Bucket tooth anomaly detection method and device, electronic equipment and computer program product

Abstract

The invention is suitable for the technical field of computers, and provides a bucket tooth anomaly detection method and device, electronic equipment and a computer program product. The method comprises the following steps: aiming at the abnormity of the same type of bucket teeth, storing N first flag bits of the bucket teeth at all positions on a bucket in a corresponding first queue, and storing N second flag bits of the bucket teeth at all positions in a corresponding second queue; the first number and the second number of the bucket teeth at all the positions are counted; if target bucket teeth exist in the bucket teeth at all the positions, it is determined that an abnormal event exists in the target bucket teeth, the target bucket teeth are bucket teeth of which the first number and the second number are both larger than a first threshold value, and the abnormal event indicates the possibility that the target bucket teeth have the bucket tooth abnormity. According to the invention, the accuracy and robustness of bucket tooth anomaly detection can be improved.

Description

Technical Field

[0001] This application belongs to the field of computer technology, and particularly relates to a method, device, electronic device, and computer program product for detecting abnormal bucket teeth. Background Art

[0002] The detection of abnormal conditions such as the detachment or fracture of the bucket teeth of an excavator usually relies on computer vision technology. For example, methods such as edge detection, color segmentation, and shape analysis are used to detect whether the bucket teeth are abnormal. However, the accuracy and robustness of the detection of abnormal bucket teeth still need to be improved. Summary of the Invention

[0003] Embodiments of this application provide a method, device, electronic device, and computer program product for detecting abnormal bucket teeth, which can improve the accuracy and robustness of the detection of abnormal bucket teeth.

[0004] In a first aspect, embodiments of this application provide a method for detecting abnormal bucket teeth, including:

[0005] For the same type of abnormal bucket teeth, store the N first flag bits of the bucket teeth at each position on the bucket in the corresponding first queue, and store the N second flag bits of the bucket teeth at each position in the corresponding second queue; the N first flag bits represent whether the bucket teeth at the corresponding positions have the abnormal bucket teeth at N first moments, and the bucket is in a vertically upward state at the N first moments; the N second flag bits represent whether the bucket teeth at the corresponding positions have the abnormal bucket teeth at N second moments, and the bucket is in a vertically downward state at the N second moments; N is an integer greater than 1;

[0006] Count the first quantity and the second quantity of the bucket teeth at each position; the first quantity is the number of the first preset values in the first queue of the bucket teeth at the corresponding position, and the first flag bit being the first preset value represents that the bucket teeth at the corresponding position have the abnormal bucket teeth at the corresponding first moment; the second quantity is the number of the second preset values in the second queue of the bucket teeth at the corresponding position, and the second flag bit being the second preset value represents that the bucket teeth at the corresponding position have the abnormal bucket teeth at the corresponding second moment;

[0007] If there is a target bucket tooth among the bucket teeth at each position, determine that there is an abnormal event for the target bucket tooth, where the target bucket tooth is a bucket tooth for which both the first quantity and the second quantity are greater than a first threshold, and the abnormal event indicates the possibility that the target bucket tooth has the abnormal bucket teeth.

[0008] In an embodiment of the present application, for the same type of bucket tooth abnormality, N first flag bits of the bucket teeth at each position on the bucket can be stored in the corresponding first queue, and N second flag bits of the bucket teeth at each position can be stored in the corresponding second queue. Then, based on the first queue and the second queue, the first quantity and the second quantity of the bucket teeth at each position are statistically calculated. If there are bucket teeth at each position whose first quantity and second quantity are both greater than a first threshold, then it can be determined that the bucket tooth is a target bucket tooth, and there is an abnormal event for the target bucket tooth. The abnormal event indicates the possibility of the bucket tooth having a bucket tooth abnormality. This solution can effectively reduce accidental misjudgments in single-frame detection by maintaining queues in different states (i.e., the first queue when the bucket is in the vertically upward state and the second queue when the bucket is in the vertically downward state). By statistically calculating the bucket tooth abnormality conditions of the bucket teeth at each position in multiple moments through the queues and further judging the bucket tooth abnormality conditions based on the set first threshold, it can avoid noise or error interference during single-frame detection and improve the accuracy and robustness of bucket tooth abnormality detection.

