Comparison of skeleton models and classification accuracy for posture-based threat assessment using deep-learning
This paper compares the effectiveness of two different skeletal pose models for a near real-time, multi-stage classifier. A cascaded neural-network (NN) classifier was previously developed to identify the level of threat posed by an armed person based on detected weapons and body posture. On an updated database of images containing armed individuals and groups, AlphaPose was used to calculate both MPII and COCO skeletons while OpenPose was used to calculate the COCO only. For comparison, we evaluated the importance of individual skeletal joints by systematically removing specific joints from the feature vector and retraining a reduced order network. On the database of images, the AlphaPose-COCO network was best able to correctly classify the threat presented by individuals, 83.7% on average, while AlphaPose-MPII registered 82.2% and 77.6% for OpenPose-COCO. As expected, the most important single joint in both skeleton models is the location of the pistol. As a guide for others deciding which skeleton to use for further studies, we conclude that neither skeleton significantly outperforms the other.
Firearms, Neural networks, Image classification, Weapons, Video
Kevin Carey, Benjamin Abruzzo, Christopher Lowrance, Eric Sturzinger, Ross Arnold, Christopher Korpela, "Comparison of skeleton models and classification accuracy for posture-based threat assessment using deep-learning," Proc. SPIE 11413, Artificial Intelligence and Machine Learning for Multi-Domain Operations Applications II, 1141321 (21 April 2020); https://doi.org/10.1117/12.2556422