Unmanned aerial vehicle embankment piping patrol system and method based on deep learning
A technology of deep learning and unmanned aerial vehicles, applied in the direction of neural learning methods, control/regulation systems, mechanical equipment, etc., can solve the problems of unusable polder areas, save labor costs, relieve pressure on dike patrols, and reduce safety risks Effect
Pending Publication Date: 2022-05-27
NAT UNIV OF DEFENSE TECH
View PDF0 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
This method also cannot be used in polder areas with fast water flow and high water level during flood season
[0007] Existing piping detection is basically on the side of the water inlet, and can only be carried out under relatively stable water conditions
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
[0041] To make the object, technical solution and advantages of embodiments of the present invention more clear, the following will be combined with the accompanying drawings in the embodiments of the present invention, the technical solutions in the embodiments of the present invention are clearly and completely described, obviously, the embodiments described are part of the embodiments of the present invention, not all embodiments.
[0042] as Figure 4 As shown in the present embodiment, a UAV polder surge patrol system based on deep learning, comprising a UAV platform, an airborne visible light and infrared camera, an image transmission system, a remote control, a video capture card, a ground station, a deep learning pipe surge detection model.
[0043] The UAV platform is used for overload cameras and image transmission equipment to achieve cruising flight along the polder;
[0044] The airborne visible camera, to achieve the capture of visible light images of the polder area ...
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 an unmanned aerial vehicle embankment piping patrol system and method based on deep learning, and the system comprises an unmanned aerial vehicle platform which is used for overloading a visible light camera, an infrared camera and an image transmission system, and achieves the cruising flight of an embankment along the line. The visible light camera is used for shooting a visible light image of the embankment region and outputting a visible light video stream; the infrared camera is used for shooting an infrared image of the embankment region and outputting an infrared video stream; the image transmission system is used for receiving videos of the visible light camera and the infrared camera and sending video streams to the remote controller; the remote controller controls the unmanned aerial vehicle platform and outputs an unmanned aerial vehicle image transmission video stream to the ground station; the ground station obtains an unmanned aerial vehicle image transmission video stream sent by the remote controller, piping is detected in real time in the collected visible light or infrared image through a deep learning piping detection model, and target information is prompted through a graph or voice. The method effectively relieves the manual embankment patrol pressure of the flood fighting front-line, effectively reduces the safety risk of embankment patrol personnel, and improves the safety of the embankment patrol personnel. And labor cost is saved.
Description
Technical field [0001] The present invention relates to the technical field of polder pipe surge inspection, specifically to a UAV Polder surge patrol system and method based on deep learning. Background [0002] There are many types and large numbers of domestic flood control levees, and a considerable number of polders along rivers, rivers and lakes are built using earth and stone, which is very prone to pipe surge dangers during the flood season, which brings huge hidden dangers to the safety of people's lives and property in the polder area Figure 1 as shown. [0003] At present, the instruments used to detect pipe surges are mainly "popular dike pipe surge leakage detection system". The device is equipped on patrol boats to detect the inlet of pipe surges and is only suitable for static waters; it is not realistic to patrol on a boat in a flood with turbulent currents, and high-speed water flow will introduce errors, resulting in instrument failure. [0004] At present, the ...
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 Patent Type & AuthorityApplications(China)
IPC IPC(8): G05D1/10G06K9/62G06N3/04G06N3/08G06V10/80G06V10/82
CPCG05D1/101G06N3/08G06N3/045G06F18/253Y02T10/40
Inventor朱斌解博朱耀轩陈熠冷吴西张峻洁李西
OwnerNAT UNIV OF DEFENSE TECH