Canal lining damage image recognition method based on unmanned aerial vehicle inspection
An image recognition and unmanned aerial vehicle technology, applied in image enhancement, image analysis, image data processing, etc., can solve problems such as backward detection methods and detection deviations, and achieve the effect of unmanned and rapid detection
Active Publication Date: 2019-10-25
CHINA INST OF WATER RESOURCES & HYDROPOWER RES
View PDF10 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0005] The technical problem solved by the present invention is: the existing channel damage detection method is relatively backward, and there is a certain degree of deviation in the detection, thereby providing a channel lining damage image recognition method based on drone inspection
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0042] The camera carried by the UAV is used to fly at a certain height and viewing angle, and the video information is collected from the lining on both sides of the channel along the axis of the channel with a certain starting point as the reference. Framing the video to obtain independent continuous image information, such as image 3 As shown, the image reflects the order of the video taken by the UAV and the actual information of the river, and then the track coordinate information recorded by the UAV during flight is combined with the time information and matched with the image information, and the location information of the channel can be obtained .
[0043] For the acquired channel image, through dynamic double-window Otsu binarization processing, and then a series of mechanical morphological processing based on structural elements such as expansion, corrosion, and gap filling, to distinguish the lining part of the channel from the non-lining part, and the channel is ...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a canal lining damage image recognition method based on unmanned aerial vehicle inspection, and belongs to the technical field of road lining damage detection. According to theinvention, based on a double-window Otsu thresholding method, binarization classification is carried out on a canal lining part and a non-lining part in an image shot by an unmanned aerial vehicle; canny edge detection and a series of methods such as the maximum communication threshold and the minimum external moment are adopted to obtain the contour of the channel in the image, and then the damaged part and the damaged proportion of the channel lining are obtained. According to the method, damage condition research based on the unmanned aerial vehicle technology is conducted on a certain diversion engineering channel, the damage condition of the canal lining is obtained, consumed time is short, operation is convenient and fast, and effectiveness is high.
Description
technical field [0001] The invention relates to the technical field of channel lining damage detection, in particular to an image recognition method for channel lining damage based on unmanned aerial vehicle inspection. Background technique [0002] As an important water transmission and distribution structure, the channel is widely used in practical engineering, but when its working environment changes, it will face frost heave damage and other types of damage. Due to the long channel lines and wide distribution range, affected by traffic conditions and climate conditions, it is difficult to detect damage in a timely and accurate manner through traditional manual on-site inspections. In addition, during manual inspection, the inspectors have relatively large subjective factors in judging whether damage occurs and the degree of damage, and there may be certain deviations in judging the damage. Therefore, it is necessary to use some modern means such as drones, cameras and o...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More IPC IPC(8): G06T7/00G06T7/11G06T7/13G06T7/136G06T7/62G06T5/30G06T5/00
CPCG06T7/0002G06T5/30G06T7/13G06T7/136G06T7/11G06T7/62G06T2207/10016G06T2207/30108G06T5/70
Inventor 于沭温彦锋马金龙苏安双王国志张国英邓刚张守杰李兆宇张延亿王宇边京红
Owner CHINA INST OF WATER RESOURCES & HYDROPOWER RES