A method and system for automatic identification of water body floating objects based on artificial intelligence

Abstract

The invention discloses an artificial intelligence-based automatic identification method and system for floating objects in a water body. Firstly, the characteristic value knowledge base of different ground objects represented by different types of floating objects in different wave bands is constructed; the characteristic value knowledge base is used as the basis for classification, The classification method of the decision tree is used to classify the monitoring images of floating objects, and then the clustering processing is used to classify and post-process the classification results to obtain the results of the identification of floating objects in the monitoring images; the accuracy evaluation of the identification results of floating objects in the monitoring images is carried out; finally The feature numerical knowledge base is input into the support vector machine for training, and the trained support vector machine model is used to automatically identify the floating object information in the floating object monitoring image. The invention is suitable for automatic identification of floating object information in images, thereby effectively and reasonably organizing floating cleaning actions, and is of great significance for ensuring ship navigation, dam safety, reservoir scheduling operation, and the like.

Description

technical field [0001] The invention belongs to the field of image recognition and machine intelligence learning, and relates to a method and system for automatic identification of floating objects in water bodies based on artificial intelligence, which is suitable for automatic identification of floating object information in images, so as to effectively and reasonably organize cleaning actions, and to ensure It is of great significance for ship navigation, dam safety, reservoir dispatching and operation, etc. Background technique [0002] Floating matter is solid waste that floats on the surface of water bodies depending on buoyancy, including logs, branches, straw, straw, plastic products, and human and animal carcasses. The existence of floating objects has adverse effects on water quality, water surface landscape, water supply, aquatic products, shipping, etc., not only destroying the ecological environment, but also threatening drinking water safety. Especially in the...

AI Technical Summary

Problems solved by technology

There are few studies on the automatic identification of floating objects. Remote sensing images can only identify large-scale floating objects. When applied to rivers and reservoirs, it is often impossible to accurately identify the specific conditions of floating objects in a small area due to insufficient image resolution; Sampling to identify floating objects consumes manpower and material resources, and due to factors such as actual water flow and terrain, field sampling in some areas is often very difficult

The existing research has provided technical reference for the further development of the rapid identification of floating objects to a certain extent, but the existing methods are still unable to quickly and accurately automatically identify floating objects

Images