[0009] In a second aspect, an embodiment of the present application provides a bucket tooth abnormality detection device, including:

[0010] A flag bit storage module, configured to, for the same type of bucket tooth abnormality, store N first flag bits of the bucket teeth at each position on the bucket in the corresponding first queue, and store N second flag bits of the bucket teeth at each position in the corresponding second queue; the N first flag bits represent whether the bucket tooth at the corresponding position has the bucket tooth abnormality at N first moments, and the bucket is in the vertically upward state at the N first moments; the N second flag bits represent whether the bucket tooth at the corresponding position has the bucket tooth abnormality at N second moments, and the bucket is in the vertically downward state at the N second moments; N is an integer greater than 1;

[0011] A quantity statistics module, configured to calculate the first quantity and the second quantity of the bucket teeth at each position; the first quantity is the quantity of a first preset value in the first queue of the bucket tooth at the corresponding position, and the first flag bit being the first preset value represents that the bucket tooth at the corresponding position has the bucket tooth abnormality at the corresponding first moment; the second quantity is the quantity of a second preset value in the second queue of the bucket tooth at the corresponding position, and the second flag bit being the second preset value represents that the bucket tooth at the corresponding position has the bucket tooth abnormality at the corresponding second moment;

[0012] An abnormality determination module, configured to, if there is a target bucket tooth among the bucket teeth at each position, determine that there is an abnormal event for the target bucket tooth, where the target bucket tooth is a bucket tooth whose first quantity and second quantity are both greater than a first threshold, and the abnormal event indicates the possibility of the target bucket tooth having the bucket tooth abnormality.

[0013] In a third aspect, an embodiment of the present application provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the electronic device implements the method described in the first aspect above.

[0014] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing a computer program, and when the computer program is executed by a computer, the method described in the first aspect above is implemented.

[0015] In a fifth aspect, an embodiment of the present application provides a computer program product including a computer program, and when the computer program is run, the method described in the first aspect above is executed.

[0016] It can be understood that the beneficial effects of the second to fifth aspects above can refer to the relevant descriptions in the first aspect above, and will not be elaborated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings in the following description are only some embodiments of the present application, and those of ordinary skill in the art can also obtain other drawings based on these drawings without creative efforts.

[0018] Figure 1 is a flowchart of the tooth abnormality detection method provided by the embodiment of the present application;

[0019] Figure 2 is a structural diagram of the tooth abnormality detection device provided by the embodiment of the present application;

[0020] Figure 3 is a structural diagram of the electronic device provided by the embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] In the following description, specific details such as specific system structures and technologies are proposed for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present application. However, those skilled in the art should clearly understand that the present application can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present application.

[0022] It should be understood that, as used in the specification of this application and the appended claims, the term "comprising" indicates the presence of the described features, integers, steps, operations, elements, and / or components, but does not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and / or their groups.

[0023] It should also be understood that the term "and / or" as used in the specification of this application and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0024] As used in the specification of this application and the appended claims, the term "if" may be construed, depending on the context, as "when" or "once" or "in response to determining" or "in response to detecting". Similarly, the phrase "if determined" or "if [the described condition or event] is detected" may be construed, depending on the context, as meaning "once determined" or "in response to determining" or "once [the described condition or event] is detected" or "in response to detecting [the described condition or event]".

[0025] In addition, in the description of the specification of this application and the appended claims, the terms "first", "second", "third", etc. are used only for distinguishing descriptions and should not be construed as indicating or implying relative importance.

[0026] Reference to "one embodiment" or "some embodiments" or the like described in the specification of this application means that a specific feature, structure, or characteristic described in connection with that embodiment is included in one or more embodiments of this application. Thus, statements such as "in one embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments", etc. that appear in different places in this specification do not necessarily all refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "comprising", "including", "having", and their variants all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0027] The abnormal tooth detection method provided by the embodiments of this application can be applied to electronic devices such as mobile phones, tablet computers, laptop computers, ultra-mobile personal computers (UMPCs), netbooks, personal digital assistants (PDAs), etc., and the embodiments of this application do not impose any restrictions on the specific types of electronic devices.

[0028] Please refer to Figure 1 , Figure 1The flowchart of the bucket tooth anomaly detection method provided by the embodiment of the present application is shown. This method is applied to an electronic device. By way of example and not limitation, the method includes the following steps:

[0029] Step 101, for the same type of bucket tooth anomaly, store the N first flag bits of the bucket teeth at each position on the bucket in the corresponding first queue, and store the N second flag bits of the bucket teeth at each position in the corresponding second queue.

