Systems and methods for monitoring, optimization, and control of pool/spa equipment using video analytics are provided. A camera system in communication with a microprocessor monitors a pool/spa environment, identifies objects of interest in the pool/spa environment, classifies the objects of interest, and identifies scenarios and/or learned behaviors of objects utilizing video analytics. The analytics can include object detection in combination with tracking algorithms in order to precisely locate objects of interest within the video frames. Further image classification and scene labeling algorithms may be used to classify the object in order to define its attributes. Once processed, the system can transmit alerts or commands to pool/spa users and devices to modify the operation thereof based on the identified attributes of the objects of interest.