ABSTRAT:

Suspicious activities are of a problem when it comes to the potential risk it brings to humans. With the increase in criminal activities in urban and suburban areas, it is necessary to detect them to be able to minimize such events. Early days surveillance was done manually by humans and were a tiring task as suspicious activities were uncommon compared to the usual activities. With the arrival of intelligent surveillance systems, various approaches were introduced in surveillance. We focus on analysing two cases, those if ignored could lead to high risk of human lives, which are detecting potential gun-based crimes and detecting abandoned luggage on frames of surveillance footage. We present a deep neural network model that can detect handguns in images and a machine learning and computer vision pipeline that detects abandoned luggage so that we could identify potential gun-based crime and abandoned luggage situations in surveillance footage.

EXISTING SYSTEM :

Many activities appear suspicious under activities in surveillance footage and some of them even pose a threat to lives. We specifically focus on two cases and identify solutions to detect them. Detecting objects was a challenge and before arriving at an end to end solution different indirect approaches and pipelines were used. Conventional methods used in indirect approaches included handcrafted features and shallow neural network architectures to pertain to the resource limitations and effective pipelines to detect objects. A. Gun Detection Research Some of the early literature involving detection of weapons focused on analysing x-ray images [6]and infrared images [7] to detect concealed weapons. These systems had machines scanning through individuals and belongings that go through them and the images obtained from those were analysed using different approaches to detect weapons

EXISTING SYSTEM DISADVANTAGES:

1.LESS ACCURACY

2. LOW EFFICIENCY

PROPOSED SYSTEM :

uler and Farrow uses moving object tracking to detect abandoned objects with a new stationary algorithm. Their technique comprises of two main parts: a tracker for detecting and tracking movements and a stationary object detector that allows the objects abandoned to be detected and persistently detected rapidly. And Their method uses a background subtraction-based tracker for identify stationary objects. [13] Some systems have been created for detection of abandoned objects consisting of four primary parts: foreground segmentation, moving object tracking, stationary object monitoring and event detection. [14] A popular technique for detecting moving objects in a scene is to use a background subtraction in which moving objects are perceived as foreground and non-moving objects are taken as the background. Such methods give good accurate results and computationally less expensive. However, Lim and Keels proposed a triplet CNN model, named as Feigned [15] is introduced to further improve accuracy by using deep learning techniques.

PROPOSED SYSTEM ADVANTAGES:

1.HIGH ACCURACY

2.HIGH EFFICIENCY

SYSTEM REQUIREMENTS
SOFTWARE REQUIREMENTS:
• Programming Language : Python
• Font End Technologies : TKInter/Web(HTML,CSS,JS)
• IDE : Jupyter/Spyder/VS Code
• Operating System : Windows 08/10

HARDWARE REQUIREMENTS:

 Processor : Core I3
 RAM Capacity : 2 GB
 Hard Disk : 250 GB
 Monitor : 15″ Color
 Mouse : 2 or 3 Button Mouse
 Key Board : Windows 08/10