Underwater human body detection using computer vision algorithms

The number of studies to ensure the security when life-threatening unexpected events are encountered increases. Increasing of time spent under the water can cause the death of people. Thus, people who are in a risk of suffocation in the water must be found for early intervention and this process must be quick. The main contribution of this study is to detect and to track the people under the water quickly. Thresholding, Background Subtraction, Interframe Difference and Foreground Detection methods have been applied to create the silhouette of the people under the water. These methods have been demonstrated on videos which are found from internet.