Published Paper Details:

Oil spills are a very dangerous occurrence for marine ecosystem is affected and the marine life-forms' existence gets unnecessarily threatened. Oil destroys the insulating ability of fur-bearing mammals, such as sea otters, and the water repellency of a bird's feathers, thus exposing these creatures to the harsh elements. Without the ability to repel water and insulate from the cold water, birds and mammals will die from hypothermia, as a result, it becomes important to employ various oil spill cleanup methods. In our system we may automatically detect & cleaning the oil in the sea water by using a modern technique. In this paper, we present a CNN architecture for semantically segmenting SAR images into multiple classes. The proposed CNN is specifically designed to run on remote embedded systems, which have very limited hardware capability and strict limits on power consumption. Even if the performance in terms of results accuracy does not represent a step forward compared with previous solutions, the presented CNN has the important advantage of being able to run on remote embedded systems with limited hardware resources while achieving good performance. The presented CNN is compatible with dedicated hardware accelerators available on the market due to its low memory footprint and small size. So that the amount of data that needs to be transmitted to ground and processed on ground can be substantially reduced, which will be greatly beneficial in significantly reducing the amount of time needed for identification of oil spills from SAR / real-time images and send SMS alert. And IoT devices equipped with GPS modules are deployed in strategic locations to monitor for oil spills. These devices are capable of collecting GPS location data.