Search

CN-120676242-B - Method, device and equipment for detecting abnormal information in mine

CN120676242BCN 120676242 BCN120676242 BCN 120676242BCN-120676242-B

Abstract

The embodiment of the specification discloses a method, a device and equipment for detecting abnormal information in a mine, wherein the method can comprise the steps of obtaining a living body detection result in a preset area in the mine, starting image acquisition equipment in the preset area if the living body detection result indicates that a target living body exists in the preset area, obtaining a target image which is acquired by the image acquisition equipment and contains the target living body, inputting the target image into an abnormal detection model to obtain an abnormal detection result which is output by the abnormal detection model, and detecting whether the abnormal information exists in the target image or not by the abnormal detection model, wherein the abnormal information comprises illegal behaviors of the target living body in the target image. Based on the scheme of the invention, the abnormal condition in the mine can be automatically and efficiently detected.

Inventors

  • LIU KUN
  • DU JIANFEI
  • LIU XUGUANG

Assignees

  • 内蒙古伊泰信息技术有限公司

Dates

Publication Date
20260508
Application Date
20250529

Claims (7)

  1. 1. A method of detecting anomaly information in a mine, comprising: acquiring a living body detection result in a preset area in a mine; if the living body detection result indicates that a target living body exists in the preset area, starting image acquisition equipment in the preset area; Acquiring a target image containing the target living body acquired by the image acquisition equipment; The method comprises the steps of inputting a target image into an anomaly detection model to obtain an anomaly detection result output by the anomaly detection model, wherein the anomaly detection model is used for detecting whether anomaly information exists in the target image, the anomaly information comprises illegal behaviors of a target living body in the target image, the anomaly detection model is obtained by training a neural network model through training data, the training data comprises images with anomaly information and corresponding anomaly information labels, the anomaly information labels are used for indicating the types of the anomaly information and the anomaly information in the images, and the types of the anomaly information comprise non-wearing safety helmets, non-wearing work clothes, non-carrying miner lamps, mine smoking, illegal heating equipment, overhead operation, illegal sitting on a conveyor belt or illegal passing through guardrails; If the abnormal detection result indicates that the target image is an image with the area ratio of the blocked area exceeding a preset threshold value, acquiring first video data acquired by the image acquisition equipment in a target time period aiming at the preset area, wherein the ending time of the target time period is the current time; Generating third alarm information based on the first video data, wherein the third alarm information comprises at least one of equipment number information of the image acquisition equipment, area position information of the image acquisition equipment and the first video data; And sending the third alarm information to a terminal of a mine manager.
  2. 2. The method according to claim 1, wherein the acquiring the target image including the target living body acquired by the image acquisition apparatus specifically includes: and acquiring multi-frame video frame data which are acquired by a camera and contain the target living body.
  3. 3. The method of claim 2, further comprising, after the acquiring the multi-frame video frame data including the target living body acquired by the camera: performing data filtering on the multi-frame video frame data to obtain target video frame data meeting the preset quality requirement; Inputting the target image into an anomaly detection model to obtain an anomaly detection result output by the anomaly detection model, wherein the anomaly detection result specifically comprises: Inputting the target video frame data into an anomaly detection model to obtain an anomaly detection result output by the anomaly detection model.
  4. 4. The method of claim 1, wherein the anomaly detection result includes type information of anomaly information, the type information of anomaly information includes specific offence information, and the step of inputting the target image into an anomaly detection model to obtain an anomaly detection result output by the anomaly detection model further includes: Generating alarm information if the abnormal detection result indicates that abnormal information exists in the target image, wherein the alarm information comprises at least one of area position information, alarm time point information, type information of the abnormal information, identity information of offenders and processing suggestion information of abnormal conditions; And sending the alarm information to a terminal of a mine manager so that the mine manager can process abnormal conditions in the mine based on the alarm information.
  5. 5. The method of claim 1, wherein the inputting the target image into the anomaly detection model to obtain the anomaly detection result output by the anomaly detection model further comprises: if the abnormal detection result shows that the target living body in the target image has illegal behaviors, the face recognition model is utilized to determine the personnel identity information of the target living body based on a personnel face feature database, and the personnel face feature database stores personnel face feature data of personnel allowed to go into the well.
  6. 6. An apparatus for detecting anomaly information in a mine, comprising: The first acquisition module is used for acquiring a living body detection result in a preset area in the mine; the device starting module is used for starting the image acquisition device in the preset area if the living body detection result indicates that a target living body exists in the preset area; The second acquisition module is used for acquiring the target image containing the target living body acquired by the image acquisition equipment; The system comprises an anomaly detection module, a training data processing module, an anomaly detection module and a control module, wherein the anomaly detection module is used for inputting a target image into the anomaly detection module to obtain an anomaly detection result output by the anomaly detection module, the anomaly detection module is used for detecting whether anomaly information exists in the target image, the anomaly information comprises the target living body in the target image and a violation behavior, the anomaly detection module is obtained by training a neural network model through training data, the training data comprises an image with anomaly information and a corresponding anomaly information label, the anomaly information label is used for indicating the presence of the anomaly information and the type of the anomaly information in the image, and the type of the anomaly information comprises a non-wearing safety helmet, a non-wearing working garment, a non-carrying miner lamp, mine smoking, a violation heating device, an empty-roof operation, a violation sitting on a conveyor belt or a violation passing guardrail; The first video data acquisition module is used for acquiring first video data acquired by the image acquisition equipment in a target time period aiming at a preset area if the abnormal detection result indicates that the target image is an image with the area occupation ratio of the blocked area exceeding a preset threshold value; The third alarm information generation module is used for generating third alarm information based on the first video data, wherein the third alarm information comprises at least one of equipment number information of the image acquisition equipment, area position information of the image acquisition equipment and the first video data; and the third alarm information sending module is used for sending the third alarm information to a terminal of a mine manager.
  7. 7. An apparatus for detecting anomaly information in a mine, comprising: At least one processor, and A memory communicatively coupled to the at least one processor, wherein, The memory stores instructions executable by the at least one processor, the instructions are executable by the at least one processor to enable the at least one processor to: acquiring a living body detection result in a preset area in a mine; if the living body detection result indicates that a target living body exists in the preset area, starting image acquisition equipment in the preset area; Acquiring a target image containing the target living body acquired by the image acquisition equipment; The method comprises the steps of inputting a target image into an anomaly detection model to obtain an anomaly detection result output by the anomaly detection model, wherein the anomaly detection model is used for detecting whether anomaly information exists in the target image, the anomaly information comprises illegal behaviors of a target living body in the target image, the anomaly detection model is obtained by training a neural network model through training data, the training data comprises images with anomaly information and corresponding anomaly information labels, the anomaly information labels are used for indicating the types of the anomaly information and the anomaly information in the images, and the types of the anomaly information comprise non-wearing safety helmets, non-wearing work clothes, non-carrying miner lamps, mine smoking, illegal heating equipment, overhead operation, illegal sitting on a conveyor belt or illegal passing through guardrails; If the abnormal detection result indicates that the target image is an image with the area ratio of the blocked area exceeding a preset threshold value, acquiring first video data acquired by the image acquisition equipment in a target time period aiming at the preset area, wherein the ending time of the target time period is the current time; Generating third alarm information based on the first video data, wherein the third alarm information comprises at least one of equipment number information of the image acquisition equipment, area position information of the image acquisition equipment and the first video data; And sending the third alarm information to a terminal of a mine manager.

