Monitoring Human Activity Patterns in Linnaean Botanical Gardens using Machine Learning

Abstract: Urbanisation in this fast-paced world although possessing some lucrative advantages causes some serious problems to its inhabitants. Green spaces are important in highly urbanised societies for adequate restoration of mental health and physical well being. This study focuses on understanding people’s behaviour in green spaces. To enable this, this study was designed with a video of volunteers in a greenspace. In order to automate the data collection required to observe the participants and study their behavioural patterns, computer science aided interventions and machine learning algorithms were employed. YOLOv4 enabled the detection of objects using a regression-based approach to accurately determine the position of the bounding boxes. Using the bounding box coordinates, experiments were conducted with several use cases like hotspot detection and crowd detection. Further using transfer learning, attempts were made to recognize the actions of humans in the videos. The experiments were evaluated using the mean Average Precision technique and achieved good results for the use cases mentioned above. With implications in hotspot detection and crowd detection, the outcome of the study can contribute towards a better and efficient object detection and action recognition.