this type of systems is that information about the
possible trespasser may be absent in the database used for biometric identification.

It should be noted that in the majority of cases, data from CCTV cameras are used only for
the creating archives of video records, and the possibilities of intelligent video analysis of data
from remote objects are practically not used. Such situation is determined in particular by
technical difficulties associated with the use of intelligent video surveillance systems in practice.

In the majority of papers on CCTV cameras records analysis the effectiveness of the fall
event classifiers is artificially overestimated because of the limitations of the datasets used for
testing and training procedure. These limitations may be described as follows:
• Dataset is usually formed by the data recorded in unchanged conditions (most often in the
laboratory conditions, rather than realistic ones), and for uniform illumination of the entire
analyzed scene.
• One and the same person acts as test subjects.
• Movement artifacts of the”fall” type are similar in preceding actions of the subject and her/his
relative position toward the camera at the time of the fall.
Proposed system:
In present work, an open database of video recordings provided by the Laboratory of Electronics
and Imaging of the National Center for Scientific Research in Chalon-sur-Saone was used.
In Fig. 1of frames extracted from the video records both corresponding to fall and non-
fall episodes are presented. The merits of this database include the following factors

 Video signals are recorded for various environmental conditions.

 The illumination of the experimental scene is irregular. The dataset contains records for

which contrast of the human over the background objects is rather low due to the limits of the

camera dynamic range and presence of regions with high brightness

 4 different subjects (3 men and 1 woman) participated in the experiments.

 Falls were performed at different viewing angles, both from the standing position and from

the sitting position.

 Volunteers were falling both on a specially prepared cushioning base, and directly on the

floor.
 SYSTEM SPECIFICATIONS
SOFTWARE REQUIREMENTS:

Platform : python 3.7

IDE : Pycharm
Libraries : OpenCV

HARDWARE REQUIREMENTS:

RAM : 4GB and Higher

Processor : Intel i3 and above
Hard Disk : 500GB: Minimum

CONCLUSION:
In this paper, we presented the feasibility study of deep learning and transfer learning techniques
usage in fall detection by means of surveillance camera data processing. The proposed method
allows detecting fall events on video records. We achieved Cohen’s kappa of 0.93 and 0.60 for
the fall – non-fall classification for the known and unknown for classifier surrounding
conditions, respectively. The future activity will consider enriching the dataset. Moreover, we are
planning to improve the classifier performance by using additional heuristics considering relative
positions of the frames in time and knowledge about typical duration of fall episodes. The results
might be used while creating new noncontact fall detectors both for outdoor and indoor
applications.