Description

Method, device and equipment for detecting abnormal information in mine Technical Field The present application relates to the field of information detection technologies, and in particular, to a method, an apparatus, and a device for detecting abnormal information in a mine. Background The construction of the underground mine construction site has the characteristics of complex geological conditions, large construction difficulty, multiple disaster types, wide distribution range, numerous hidden dangers such as unsafe behaviors of people, unsafe states of objects and the like. The environment under the mine is complex, people are difficult to keep alert for a long time due to visual fatigue, security officers or equipment operators cannot get up, and illegal operations cannot be supervised in time. Therefore, intelligent monitoring equipment is needed to replace human eyes, abnormal conditions are automatically found, an alarm is formed, and on-site personnel and supervisory personnel are timely reminded. In view of this, it is desirable to provide a solution that can automatically and efficiently detect abnormal information in a mine. Disclosure of Invention In view of the above, the embodiments of the present application provide a method, an apparatus, and a device for detecting abnormal information in a mine, so as to provide a scheme capable of automatically and efficiently detecting abnormal information in a mine. In order to solve the above technical problems, an embodiment of the present disclosure provides a method for detecting abnormal information in a mine, including: acquiring a living body detection result in a preset area in a mine; if the living body detection result indicates that a target living body exists in the preset area, starting image acquisition equipment in the preset area; Acquiring a target image containing the target living body acquired by the image acquisition equipment; the target image is input into an anomaly detection model to obtain an anomaly detection result output by the anomaly detection model, the anomaly detection model is used for detecting whether anomaly information exists in the target image or not, and the anomaly information comprises the illegal behaviors of the target living body in the target image. The embodiment of the specification also provides a device for detecting abnormal information in a mine, which comprises: The first acquisition module is used for acquiring a living body detection result in a preset area in the mine; the device starting module is used for starting the image acquisition device in the preset area if the living body detection result indicates that a target living body exists in the preset area; The second acquisition module is used for acquiring the target image containing the target living body acquired by the image acquisition equipment; The abnormality detection module is used for inputting the target image into an abnormality detection model to obtain an abnormality detection result output by the abnormality detection model, wherein the abnormality detection model is used for detecting whether abnormality information exists in the target image or not, and the abnormality information comprises the illegal behaviors of the target living body in the target image. The embodiment of the specification also provides equipment for detecting abnormal information in a mine, which comprises: At least one processor, and A memory communicatively coupled to the at least one processor, wherein, The memory stores instructions executable by the at least one processor, the instructions are executable by the at least one processor to enable the at least one processor to: acquiring a living body detection result in a preset area in a mine; if the living body detection result indicates that a target living body exists in the preset area, starting image acquisition equipment in the preset area; Acquiring a target image containing the target living body acquired by the image acquisition equipment; the target image is input into an anomaly detection model to obtain an anomaly detection result output by the anomaly detection model, the anomaly detection model is used for detecting whether anomaly information exists in the target image or not, and the anomaly information comprises the illegal behaviors of the target living body in the target image. At least one embodiment provided in this specification enables the following benefits: In the embodiment of the specification, after a living body detection result in a preset area in a mine is obtained, if the living body detection result indicates that a target living body exists in the preset area, an image acquisition device in the preset area can be started, a target image which is acquired by the image acquisition device and contains the target living body is obtained, and finally the target image can be input into an anomaly detection model to obtain an anomaly detection result output by the anomaly d