See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/374558454

Suspicious Activity Tracking Artificial Intelligence Camera

Article in High Technology Letters · October 2023

DOI: 10.37896/HTL29.10/9518

CITATIONS READS

3 1,663

2 authors, including:

Nookala Venu
Madhav Institute of Technology & Science Gwalior
129 PUBLICATIONS 1,894 CITATIONS

SEE PROFILE

All content following this page was uploaded by Nookala Venu on 10 October 2023.

The user has requested enhancement of the downloaded file.

High Technology Letters ISSN NO : 1006-6748

Suspicious Activity Tracking Artificial Intelligence Camera

Dr. Nookala Venu*1, Dr.A.Arun Kumar2

*1
Assistant Professor, Centre for IoT,
Madhav Institute of Technology & Science, Gwalior - 474 005, Madhya Pradesh, India,
(A Govt. Aided UGC Autonomous Institute).
2
Professor & HoD, Department of CSIT,
Marri Laxman Reddy Institute of Technology and Management, Dundigal, Hyderabad -500043,
Telangana, (Autonomous Institute).

Abstract
The latest progress in the technology has led to automation and digitization in almost every
field, and has influenced a wide scope of application. This has caused enormous amount of
data flow from each sector, where the information contained in the data acts as the important
component for the progress of the single person, organization, state, country and so on. These
data with valuable information can be used in the constructive and the destructive perceptive
based on the hands that handle it. So protective measures become very essential for
preserving the data from unwanted access. This paves for developing a system to identify the
suspicious movement in the public areas like military regimes, schools, colleges, hospitals
and financial organizations to safe the data. The method put forward in the paper incorporates
the motion sensors and the face identification system to detect the suspicious activities and
report to the lawful person. The algorithm for the system was developed using the python and
tested for various sets of exemplary real time video recordings to know the accuracy in the
detection.

Keywords: Smart Security, Suspicious Activity, Motion Sensors, Facial Identification

1. Introduction
Tracking and detecting suspicious activity is one of the most demanding tasks for many
security personnel and systems [1]. If a security system fails in places like airports and banks,
then criminals will get an advantage to carry out theft at gunpoint [2]. Out of fear, people
won’t be able to call the police for help. But if a smart camera can detect any suspicious
activity and automatically trigger an alarm to call the police, then such criminal acts can be
prevented. Suspicious Human Activity Recognition from Video Surveillance is an active
research area of image processing and computer vision which involves recognition of human
activity and categorizes them into normal and abnormal activities. Abnormal activities are the
unusual or suspicious activities rarely performed by the human at public places, such as left

Volume 29, Issue 10, 2023 184 http://www.gjstx-e.cn/

High Technology Letters ISSN NO : 1006-6748

luggage for explosive attacks, theft, running crowd, fights and attacks, vandalism and
crossing borders [3]. Normal activities are the usual activities performed by the human at
public places, such as running, boxing, jogging and walking, hand waving and clapping.
Now-a-days, use of video surveillance is increasing day by day to monitor the human activity
which prevents the suspicious activities of the human [4]. An important chore of the video
surveillance is to analyze the captured video frames for identifying unusual or suspicious
activities in security-sensitive region of any country such as banks, parking lots, department
stores, government buildings, prisons, military bases. Video Surveillance captures images of
moving objects in order to watch assault and fraud, comings and goings, prevent theft, as well
as manage crowd movements and incidents. In public places, human performs normal (usual)
and abnormal (suspicious or unusual) activities. Normal activities are the usual activities that
are not dangerous for the human world but abnormal activities may be dangerous for all over
the world. Therefore, an intelligent surveillance system is required that can recognize all the
activities and identify the more dangerous and suspicious activities performed by a human
being. There are two types of surveillance system-first is semi-autonomous in which video is
recorded and sent for analysis by human expert [5-6]. Non-intelligent video surveillance
requires the continuous monitoring by human, which is very costly, problematic and also
very difficult and challenging to watch over all the videos continuously by a guard to prevent
the suspicious 2 human activity. Therefore, a second Fully-autonomous surveillance system
is required that performs low level tasks-motion detection, tracking, classification and
identification of abnormal event.
2. Objective
The main motor of this research paper is to increase intelligence in video
surveillance.Toincrease the intelligence of the video surveillance system, detect all the
irregular movements within the area and select the suspicious ones.Theft reduction, asset
protection, security investigations, providing evidence.

