The problem Suspect Tracking and following Bot solves

Our solution mainly targets object detection and its main goal is to identify and find one or more effective targets using video data. It covers a wide range of techniques, including image processing, pattern recognition, artificial intelligence, and machine learning.
Object detection is breaking into a wide scope of enterprises, with use cases extending from individual security to efficiency in the working environment. Object detection is applied in numerous territories of image processing, including picture retrieval, security, observation, computerized vehicle systems, and machine investigation. Critical difficulties remain in the field of object detection. The potential outcomes are inestimable with regard to future use cases for object detection.
Major areas of application are:

1. Object tracking
   Monitoring items with an item/object detection framework is also possible, for example, tracking a ball during a football world cup match, tracking the swing of a cricket bat, or tracking an individual in a film.
   Surveillance and security, traffic monitoring, video correspondence, robot vision, and activity are just a few of the applications for object tracking.

2. CCTV surveillance that is automated
   Surveillance is an important part of security and monitoring. Continuous advancements in computer vision innovation are required to better various programmed surveillance systems. However, their viability is governed by a variety of conditions, and they are not completely dependable. In both discovery and follow-up activities, this investigation looked into the ability of an automated surveillance system to reduce the CCTV administrator's outstanding task.

In most cases, CCTV is required to run indefinitely, necessitating a large memory framework to store the captured video. We can automate CCTV by using an object discovery framework, such that once a few items are detected, the recording will begin.

Challenges we ran into

1. Budget problem - since the hardware part is very expensive. so we try to spend little money as possible on the hardware.

2. Integration of Raspberry Pi with the computer due to lack of monitor and other hardware.

3. Writing Algorithms for recognition and tracking

4. Debugging - as there were lots of errors in our program, which takes lots of time to correct the working of the project

5. Testing the algorithms written for bot in real-world was challenging and demanded many corrections in algorithms and code.