[0030] Among them, for the same type of bucket tooth anomaly, each bucket tooth at a position corresponds to a first queue and a second queue. Each first queue includes the N first flag bits of the bucket tooth at the corresponding position, and each second queue includes the N second flag bits of the bucket tooth at the corresponding position.

[0031] By way of example and not limitation, there are 5 bucket teeth on the bucket. According to the positions of the 5 bucket teeth on the bucket, the 5 bucket teeth can be called the bucket tooth at the first position, the bucket tooth at the second position, the bucket tooth at the third position, the bucket tooth at the fourth position, and the bucket tooth at the fifth position in sequence from right to left or from left to right. Taking the bucket tooth at the first position as an example, the bucket tooth at the first position corresponds to a first queue and a second queue. The first queue includes the N first flag bits of the bucket tooth at the first position, and the second queue includes the N second flag bits of the bucket tooth at the first position.

[0032] The N first flag bits represent whether there is a bucket tooth anomaly at the corresponding position of the bucket tooth at N first moments when the bucket is in a vertically upward state; the N second flag bits represent whether there is a bucket tooth anomaly at the corresponding position of the bucket tooth at N second moments when the bucket is in a vertically downward state; N is an integer greater than 1.

[0033] The types of bucket tooth anomalies include but are not limited to bucket tooth detachment anomalies or bucket tooth fracture anomalies.

[0034] For the bucket tooth detachment anomaly, by maintaining the first queue when the bucket is in a vertically upward state and the second queue when the bucket is in a vertically downward state, and the flag bits in the first queue and the second queue represent whether there is a bucket tooth detachment anomaly at the corresponding position of the bucket tooth at N moments when the bucket is in the corresponding state, it is possible to detect the possibility of bucket tooth detachment at each position on the bucket based on the first queue and the second queue. For the bucket tooth fracture anomaly, by maintaining the first queue when the bucket is in a vertically upward state and the second queue when the bucket is in a vertically downward state, and the flag bits in the first queue and the second queue represent whether there is a bucket tooth fracture anomaly at the corresponding position of the bucket tooth at N moments when the bucket is in the corresponding state, it is possible to detect the possibility of bucket tooth fracture at each position on the bucket based on the first queue and the second queue.

[0035] It should be noted that for the abnormal detachment and abnormal fracture of the bucket teeth, the value of N can be the same or different, and the present application does not limit this. For example, for the abnormal detachment of the bucket teeth, the value of N is 15; for the abnormal fracture of the bucket teeth, the value of N is 30.

[0036] In this embodiment, by maintaining multiple queues to record the detection results of the bucket teeth in different states respectively, it is possible to avoid accidental misjudgment of single-frame detection by accumulating and statistically analyzing the detection results at multiple moments, thereby improving the accuracy and stability of detection. Specifically, by detecting the state change of the bucket teeth at a certain position, accumulating this change at multiple moments, and comparing it with a preset first threshold to determine whether there is an abnormal event, the influence brought by environmental noise, false detection or missed detection can be significantly reduced, breaking through the limitation of being easily interfered by noise or abnormal frames in single-frame detection. Through the cumulative processing of the detection results at multiple moments, a more reliable detection and alarm mechanism is realized, reducing the false alarm rate in single-frame detection and enhancing the robustness of the abnormal detection of the bucket teeth.

[0037] In a possible implementation manner, storing the N first flag bits of the bucket teeth at each position on the bucket in the corresponding first queue and storing the N second flag bits of the bucket teeth at each position in the corresponding second queue includes:

[0038] Obtain the current frame of the bucket image and use the current frame of the bucket image as the alternative image;

[0039] Perform state recognition on the bucket in the alternative image;

[0040] If it is recognized that the bucket is in the target state, perform bucket tooth detection on the alternative image to obtain the bucket tooth detection result. Based on the bucket tooth detection result and the coordinate range of the bucket teeth at each position, determine the flag bits of the bucket teeth at each position at the corresponding moment, and store the flag bits at the corresponding moment in the corresponding queue. If the number of flag bits in the corresponding queue has not reached N, use the next frame of the bucket image of the alternative image as the alternative image, and return to execute the step of performing state recognition on the bucket in the alternative image and the subsequent steps until the number of flag bits in the corresponding queue reaches N;

[0041] Among them, the target state includes the vertically upward state and the vertically downward state; when the bucket is in the vertically upward state, the corresponding moment is the first moment, the flag bit at the corresponding moment is the first flag bit, and the corresponding queue is the first queue; when the bucket is in the vertically downward state, the corresponding moment is the second moment, the flag bit at the corresponding moment is the second flag bit, and the corresponding queue is the second queue.