3. Literature Survey
In the ability of humans to vigilantly monitor video surveillance live footage led to the
demand for artificial intelligence that could better serve the task. Humans watching a single
video monitor for more than twenty minutes lose 95% of their ability to maintain attention
sufficient to discern significant events [7]. With two monitors this is cut in half again. Given
that many facilities have dozens or even hundreds of cameras, the task are clearly beyond
human ability. In general, the camera views of empty hallways, storage facilities, parking
lots or structures are exceedingly boring and thus attention is quickly attenuated. Many

Volume 29, Issue 10, 2023 185 http://www.gjstx-e.cn/

High Technology Letters ISSN NO : 1006-6748

researchers have also worked for making real-time intelligent surveillance system but
processing rate of the video frames is not as good as required and there is no such system
that has been developed with 100% detection accuracy and 0% false detection rate for
videos having complex background. Much of the attention is required in the following
suspicious activities detection: Abandoned object detection and theft detection Majority of
the works have been done for the abandoned object detection from surveillance videos
captured by static cameras. Suspicious human activity recognition: a review works detected
the static human as an abandoned object [8-9]. To resolve such problems, human detection
method should be very effective and system should check the presence of the owner in the
scene, if owner is invisible in the scene for long duration, then alarm should be raised. To
resolve the problem of theft or object removal, face of the person who is picking up the
static object, should match with the owner otherwise an alarm must be raised to alert the
security. Future work may also resolve the low contrast situation i.e., similar colour problem
such as black bag and black background which lead to miss detections [10-11]. Future
improvements may be integration of intensity and depth cues in the form of 3D aggregation
of evidence and occlusion analysis in detail. Spatial-temporal features can be extended to 3-
dimensional space for the improvement of abandoned object detection method for various
complex environments. Thresholding based future works can improve the performance of
the surveillance system by using adaptive or hysteresis thresholding approaches [12-13].
Few works have been also proposed for abandoned object detection from the multiple views
captured by multiple cameras. To incorporate these multiple views to infer the information
about abandoned object can also be improved. There is a large scope to detect abandoned
object from videos captured by moving cameras. 40 Falling detection Most of the works
have been done for fall detection of single person in indoor videos based on human shape
analysis, posture estimation analysis and motion-based analysis. Future works can include
the integration of multiple elderly monitoring which is able to monitor more than one person
in the indoor scene [14]. Many elder people go for morning walk every day in public areas
such as parks; to monitor these elder people, a future work can include one or more than one
human fall detection from outdoor surveillance videos. Accidents, illegal parking, and rule
breaking traffic detection several researchers have presented accidents detection, illegal
parking detection and illegal U-turn detections from static video surveillance. These systems
become incapable to detect these abnormal activities in more crowded traffic on roads.
Future works should be based on unsupervised learning of transportation system because of
no standard dataset is available for the training. Violence detection several research works

Volume 29, Issue 10, 2023 186 http://www.gjstx-e.cn/

High Technology Letters ISSN NO : 1006-6748

have been done for the prevention of violence activities such as vandalism, fighting,
shooting, punching, and hitting.
ting. To detect such violence activities, single view static video
camera has been used but sometimes this system fails in occlusion handling. Therefore, a
multi-view
view system has been proposed by few researchers to resolve this problem but it
requires important
tant cooperation between all views at the low-level
low level steps for abnormal
activity detection [15].. Future work may be automatic surveillance system for moving
videos. Improvements are required in accuracy, false alarm reduction, and frame rate to
develop an intelligent
ntelligent surveillance system for the road traffic monitoring.
monitoring

