Bullying10K: A Large-Scale Neuromorphic Dataset towards Privacy-Preserving Bullying Recognition
This addresses privacy concerns in surveillance for public safety by providing a large-scale neuromorphic dataset, though it is incremental as it builds on existing DVS technology for a specific application.
The authors tackled the problem of violence detection in public spaces while preserving privacy by introducing the Bullying10K dataset, which uses Dynamic Vision Sensors to capture 10,000 event segments totaling 12 billion events and 255 GB of data, enabling benchmarks for action recognition, temporal action localization, and pose estimation.
The prevalence of violence in daily life poses significant threats to individuals' physical and mental well-being. Using surveillance cameras in public spaces has proven effective in proactively deterring and preventing such incidents. However, concerns regarding privacy invasion have emerged due to their widespread deployment. To address the problem, we leverage Dynamic Vision Sensors (DVS) cameras to detect violent incidents and preserve privacy since it captures pixel brightness variations instead of static imagery. We introduce the Bullying10K dataset, encompassing various actions, complex movements, and occlusions from real-life scenarios. It provides three benchmarks for evaluating different tasks: action recognition, temporal action localization, and pose estimation. With 10,000 event segments, totaling 12 billion events and 255 GB of data, Bullying10K contributes significantly by balancing violence detection and personal privacy persevering. And it also poses a challenge to the neuromorphic dataset. It will serve as a valuable resource for training and developing privacy-protecting video systems. The Bullying10K opens new possibilities for innovative approaches in these domains.