Water surface floating object automatic detection method and device for urban river regulation

A technology for automatic detection of floating objects on the water surface, applied in the fields of computer vision and artificial intelligence, can solve the problems of low detection accuracy and poor generalization ability, and achieve the effects of high detection accuracy, good support, and strong anti-interference ability.

CN111259827AActive Publication Date: 2020-06-09HOHAI UNIV
2 Cites 4 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Publication Date
2020-06-09

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a water surface floating object automatic detection method and device for urban river regulation. The method comprises the steps if automatically extracting an image from a water surface monitoring video stream, and enhancing the image based on a self-adaptive contrast ratio; clustering the size of a target detection object in the image to obtain size distribution of a detected target; constructing an improved Faster R-CNN network model, determining a fused feature layer according to the size of a target detection object and the size of a receptive field of each layer of the convolutional neural network model, and fusing features extracted across the feature layers in a splicing mode; determining the size and the length-width ratio of an RPN network anchor frame according to a clustering result, and generating suggested areas of targets of different sizes; and optimizing network model parameters through an iterative method and realizing detection of water floaters. The invention can achieve the automatic recognition and marking of the floaters in the video stream, solves problems that the detection accuracy is low and the generalization capability is poor, can achieve the automatic detection of the floaters, and can be used for the automatic supervision of an actual project, such as an urban river channel.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to an automatic detection method and device for floating objects on the water surface facing urban river channel supervision, and belongs to the fields of artificial intelligence and computer vision. Background technique

[0002] With the rapid economic and social development, water ecology and water environment issues have become one of the people's livelihood issues that the masses are most concerned about. The accumulation of floating objects on the water surface not only affects the quality of the urban living environment, but also causes water pollution and damage to the ecological balance, and even threatens the safety of drinking water. In order to solve complex water environment problems, the river chief system proposes to strengthen water environment governance, and relevant departments can report and respond quickly to the floating objects on the water surface in a timely manner, which requires intelligent detection of f...

Examples

Embodiment Construction

[0039] Below in conjunction with specific embodiment and accompanying drawing, further illustrate the present invention, it should be understood that these embodiments are only used to illustrate the present invention and are not intended to limit the scope of the present invention, after having read the present invention, those skilled in the art will understand various aspects of the present invention Modifications in equivalent forms all fall within the scope defined by the appended claims of this application.

[0040] Such as figure 1 As shown, the embodiment of the present invention discloses a method for automatic detection of floating objects on the water surface for urban river supervision, which mainly includes the following steps:

[0041] Step 1. Automatic extraction of image data sets based on adaptive contrast enhancement; in this step, images are obtained from the water surface monitoring video stream and image enhancement is performed based on adaptive contrast,...