4. Proposed System

Fig.1: System Architecture

4.1 Flow Chart

Fig.2: Flowchart
lowchart of suspicious activity tracking AI camera

Volume 29, Issue 10, 2023 187 http://www.gjstx-e.cn/

High Technology Letters ISSN NO : 1006-6748

4.2 Hardware Requirements

Raspberry Pi 4
Raspberry Pi 4 Model B was released in June 2019 with a 1.5 GHz 64-bit quad core ARM
Cortex-A72 processor, on-board 802.11ac Wi-Fi, Bluetooth 5, full gigabit Ethernet
(throughput not limited), two USB 2.0 ports, two USB 3.0 ports, 2-8 GB of RAM, and dual-
monitor support via a pair of micro HDMI (HDMI Type D) ports for up to 4K resolution. The
version with 1 GB RAM has been abandoned and the prices of the 2 GB version have been
reduced. The 8 GB version has a revised circuit board. The Pi 4 is also powered via a USB-C
port, enabling additional power to be provided to downstream peripherals, when used with an
appropriate PSU. But the Pi can only be operated with 5 volts and not 9 or 12 volts like other
mini computers of this class. The initial Raspberry Pi 4 board has a design flaw where third-
party e-marked USB cables, such as those used on Apple MacBooks, incorrectly identify it
and refuse to provide power. Tom's Hardware tested 14 different cables and found that 11 of
them turned on and powered the Pi without issue. The design flaw was fixed in revision 1.2
of the board, released in late 2019. In mid-2021, Pi 4 B models appeared with the improved
Broadcom BCM2711C0. The manufacturer is now using this chip for the Pi 4 B and Pi 400.
However, the tack frequency of the Pi 4 B was not increased in the factory.

Fig.3: Raspberry Pi 4

Volume 29, Issue 10, 2023 188 http://www.gjstx-e.cn/

High Technology Letters ISSN NO : 1006-6748

Fig.4: RPI Camera module

The sensor itself has a native resolution of 5 megapixels and has a fixed focus lens on board.
In terms of still images, the camera is capable of 2592 x 1944-pixel static images, and also
supports 1080p30, 720p60 and 640x480p60/90 video. No adapters required! This camera will
plug directly into the Raspberry Pi 3 Model B camera port! These 5 megapixels sensor with
OV5647 camera module is capable of 1080p video and still images that connect directly to
your Raspberry Pi. This is the plug-and-play compatible latest version of the Raspbian
operating system, making it perfect for time lapse photography, recording video, motion
detection and security applications. Connect the included ribbon cable to the CSI (Camera
Serial Interface) port on your Raspberry Pi, and you are good to go! The board itself is tiny,
at around 25mm x 23mm x 9mm and weighing in at just over 3g, making it perfect for mobile
or other applications where size and weight are important. The sensor has a native resolution
of 5 megapixels, and has a fixed focus lens on board. In terms of still images, the camera is
capable of 2592 x 1944-pixel static images, and also supports 1080p30, 720p60 and
640x480p90 video. This module is only capable of taking pictures and video, not sound.

Voltage Regulator

Fig.5: Voltage Regulator

Volume 29, Issue 10, 2023 189 http://www.gjstx-e.cn/

High Technology Letters ISSN NO : 1006-6748

Speaker

Fig.6: Speaker
Raspberry Pi does not have a speaker. However, there are several audio output modes that
you can connect a speaker to. You can connect Raspberry Pi to a speaker physically with an
audio jack or a USB port.

4.3 Software Requiremements

 AIML code
 JAVA Script
4.4 Implementation of Project

Fig.7: Schematic Diagram

Tracking and detecting suspicious activity is one of the most demanding tasks for many
security personnel and systems. If a security system fails in places like airports and banks,
then criminals will get an advantage to carry out theft at gunpoint. Out of fear, people won’t
be able to call the police for help. But if a smart camera can detect any suspicious activity and
automatically trigger an alarm to call the police, then such criminal acts can be prevented

Volume 29, Issue 10, 2023 190 http://www.gjstx-e.cn/

High Technology Letters ISSN NO : 1006-6748

Click on the start button and perform the suspicious activity in front of the camera. The
python model will try to recognize it and if found unusual, will issue an alert through
speakers.

