Abstract: There is disclosed a method of removing underwater gas bubbles from underwater devices such as cameras, optical lenses, or domes comprising acquiring a camera image or a sequence of images, applying a computer vision algorithm for detecting bubbles that stick to underwater cameras, optical lenses or domes and vibrating a motor for a time period sufficient to remove the majority of the bubbles, and optionally repeating vibrating the motor until complete removal or dismissal of bubbles is achieved. There is further disclosed a method of moving a moving element with respect to an underwater surface associated with an underwater acquisition device, wherein a motion of the moving element enables at least part of the moving element to interact with at least one of the surface or the underwater gas bubbles, thereby dismissing or removing underwater gas bubbles from at least part of the surface. Corresponding systems are also disclosed.

Abstract: It is provided a method of detecting human drowning, comprising: attempting to detect humans in a sequence of underwater images taken by a single camera, for identifying humans-in-water candidates in the images, said detection using at least a machine learning algorithm, tracking humans-in-water candidates throughout this sequence, and detecting human drowning risk. It is also provided a system for detecting human drowning, comprising at least one underwater camera configured to take at least a sequence of underwater images, the system being configured to attempt to detect humans in the sequence of underwater images, for identifying humans-in-water candidates in the images, said detection using at least a machine learning algorithm, track humans-in-water candidates throughout this sequence, and detect human drowning risk.

Abstract: It is provided a method of detecting human drowning, comprising: attempting to detect humans in a sequence of underwater images taken by a single camera, for identifying humans-in-water candidates in the images, said detection using at least a machine learning algorithm, tracking humans-in-water candidates throughout this sequence, and detecting human drowning risk. It is also provided a system for detecting human drowning, comprising at least one underwater camera configured to take at least a sequence of underwater images, the system being configured to attempt to detect humans in the sequence of underwater images, for identifying humans-in-water candidates in the images, said detection using at least a machine learning algorithm, track humans-in-water candidates throughout this sequence, and detect human drowning risk.