Digital Detection of Suspicious Behavior With Gesture Recognition and Patterns Using Assisted Learning Algorithms

Digital Detection of Suspicious Behavior With Gesture Recognition and Patterns Using Assisted Learning Algorithms

Nancy E. Ochoa Guevara (Fundación Universitaria Panamericana, Colombia), Andres Esteban Puerto Lara (Fundación Universitaria Panamericana, Colombia), Nelson F. Rosas Jimenez (Fundación Universitaria Panamericana, Colombia), Wilmar Calderón Torres (Fundación Universitaria Panamericana, Colombia), Laura M. Grisales García (Fundación Universitaria Panamericana, Colombia), Ángela M. Sánchez Ramos (Fundación Universitaria Panamericana, Colombia) and Omar R. Moreno Cubides (Fundación Universitaria Panamericana, Colombia)
Copyright: © 2020 |Pages: 30
DOI: 10.4018/978-1-7998-1839-7.ch007

Abstract

This chapter presents a study to identify with classification techniques and digital recognition through the construction of a prototype phase that predicts criminal behavior detected in video cameras obtained from a free platform called MOTChallenge. The qualitative and descriptive approach, which starts from individual attitudes, expresses a person in his expression, anxiety, fear, anger, sadness, and neutrality through data collection and feeding of some algorithms for assisted learning. This prototype begins with a degree higher than 40% on a scale of 1-100 of a person suspected, subjected to a two- and three-iterations training parameterized into four categories—hood, helmet, hat, anxiety, and neutrality—where through orange and green boxes it is signaled at the time of the detection and classification of a possible suspect, with a stability of the 87.33% and reliability of the 96.25% in storing information for traceability and future use.
Chapter Preview
Top

Background

Problematic

According to Norza, Peñaloza and Rodriguez (2016) perpetrators of crimes against life and personal integrity they increased by 49.61% during 2016, compared to the immediately preceding year. A total of 147,891 cases in 2015, he went on to have 221,256 in 2016. Likewise, we can see that being Bogota the capital of the heads republic with a 16.31% registration of occurrences of crimes nationwide. Theft 146,643 people had records, noting an increase of 45% over 2015. The 50.30% of the total was presented at: Bogota (25.84%), Antioquia (14.44%) and Valle (10, 01%).

This shows that criminal behavior and perceived insecurity in the cities especially in Bogota, is not only in perception; but they are a reality and are a problem that can be tackled from several disciplines. The certain suspicious attitudes that precede the crime early, could serve to generate the necessary alarms and take measures to prevent its occurrence. With the information provided by the OAIEE in 2019, evidence that measures such as increasing police in critical areas such as Transmilenio (transport stations), parks and school zones have not been very effective in cities, especially in Bogota.

Problem Formulation

How the digital recognition of suspicious behavior by identifying gestures and patterns, will predict criminal behavior detected in video cameras using assisted learning algorithms?

Overall Objective

Identify classification techniques and digital recognition of suspicious behavior by detecting gestures and patterns, using algorithms assisted learning, so that through a prototype phase, to predict criminal behavior detected in video obtained from a free platform.

Complete Chapter List

Search this Book:
Reset