4.5. Testing

Fig. 8: Some Activities

Save the JavaScript code as .html and open it in any browser with JavaScript enabled. Click
on the start button and perform the suspicious activity in front of the camera. The ML model
will try to recognize it and if found unusual, will issue an alert. We are also adding functions
for automatically calling and messaging the police.
5. Results and Discussion

Fig.10: Result

Volume 29, Issue 10, 2023 191 http://www.gjstx-e.cn/

High Technology Letters ISSN NO : 1006-6748

When we perform the suspicious activity in front of the camera the camera will try to
recognize it and if found unusual, will issue an alert using speaker that nuisance detected.

6. Conclusion
In this research paper we have done the various techniques related to abandoned object
detection, theft detection, falling detection, accidents and illegal parking detection, violence
detection and fire detection for the foreground object extraction, tracking, feature extraction
and classification. In past decades, several researchers proposed novel approaches with
noise removal, illumination handling, and occlusion handling methods to reduce the false
object detection.

References

[1] Venu, D., Arun Kumar, A., & Vaigandla, K. K. (2022). Review of Internet of Things
(IoT) for Future Generation Wireless Communications. International Journal for Modern
Trends in Science and Technology, 8(03), 01-08.
[2] Venu, D. N. (2015). Analysis of Xtrinsic Sense MEMS Sensors. International Journal of
Advanced Research in Electrical, Electronics and Instrumentation Engineering , 4 (8),
7228-7234.
[3] Nookala Venu, G. R. (2022). Smart Road Safety and Vehicle Accidents Prevention
System for Mountain Road. International Journal for Innovative Engineering
Management and Research , 11 (06), 209-214.
[4] Nookala Venu, D., Kumar, A., & Rao, M. A. S. (2022). Smart Agriculture with Internet
of Things and Unmanned Aerial Vehicles. NeuroQuantology, 20(6), 9904-9914.
[5] Nookala Venu, D., Kumar, A., & Rao, M. A. S. (2022). Internet of Things Based Pulse
Oximeter For Health Monitoring System. NeuroQuantology, 20(5), 5056-5066.
[6] Mr.RadhaKrishna Karne, M. M. (2022). Applications of IoT on Intrusion Detection
System with Deep Learning Analysis. International Jourfor Innovative Engineering and
Management Research , 11 (06), 227-232.
[7] Dr. Nookala Venu, D. A. (2022, March). Routing and Self-Directed Vehicle Data
Collection for Minimizing Data Loss in Underwater Network. IJFANS International
Journal of Food and Nutritional Sciences , 170-183.
[8] Sowmya Jagadeesan, B. B. (2022). A Perishable Food Monitoring Model Based on IoT
and Deep Learning to Improve Food Hygiene and Safety Management. IJFANS
International Journal of Food and Nutritional Sciences , 11 (8), 1164-1178.
[9] Venu, D. N. (2022). Smart Agriculture Remote Monitoring System Using Low Power
IOT Network. IJFANS International Journal of Food and Nutritional Sciences, 11 (6),
327-340.
[10] Venu, D. N. (2022). IOT Surveillance Robot Using ESP-32 Wi-Fi CAM & Arduino.
IJFANS International Journal of Food and Nutritional Sciences , 11 (5), 198-205.

Volume 29, Issue 10, 2023 192 http://www.gjstx-e.cn/

High Technology Letters ISSN NO : 1006-6748

[11] Sandhya rani B, S. K. (2022). Vehicle Fuel Level Monitor and Locate the Nearest Petrol
Pumps using IoT. International Journal for Innovative Engineering and Management
Research , 11 (06), 233-240.

[12] Nookala Venu, V. M. (2022). Alcohol Detection and Engine Locking System.
International Journal for Innovative Engineering and Management Research , 11 (06),
157-160.
[13] Venu, D. N. (2022). IOT Based Enabled Parking System in Public Areas. IJFANS
International Journal of Food and Nutritional Sciences, 11 (4), 162-174.
[14] Sandhya rani, D. V. (2022). IOT Based Smart Irrigation System Using Node MCU.
International Journal For Innovative Engineering and Management Research , 11 (6),
100-106.
[15] Dr.Nookala Venu, A. E. (2022). Low Power Area Efficient ALU with Low Power Full
Adder. International Journal For Innovative Engineering and Management Research ,
11 (06), 167-170.

Volume 29, Issue 10, 2023 193 http://www.gjstx-e.cn/

View publication stats