Anomalous pose detection method and system

A system comprising:

• a display;
• an input device;
• a processor communicatively coupled to the display and the input device;
• and
• a memory communicatively coupled to the processor and having stored thereon computer program code that is executable by the processor, wherein the computer program code, when executed by the processor, causes the processor to
• detect a living object of interest in a field of view of a video camera;
• generate, by a neural network, a pose vector associated with a pose of the living object of interest;
• compare the pose vector of the living object of interest to one or more clusters of pose vectors in a dataset of pose vectors, each cluster of pose vectors comprising one or more pose vectors generated from poses of living objects found in the field of view of the video camera;
• determine a value associated with a similarity of the pose vector of the living object of interest to at least one of the one or more pose vectors comprising a cluster of pose vectors wherein the determination of the value associated with the similarity of the pose vector of the living object of interest to at least one of the one or more pose vectors comprising a cluster of pose vectors comprises determining an Euclidean distance, wherein the Euclidean distance is determined using the pose vector of the living object of interest and a cluster center of each of the clusters of pose vectors;
• compare the value associated with the similarity of the pose vector of the living object to at least one of the one or more pose vectors comprising a cluster of pose vectors to a predetermined value;
• and
• based on the comparison of the value associated with the similarity of the pose vector of the living object to at least one of the one or more pose vectors comprising a cluster of pose vectors to the predetermined value, add the pose vector to the dataset of pose vectors or generating an alert, wherein if the pose vector of the living object is added to the dataset of pose vectors, the pose vector is added to a cluster of the one or more clusters of pose vectors, and the cluster center of the cluster is recalculated.