Towards Building a Visual Behaviour Analysis Pipeline for Suicide Detection and Prevention

Abstract

Understanding human behaviours through video analysis has seen significant research progress in recent years with the advancement of deep learning. This topic is of great importance to the next generation of intelligent visual surveillance systems which are capable of real-time detection and analysis of human behaviours. One important application is to automatically monitor and detect individuals who are in crisis at suicide hotspots to facilitate early intervention and prevention. However, there is still a significant gap between research in human action recognition and visual video processing in general, and their application to monitor hotspots for suicide prevention. While complex backgrounds, non-rigid movements of pedestrians and limitations of surveillance cameras and multi-task requirements for a surveillance system all pose challenges to the development of such systems, a further challenge is the detection of crisis behaviours before a suicide attempt is made, and there is a paucity of datasets in this area due to privacy and confidentiality issues. Most relevant research only applies to detecting suicides such as hangings or jumps from bridges, providing no potential for early prevention. In this research, these problems are addressed by proposing a new modular design for an intelligent visual processing pipeline that is capable of pedestrian detection, tracking, pose estimation and recognition of both normal actions and high risk behavioural cues that are important indicators of a suicide attempt. Specifically, based on the key finding that human body gestures can be used for the detection of social signals that potentially precede a suicide attempt, a new 2D skeleton-based action recognition algorithm is proposed. By using a two-branch network that takes advantage of three types of skeleton-based features extracted from a sequence of frames and a stacked LSTM structure, the model predicts the action label at each time step. It achieved good performance on both the public dataset JHMDB and a smaller private CCTV footage collection on action recognition. Moreover, a logical layer, which uses knowledge from a human coding study to recognise pre-suicide behaviour indicators, has been built on top of the action recognition module to compensate for the small dataset size. It enables complex behaviour patterns to be recognised even from smaller datasets. The whole pipeline has been tested in a real-world application of suicide prevention using simulated footage from a surveillance system installed at a suicide hotspot, and preliminary results confirm its effectiveness at capturing crisis behaviour indicators for early detection and prevention of suicide.

Understanding and detecting behaviours prior to a suicide attempt: A mixed-methods study

“…A range of existing deep learning-based computer vision algorithms were tested in various combinations, and a new skeleton-based action recognition model was proposed to find the optimal design for this setting and application. Full details of the algorithm selection are reported elsewhere ( Li et al, 2022 ). The algorithm was trained using footage depicting a range of behaviours from this specific location.…”

Sensor Fusion for Social Navigation on a Mobile Robot Based on Fast Marching Square and Gaussian Mixture Model

“…Real-time people detection has had a great development in recent years, with diverse techniques and applications in several research fields [24][25][26]. In this paper, it was decided to combine MediaPipe [27] and YOLO [28].…”

Evaluating a Human Detection Model in a Behaviour Analysis Pipeline for Suicide Prevention

“…After just 10 minutes of training, psychology doctoral students could correctly identify approximately 25% of incident clips preceding a suicide attempt, with no false positives [8]. We have developed a computer vision analysis pipeline to identify specific behaviours preceding a suicide attempt [9], with preliminary analysis showing that good accuracy can be achieved with very strong levels of acceptability amongst the public and people with lived experience [10]. Despite overall strong support, some respondents raised concerns that biases embedded within algorithms could potentially lead to negative outcomes, especially for culturally and linguistically diverse (CALD) and First Nations communities who may have prior negative experiences with first responders or other personnel [11].…”