CN-115810176-B - Area monitoring method, device, electronic equipment and storage medium

CN115810176BCN 115810176 BCN115810176 BCN 115810176BCN-115810176-B

Abstract

The application provides a regional monitoring method, a regional monitoring device, electronic equipment and a storage medium, wherein regional monitoring comprises the steps of acquiring at least two first detection images acquired by a camera in the flight process of an unmanned aerial vehicle; and generating first alarm information when the target object detection result indicates that the target object is detected from the first detection images. According to the application, the camera is carried on the unmanned aerial vehicle for monitoring, so that indoor and outdoor monitoring objects can be monitored simultaneously, the inspection frequency can be improved, in addition, the collected images are detected, the outdoor monitoring objects can be monitored well, prompt can be sent to related management staff in time, and the safety is improved.

Inventors

YAN TONG
XIA YAN
YOU ZHONGJUN
XIE ZHIHU

Assignees

航天信息股份有限公司

Dates

Publication Date: 20260508
Application Date: 20221221

Claims (7)

1. A method for monitoring a region, comprising: acquiring at least two first detection images acquired by a camera in the flight process of the unmanned aerial vehicle; The method comprises the steps of carrying out target object detection on at least two first detection images to obtain target object detection results, specifically, carrying out target object positioning on each first detection image, extracting target object images according to the positioned target objects, respectively extracting images of knees and feet from each target object image according to the knees and feet of a preset person as key points, judging whether the person moves by comparing whether the knees in each image are bent and whether the feet are moving, and judging whether the person is a living body according to the result and taking the result as the target object detection result; Generating first alarm information when the target object detection result indicates that a target object is detected from the first detection image; The method comprises the steps of controlling the unmanned aerial vehicle to fly for at least one time according to preset monitoring points and monitoring routes, acquiring at least two second detection images through cameras in the process that the unmanned aerial vehicle flies along the monitoring routes, carrying out volume measurement on objects stored in the monitoring points according to the second detection images for each second detection image to obtain corresponding measurement data, and obtaining volume change data of the objects stored in the monitoring points by comparing the measurement data; When the volume change data meets a preset second alarm condition, the second alarm information is sent out, wherein the second alarm information comprises operation information for the object stored in the monitoring point, the operation information at least comprises the in-out warehouse weight of the object, the expected volume change is calculated based on the operation information and the physical attribute of the object, the volume change data actually measured by an unmanned aerial vehicle image is compared with the expected volume change, and when the two are different, the second alarm information is generated; the method further comprises the steps of performing angle correction on at least two images acquired by the camera according to a pre-acquired standard image, performing data enhancement on the images subjected to angle correction, and obtaining a first detection image; The method comprises the steps of acquiring video data acquired through a camera in the flight process of an unmanned aerial vehicle, uploading the video data to a user side, wherein the video data are used for enabling the user side to display, responding to voice information sent by the user side, and playing the voice information through the unmanned aerial vehicle.
2. The method according to claim 1, wherein performing object detection on the at least two first detection images to obtain object detection results includes: performing target object positioning on each first detection image, and extracting a target object image according to the positioned target object; and respectively extracting key features from each target object image according to preset key points, and comparing the key features to obtain a target object detection result.
3. The method according to claim 2, wherein the method further comprises: And scaling the pixel value of the pixel point in the image acquired by the camera to the interval of 0-1 in equal proportion, and determining the image with the scaled pixel value as a first detection image.
4. An area monitoring apparatus, comprising: The acquisition module is used for acquiring at least two first detection images acquired by a camera in the flight process of the unmanned aerial vehicle; The detection module is used for detecting the target object of the at least two first detection images to obtain a target object detection result; the method is specifically used for carrying out target object positioning on each first detection image and extracting target object images according to the positioned target objects, respectively extracting images of knees and feet from each target object image according to the preset knees and feet of a person as key points, judging whether the person moves by comparing whether the knees in each image are bent and whether the feet are moving, judging whether the person is a living body according to the knees and feet of the person, and taking the knees and feet of the person as target object detection results; an alarm module for generating first alarm information when the target object detection result indicates that the target object is detected from the first detection image The area monitoring device is also used for controlling the unmanned aerial vehicle to fly at least once according to preset monitoring points and monitoring routes, acquiring at least two second detection images by a camera in the process of flying the unmanned aerial vehicle along the monitoring routes, measuring and calculating the volume of an object stored in the monitoring points according to the second detection images aiming at each second detection image to obtain corresponding measuring and calculating data, and obtaining the volume change data of the object stored in the monitoring points by comparing the measuring and calculating data; When the volume change data meets a preset second alarm condition, the second alarm information is sent out, wherein the second alarm information comprises operation information for the object stored in the monitoring point, the operation information at least comprises the in-out warehouse weight of the object, the expected volume change is calculated based on the operation information and the physical attribute of the object, the volume change data actually measured by an unmanned aerial vehicle image is compared with the expected volume change, and when the two are different, the second alarm information is generated; The acquisition module is also used for carrying out angle correction on at least two images acquired by the camera according to a pre-acquired standard image, and carrying out data enhancement on the images subjected to the angle correction to obtain a first detection image; the area monitoring device is further used for acquiring video data acquired through a camera in the flight process of the unmanned aerial vehicle, uploading the video data to a user side, wherein the video data are used for enabling the user side to display, and responding to voice information sent by the user side, playing the voice information through the unmanned aerial vehicle.
5. An electronic device includes a processor, a communication interface, a memory, and a communication bus through which the processor, the memory, and the communication interface communicate with each other; the memory is configured to store at least one executable instruction, where the executable instruction causes the processor to perform operations corresponding to the area monitoring method according to any one of claims 1-3.
6. A computer storage medium having stored thereon a computer program which when executed by a processor implements the area monitoring method as claimed in any one of claims 1 to 3.
7. A computer program product comprising computer instructions that instruct a computing device to perform operations corresponding to the area monitoring method of any one of claims 1-3.

