A Machine Learning Approach to Detect Violent Behaviour from Video

Abstract

The automatic classification of violent actions performed by two or more persons is an important task for both societal and scientific purposes. In this paper, we propose a machine learning approach, based a Support Vector Machine (SVM), to detect if a human action, captured on a video, is or not violent. Using a pose estimation algorithm, we focus mostly on feature engineering, to generate the SVM inputs. In particular, we hand-engineered a set of input features based on keypoints (angles, velocity and contact detection) and used them, under distinct combinations, to study their effect on violent behavior recognition from video. Overall, an excellent classification was achieved by the best performing SVM model, which used keypoints, angles and contact features computed over a 60 frame image input range.

Violent Video Classification with Transfer Learning Approach Using Inception-V3 and Support Vector Machine

“…The method based on extraction of visual hand-crafted features, such as angles, velocity and contact between two human subjects and creating a feature vector with encoded temporal information was proposed in (9) . Further a binary classification SVM model is utilized to predict violent behavior.…”

“…F1-score measures test accuracy, a Harmonic Mean between precision and recall, with a score between 0 and 1. In present study will focus on calculating the F1-score (9) to check the model behavior using following formula (1).…”