[0042] During the abnormal detection of the bucket teeth, the image acquisition device can be used to collect the bucket images of the excavator in real time. When it is necessary to store the corresponding flag bits in the first queue and the second queue, the electronic device can store N first flag bits in the first queue and N second flag bits in the second queue based on the current frame bucket image and subsequent multiple frame bucket images collected by the image acquisition device. Among them, each frame of bucket image corresponds to a moment, and different frame bucket images correspond to different moments.

[0043] When the excavator is working, the bucket teeth can be better displayed when the bucket is in the vertically upward state and the vertically downward state, which is convenient for identifying whether there are abnormal bucket teeth at each position. Therefore, in this embodiment, when detecting abnormal bucket teeth, the posture of the bucket can be divided into three states, which are the vertically upward state, the vertically downward state, and other states. When the bucket is in the vertically upward state or the vertically downward state, further bucket tooth detection is performed. For other states (such as the side or the state with an offset angle), the bucket tooth detection is skipped, which can avoid performing bucket tooth detection in unnecessary states, reduce ineffective detection, avoid unnecessary calculations and misjudgments, improve the operation efficiency of the abnormal bucket tooth detection scheme, and reduce the resource consumption of the abnormal bucket tooth detection scheme.

[0044] In this embodiment, the bucket detection and the bucket tooth detection are processed separately. First, the state of the bucket (vertically upward state, vertically downward state, or other state) is identified, and then it is determined whether to perform bucket tooth detection according to the state of the bucket. Only when the bucket is in the vertically upward state or the vertically downward state, will the state of the bucket teeth be further detected, while for other postures, the bucket tooth detection is skipped. This step-by-step processing method avoids unnecessary computational burdens and improves the efficiency of abnormal bucket tooth detection at the same time.

[0045] In one embodiment, the electronic device can use the bucket detection model to identify the state of the bucket in the alternative image, and obtain the position coordinates of the bucket frame used to enclose the area where the bucket is located in the alternative image and the state of the bucket in the alternative image; if it is recognized that the state of the bucket in the alternative image is the vertically upward state or the vertically downward state, in order to reduce the computational amount of abnormal detection, the bucket sub-image containing only the bucket can be cropped from the alternative image based on the position coordinates of the bucket frame, and then the bucket sub-image is input into the bucket tooth detection model to realize the abnormal detection of the bucket teeth at each position.

[0046] When there are teeth on the bucket at various positions that are not broken, the tooth detection result includes at least one tooth coordinate and a tooth label corresponding to each tooth coordinate, and the tooth label indicates whether the tooth at the corresponding tooth coordinate has an abnormal detachment. By way of example and not limitation, the tooth label can be 0 or 1, where 0 indicates that the tooth is normal (i.e., there is no abnormal detachment), and 1 indicates that there is an abnormal detachment. In this embodiment, a deep learning model is used to detect and classify the teeth, and the states of the teeth are divided into two categories: normal teeth and abnormal detachment. The introduction of deep learning improves the detection accuracy and can effectively handle the problem of tooth state recognition in complex scenarios. By learning from a large amount of training data of teeth, the tooth detection model can accurately identify the detachment or fracture of the teeth, is applicable to tooth detection under different working conditions, and has stronger generalization ability. The introduction of the deep learning model improves the intelligence level and accuracy of tooth detection and can more accurately detect the abnormal state of the teeth.

[0047] On this basis, in a possible implementation manner, based on the tooth detection result and the coordinate range of the teeth at each position, the flag bit of the teeth at each position at the corresponding moment is determined, including:

[0048] For abnormal tooth detachment, if there is a first tooth among the teeth at each position, determine that the flag bit of the first tooth at the corresponding moment is a preset value indicating that there is an abnormal tooth detachment; the first tooth is a tooth whose coordinate range matches the tooth coordinate in the tooth detection result and the tooth label of this tooth coordinate indicates that there is an abnormal tooth detachment; if there is a second tooth among the teeth at each position, determine that the flag bit of the second tooth at the corresponding moment is a preset value indicating that there is no abnormal tooth detachment; the second tooth is a tooth whose coordinate range matches the tooth coordinate in the tooth detection result and the tooth label of this tooth coordinate indicates that there is no abnormal tooth detachment, or a tooth whose coordinate range does not match the tooth coordinate in the tooth detection result.