Description

Area monitoring method, device, electronic equipment and storage medium Technical Field The embodiment of the application relates to the field of equipment remote monitoring and management, in particular to a regional monitoring method and device, electronic equipment and a storage medium. Background The grain problem is one of urgent problems which are brought into the spotlight at present, and the grain country can stably and healthily develop industry, national defense, service industry, scientific cultural industry and the like. Grain problems are not only economic and civil but also development and safety issues. Meanwhile, due to the development of modern information technology, intelligent monitoring of the granary or grain pile is required. At present, the monitoring mode of the granary or grain pile is realized mainly by manually inspecting and assisting devices such as an alarm and the like. However, because the frequency of manual inspection is low, and because the alarm can only be placed indoors, the alarm can not have a good monitoring effect on grain piles placed outdoors. Disclosure of Invention The embodiment of the invention provides a region monitoring method, a device, electronic equipment and a storage medium, which are used for solving or relieving the technical problems in the prior art. The invention adopts the technical scheme that: In a first aspect, an embodiment of the present application provides a method for monitoring a region, including: the method comprises the steps of acquiring at least two first detection images acquired through a camera in the flight process of the unmanned aerial vehicle, detecting target objects of the at least two first detection images to obtain target object detection results, and generating first alarm information when the target object detection results indicate that the target objects are detected from the first detection images. Optionally, in one embodiment, the area monitoring method further includes controlling the unmanned aerial vehicle to fly at least once according to preset monitoring points and monitoring routes, acquiring at least two second detection images through cameras on the monitoring points in the process that the unmanned aerial vehicle flies along the monitoring routes, performing volume measurement on objects stored in the monitoring points according to the second detection images for each second detection image to obtain corresponding measurement data, obtaining volume change data of the objects stored in the monitoring points by comparing the measurement data, and sending out second alarm information when the volume change data meets preset second alarm conditions. Optionally, in one embodiment, the performing object detection on the at least two first detection images to obtain an object detection result includes performing object positioning on each first detection image, extracting an object image according to the positioned object, extracting key features from each object image according to preset key points, and comparing each key feature to obtain an object detection result. Optionally, in one embodiment, the area monitoring method further includes performing angle correction on at least two images acquired by the camera according to a pre-acquired standard image, and performing data enhancement on the images subjected to angle correction to obtain a first detection image. Optionally, in one embodiment, the area monitoring method further includes scaling the pixel value of the pixel point in the image acquired by the camera to be within a 0-1 interval in equal proportion, and determining the image with the scaled pixel value as the first detection image. Optionally, in one embodiment, the area monitoring method further includes acquiring video data acquired through a camera during the flight of the unmanned aerial vehicle, and uploading the video data to a user terminal, wherein the video data is used for enabling the user terminal to display; and responding to the voice information sent by the user side, and playing the voice information through the unmanned aerial vehicle. In a second aspect, an embodiment of the application provides an area monitoring device, which comprises an acquisition module, a detection module and an alarm module, wherein the acquisition module is used for acquiring at least two first detection images acquired by a camera in the flight process of an unmanned aerial vehicle, the detection module is used for detecting target objects of the at least two first detection images to obtain target object detection results, and the alarm module is used for generating first alarm information when the target object detection results indicate that a target object is detected from the first detection images. In a third aspect, an embodiment of the present application provides an electronic device, on which a computer program is stored, which when executed by a processor implements the area monitoring met