Recognition of violent actions on streets in urban spaces using Machine Learning in the context of the Covid-19 pandemic

Currently, recognition systems based on Artificial Intelligence and Computer Vision have enabled various applications in fields such as Medicine, Industrial Engineering, and in an emerging way in the field of Public Safety as a useful and necessary tool in smart cities that favours the control, management and prevention of criminal acts. Given that violence is a very frequent social problem in Latin American countries. A pilot case has been proposed in the city of Iquitos, Peru, with a tool generated to recognise violent actions from a video or image captured from a mobile phone. This work proposes the application of a mobile tool that facilitates the recognition of high-frequency violent actions on public roads. A bank of 500 images has been generated for each class of violent action prioritised in this work, then a manual labelling tool called 'LabelImg' has been used with the extraction of FPS from videos, and the convolutional neural network algorithm YOLO v3 has been used with the Darknet variant. The results of the experiment achieved an accuracy of 94% in the detection of 4 violent actions: punching, kicking, grappling and strangling.