[0049] For abnormal tooth fracture, if there is a third tooth among the teeth at each position, determine that the flag bit of the third tooth at the corresponding moment is a preset value indicating that there is an abnormal tooth fracture; the third tooth is a tooth whose coordinate range does not match the tooth coordinate in the tooth detection result; if there is a fourth tooth among the teeth at each position, determine that the flag bit of the fourth tooth at the corresponding moment is a preset value indicating that there is no abnormal tooth fracture; the fourth tooth is a tooth whose coordinate range matches the tooth coordinate in the tooth detection result.

[0050] It should be noted that if the flag bit of the first tooth at the corresponding moment is the first flag bit, then the above preset value is the first preset value; if the flag bit of the first tooth at the corresponding moment is the second flag bit, then the above preset value is the second preset value.

[0051] In one embodiment, the electronic device may determine the width of the tooth area based on the abscissa in the position coordinates of the bucket frame, and based on the abscissa of the bucket frame and the width of the tooth area, may determine the coordinate range of the teeth at each position on the bucket.

[0052] Among them, the width of the tooth area is the area width of each tooth on the bucket. The above-mentioned position coordinates of the bucket frame may include the coordinates of the upper left corner vertex and the lower right corner vertex of the bucket frame. The electronic device subtracts the abscissa of the lower right corner vertex from the abscissa of the upper left corner vertex and then divides by the target value (the target value is the value obtained by subtracting 1 from the total number of teeth on the bucket), and the width of the tooth area can be obtained. The calculation formula is as follows:

[0053] d = (x 2 - x 1 ) / (n - 1)

[0054] Among them, d represents the width of the tooth area, x 2 and x 1 respectively represent the abscissa of the lower right corner vertex and the upper left corner vertex of the bucket frame, and n represents the total number of teeth. The coordinate ranges of the n teeth are successively (x 1 , x 1 + d), (x 1 + d, x 1 + 2d), (x 1 + 2d, x 1 + 3d), (x 1 + (n - 1)d, x 1 + nd).

[0055] In this embodiment, by dividing the tooth area, the coordinates of the bucket can be refined and segmented. Each tooth position corresponds to a specific area, ensuring the detection independence and accuracy of each tooth. Even when part of the bucket is blocked or there are other interferences, the tooth detection model can still accurately identify the fallen or broken teeth, effectively improving the detection accuracy, reducing the false detection caused by area crossing or interference, and enabling the state of each tooth to be more accurately identified.

[0056] Step 102, count the first quantity and the second quantity of the teeth at each position.

[0057] Among them, the first quantity is the number of the first preset value in the first queue of the teeth at the corresponding position, and the first flag bit is the first preset value indicating that there is an abnormality of the teeth at the corresponding position at the corresponding first moment; the second quantity is the number of the second preset value in the second queue of the teeth at the corresponding position, and the second flag bit is the second preset value indicating that there is an abnormality of the teeth at the corresponding position at the corresponding second moment.

[0058] Optionally, the first preset value and the second preset value described above may be the same or different, and the present application does not limit this. By way of example and not limitation, both the first preset value and the second preset value are true.

[0059] Step 103, if there is a target tooth among the teeth at each position, it is determined that an abnormal event exists for the target tooth.

[0060] Wherein, the target tooth is a tooth for which both the first quantity and the second quantity are greater than the first threshold, and the abnormal event indicates the possibility of tooth abnormality for the target tooth.

[0061] In one embodiment, if there is a tooth at each position for which the first quantity is less than or equal to the first threshold, or the second quantity is less than or equal to the first threshold, it can be determined that there is no abnormal event for this tooth, which may be a misjudgment caused by object occlusion.

[0062] In a possible implementation manner, after determining that an abnormal event exists for the target tooth, it further includes:

[0063] Updating the third flag bit of the target tooth to a third preset value, and clearing the first queue and the second queue of the target tooth. The third flag bit being the third preset value indicates that an abnormal event exists for the target tooth.

