Vessel target real-time detection method based on deep neural network

Abstract

The invention discloses a vessel target real-time detection method based on a deep neural network. The method comprises the following steps: firstly, establishing a real-time deep neural network modelfor small target detection; constructing a small target training sample set according to a preset initial training sample set, and determining the optimal size range of the target; performing ROO training to obtain an initial deep neural network model; performing oHEM training; performing ship target detection on a preset initial training sample set by using the initial deep neural network model,adding difficult negative samples appearing in detection into the difficult negative sample set, and training the initial deep neural network model by using samples in the difficult negative sample set to obtain an optimized deep neural network model; and finally, establishing a remote sensing image pyramid model, and carrying out ship target detection layer by layer from the bottom layer of thepyramid by utilizing the optimized deep neural network. According to the method, the detection speed and precision can be greatly improved.

Description

technical field [0001] The invention relates to the field of remote sensing image target detection, in particular to a deep neural network-based real-time detection method for ship targets. Background technique [0002] Ships are important monitoring targets at sea, and remote sensing image processing is the most abundant and widely used ship monitoring technology for obtaining ship target information. In the civil field, the result information of ship detection can be used as input to other systems to help them realize and optimize programs and functions. By classifying and matching the detected ships, mapping and positioning the geographic coordinates, the position information of the target ship can be obtained, and the search and rescue at sea can be realized; by classifying the detected ships by function and size, statistical density information and By generating geographical distribution maps, fishery detection can be realized; by searching and matching ships, real-tim...

Images