SR-SqueezeNet: A lightweight hyperspectral identification model for oil spills based on smoothed activation functions

The demand for real-time identification of oil spills in disaster emergency response is urgent, Unmanned Aerial Vehicles (UAVs) are important monitoring means for oil spills by advantage of their flexible, fast and low-cost, so it's crucial of developing lightweight model for UAVs. This paper proposed a lightweight hyperspectral identification model called SR-SqueezeNet, which based on SqueezeNet model and used the designed smooth-type activation function Smooth-ReLU. And this research conducted a series of experiments based on the multi-dimensional airborne images of the oil spills. The results show that SR-SqueezeNet performs the best in both model lightweighting and extraction accuracy. Compared with the traditional SqueezeNet, the identification accuracy is improved by 1.92 %, the number of parameters is reduced by 75.11 %, and the model size is reduced from 26.46 MB to 12.15 MB. Therefore, the SR-SqueezeNet model has potential ability in the practical needs of oil spill UAVs' lightweight detection.