[0064] Determining that an abnormal event exists for the target tooth is one detection. Although this detection detects that an abnormal event exists for the target tooth, it may be a misjudgment caused by object occlusion during the working process of the excavator. Therefore, in order to determine whether this detection is a misjudgment, the third flag bit of the target tooth can be updated to the third preset value to trigger a secondary detection, and the first queue and the second queue of the target tooth are cleared to prepare for the secondary detection of the target tooth.

[0065] In a possible implementation manner, if the third flag bit of the target tooth is the third preset value, the implementation manner of the secondary detection for tooth abnormality and the target tooth includes:

[0066] Return to execute the step of storing the N first flag bits of the target tooth in the corresponding first queue and storing the N second flag bits of the target tooth in the corresponding second queue;

[0067] Count the first quantity and the second quantity of the target tooth;

[0068] If the first quantity of the target tooth is greater than the second threshold, or the second quantity of the target tooth is greater than the second threshold, an abnormal alarm for the target tooth is triggered.

[0069] In the secondary detection of the target bucket tooth, the first quantity and the second quantity of the target bucket tooth are statistically counted again. If the first quantity of the target bucket tooth counted again is greater than the second threshold, or the second quantity of the target bucket tooth counted again is greater than the second threshold, it can be determined that there is an abnormality in the target bucket tooth, and an abnormal alarm for the target bucket tooth is triggered to prompt the user that there is an abnormality in the target bucket tooth. Optionally, the electronic device can trigger the abnormal alarm for the target bucket tooth by means such as voice or pop-up window. The present application does not limit the triggering method of the abnormal alarm.

[0070] In this embodiment, the abnormal detection results of the bucket teeth in each frame of the bucket image are stored in a queue, and combined with the judgment of the flag bit, and a threshold is used to determine whether to trigger an abnormal alarm, which can avoid misjudgment caused by single-frame misdetection, improve the robustness of the bucket tooth abnormal detection, and can accurately distinguish the normal situation of the bucket teeth and the situation of the bucket teeth falling off or breaking.

[0071] In the detection process of the abnormal situation of the bucket teeth falling off and the abnormal situation of the bucket teeth breaking, the present application introduces a mechanism for setting dynamic thresholds. The number statistics of the flag bits in the queue in different states are compared with the thresholds to determine whether to trigger an abnormal alarm. By setting reasonable thresholds, the detection requirements in different working environments can be adapted, and the adaptability of the bucket tooth abnormal detection is improved. Through the setting of the second threshold, it can be ensured that the detection result will trigger an alarm only after meeting certain conditions, avoiding false alarms caused by individual accidental factors, enabling the bucket tooth abnormal detection to have better adaptability in different scenarios, and ensuring high accuracy and low false alarm rate in complex working environments.

[0072] The abnormal detection of the bucket teeth falling off and the abnormal detection of the bucket teeth breaking in this embodiment not only rely on the real-time detection results, but also combine dynamic thresholds (i.e., the first threshold, the second threshold, and the third threshold) and the third flag bit. In the detection process at multiple moments, by statistically counting the detection results at multiple moments and combining the third flag bit to judge the current alarm state. The setting of the dynamic threshold makes the alarm mechanism more flexible, while the third flag bit enhances the continuity and reliability of the alarm, preventing false alarms caused by short-term fluctuations or false detections. By combining the dynamic threshold and the third flag bit, the alarm state can be flexibly adjusted according to the detection results at different moments, improving the accuracy of the alarm and the adaptability of the bucket tooth abnormal detection.

[0073] In a possible implementation manner, after triggering the abnormal alarm for the target bucket tooth, it further includes:

[0074] Updating the third flag bit of the target bucket tooth to a fourth preset value, and clearing the first queue and the second queue of the target bucket tooth. The third flag bit being the fourth preset value indicates that there is no abnormal event for the target bucket tooth.

[0075] The electronic device updates the third flag bit of the target bucket tooth to a fourth preset value, indicating that there is no need to perform a secondary detection on the target bucket tooth. Since the bucket tooth detection of the excavator is continuously carried out, when there is no abnormal event for the target bucket tooth, by clearing the first queue and the second queue of the target bucket tooth, it can prepare for the next stage of bucket tooth detection, so as to realize the continuous detection of bucket teeth at each position.

