Water surface floating object detection and identification method and system based on YOLOv3 improvement

Abstract

The invention discloses a water surface floating object detection and identification method based on an improved YOLOv3 identification model, and relates to the technical field of computer vision. The method comprises the following steps: pre-collecting water surface floating object data, carrying out the enhancement and amplification of image data through geometric transformation and color transformation, marking the floating objects in the data, obtaining a water surface drifting object data set, and splitting the water surface drifting object data set into a training set and a test set; constructing an improved YOLOv3 network model, and training the improved YOLOv3 network model by adopting the water surface drifting object training set; constructing a water surface drifting object test set according to the water surface drifting object data image, and detecting and identifying the water surface drifting object test set by using the trained improved YOLOv3 network model. The improved YOLOv3 has strong generalization ability, occupies small storage space and video memory space, improves detection and identification accuracy, can ensure real-time performance, and can realize accurate and rapid monitoring and identification of water surface drifts in client equipment with limited computing power and memory.

Description

technical field [0001] The invention belongs to the technical field of computer vision, and relates to an improved YOLOv3-based method and system for detecting and identifying floating objects on the water surface. Background technique [0002] In recent years, the speed of urbanization and industrialization in our country is getting faster and faster, and the problem of water environment pollution is not optimistic at the same time as the economy is developing rapidly. There are a large number of floating objects in rivers and lakes, which not only destroys the natural ecological landscape, but also seriously threatens human life and health and sustainable economic development. Therefore, the research on how to effectively monitor floating objects in rivers and lakes has important practical significance. [0003] The existing floating object detection technology based on video images is mainly aimed at remote sensing images, and analyzes and detects whether there are floati...

AI Technical Summary

Problems solved by technology

YOLOv3 is currently the mainstream algorithm in the field of target detection, but its volume is too large to be embedded in devices with limited computing power (such as automatic salvage ships and other river patrol equipment, etc.) to meet the requirements of real-time detection.

Since there is currently no professional data set publicly available in the field of surface drift detection, the model has the problem of unbalanced sample categories

YOLOv3 sacrifices a certain detection speed to improve the detection accuracy, but it is still difficult to detect floating objects on the water surface of small targets.

Images