[0076] In this embodiment, by setting the third flag bit to record the detection result of the first detection, it is ensured that when both the first detection and the second detection are abnormal, verification can be carried out through the third flag bit, which can effectively prevent the phenomena of false alarms and missed alarms, enhance the reliability of abnormal alarms, prevent false alarms caused by short-term interference, and ensure the continuity and accuracy of bucket tooth abnormal detection during long-term detection tasks.

[0077] In a possible implementation manner, after returning to execute the step of storing the N first flag bits of the target bucket tooth in the corresponding first queue and storing the N second flag bits of the target bucket tooth in the corresponding second queue, it further includes:

[0078] Count the third quantity or the fourth quantity of the target bucket tooth; the third quantity is the quantity of the fifth preset value in the first queue of the target bucket tooth, and the first flag bit being the fifth preset value indicates that there is no bucket tooth abnormality for the target bucket tooth at the corresponding first moment; the fourth quantity is the quantity of the sixth preset value in the second queue of the target bucket tooth, and the second flag bit being the sixth preset value indicates that there is no bucket tooth abnormality for the target bucket tooth at the corresponding second moment;

[0079] If the third quantity of the target bucket tooth is greater than the third threshold, or the fourth quantity of the target bucket tooth is greater than the third threshold, then update the third flag bit of the target bucket tooth to the fourth preset value, and the third flag bit being the fourth preset value indicates that there is no abnormal event for the target bucket tooth.

[0080] In the secondary detection of the target bucket tooth, the third quantity and the fourth quantity of the target bucket tooth can be counted, and based on the third threshold, it can be detected whether there is a bucket tooth abnormality for the target bucket tooth. If it is detected that there is no bucket tooth abnormality for the target bucket tooth, then the third flag bit of the target bucket tooth can be updated to the fourth preset value to indicate that there is no abnormal event for the target bucket tooth, and in the first detection, it may be a misjudgment caused by object occlusion.

[0081] In an application scenario, by way of example and not limitation, an excavator has 5 bucket teeth. On this basis, queues can be set For the abnormal detachment of the bucket tooth, maintain the first queue of 5 bucket teeth when the bucket is in the vertically upward state. Set the queue For the abnormal detachment of the bucket tooth, maintain the second queue of 5 bucket teeth when the bucket is in the vertically downward state. Set the queue For abnormal bucket tooth fracture, maintain the first queue of 5 bucket teeth when the bucket is in the vertically upward state. Set the queue For abnormal bucket tooth fracture, maintain the second queue of 5 bucket teeth when the bucket is in the vertically downward state. For abnormal bucket tooth shedding, set α 1 : the first threshold, set α 4 : the second threshold, set α 3 : the third threshold, set History d : the third flag bit, initialized to Flase. For abnormal bucket tooth fracture, set α 2 : the first threshold, set α 6 : the second threshold, set α 5 : the third threshold, set History t : the third flag bit, initialized to Flase. Based on the above settings, the abnormal detection of bucket teeth can be achieved through the following steps.

[0082] Step 1, identify the position of the bucket in each frame of the bucket image in the video stream of the excavator through the bucket detection model, and obtain the position coordinates and bucket state of the bucket frame (i.e., B: [x 1 , y 1 , x 2 , y 2 , label 1 ), (x 1 , y 1 ) is the upper left vertex coordinate, (x 2 , y 2 ) is the lower right vertex coordinate, label 2 has three category states: vertically downward state (0), vertically upward state (1), other state (2).

[0083] Step 2, when the bucket state is 0 and 1, crop the bucket sub-image containing only the bucket from the bucket image according to B, and further input it into the bucket tooth detection model to obtain at least one bucket tooth coordinate and the bucket tooth label corresponding to each bucket tooth coordinate. The bucket tooth label altogether contains two categories: normal (0), shedding (1).

[0084] Step 3, when the bucket state is 2, do not perform bucket tooth detection through the bucket tooth detection model, and directly detect the bucket for the next frame of the bucket image.

[0085] Step 4, on the basis of Step 2, divide the bucket tooth area of the 5 bucket teeth on the bucket.

[0086] First, calculate the bucket tooth area width d according to the formula (x 2 - x 1 ) / 4; then obtain the coordinate range of the 5 bucket teeth according to d. The coordinate range of the bucket tooth at the first position is (x1 , x 1 + d), the coordinate range of the tooth at the second position is (x 1 + d, x 1 + 2d), the coordinate range of the tooth at the third position is (x 1 + 2d, x 1 + 3d), the coordinate range of the tooth at the fourth position is (x 1 + 3d, x 1 + 4d), the coordinate range of the tooth at the fifth position is (x 1 + 4d, x 1 + 5d). After obtaining the coordinate ranges of the teeth at the 5 positions, they can be matched with the tooth coordinates obtained in Step 2 to determine the teeth with abnormal tooth shedding and the teeth with abnormal tooth fracture among the teeth at the 5 positions.

[0087] Step 5, if the tooth label of the tooth at a certain position is 1, it is determined that the tooth at that position has abnormal tooth shedding, and the first flag bit of the tooth at that position is set to True; otherwise, the first flag bit of the tooth at that position is set to False.

[0088] Step 6, if the tooth range at a certain position does not match the tooth coordinates, it is determined that the tooth at that position has abnormal tooth fracture, and the first flag bit of the tooth at that position is set to True; otherwise, the first flag bit of the tooth at that position is set to False.

[0089] Step 7, for abnormal tooth shedding, the queue circularly stores the first flag bits of the teeth at the i-th position at N different times when the bucket state is 1.

[0090] Step 8, for abnormal tooth shedding, the queue circularly stores the second flag bits of the teeth at the i-th position at N different times when the bucket state is 0.

[0091] Step 9, for abnormal tooth fracture, the queue circularly stores the first flag bits of the teeth at the i-th position at N different times when the bucket state is 1.

[0092] Step 10, for abnormal tooth fracture, the queue circularly stores the second flag bits of the teeth at the i-th position at N different times when the bucket state is 0.

[0093] Step 11, count the number of True in the queue count the number of True in the queue if the number of True in both queues is greater than α 1, then determine the possibility of abnormal tooth loss of the bucket tooth at the i-th position, History d Set it to True and empty the queue at the same time and the queue Wait for secondary detection.

[0094] Step 12, count the number of True in the queue and count the number of True in the queue If the number of True in both queues is greater than α 2 , then determine the possibility of abnormal tooth fracture of the bucket tooth at the i-th position, History t Set it to True and empty the queue at the same time and the queue Wait for secondary detection.

[0095] Step 13, when History d is True, repeat steps 1-10. When the number of False in the queue or the queue is greater than α 3 , History d Reset to False.

[0096] Step 14, when History d is True, repeat steps 1-10. When the number of True in the queue or the queue is greater than α 4 , trigger an alarm for abnormal tooth loss, History d Reset to False and empty the queue at the same time and the queue

[0097] Step 15, when History t is True, repeat steps 1-10. When the number of False in the queue or the queue is greater than α 5 , History t Reset to False.

[0098] Step 16, when History t is True, repeat steps 1-10. When the number of True in the queue or the queue is greater than α 6 , trigger an alarm for abnormal tooth loss, History t Reset to False and empty the queue at the same time and queues

[0099] In the embodiments of the present application, by maintaining queues in different states (i.e., the first queue when the bucket is in the vertically upward state and the second queue when the bucket is in the vertically downward state), accidental misjudgments in single-frame detection can be effectively reduced. By counting the abnormal conditions of the bucket teeth at each position in the queues at multiple moments and further judging the abnormal conditions of the bucket teeth based on a set first threshold, noise or error interference during single-frame detection can be avoided, and the accuracy and robustness of bucket tooth abnormal detection can be improved.

[0100] It should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The order of execution of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0101] Corresponding to the bucket tooth abnormal detection method described in the above embodiments, Figure 2 The structural schematic diagram of the bucket tooth abnormal detection device provided by the embodiments of the present application is shown. For the sake of convenience of description, only the parts related to the embodiments of the present application are shown.

[0102] Referring to Figure 2 , the device includes:

[0103] A flag bit storage module 201, configured to store N first flag bits of the bucket teeth at each position on the bucket in a corresponding first queue and store N second flag bits of the bucket teeth at each position in a corresponding second queue for the same type of bucket tooth abnormality; the N first flag bits represent whether the bucket teeth at the corresponding positions have the bucket tooth abnormality at N first moments, and the bucket is in the vertically upward state at the N first moments; the N second flag bits represent whether the bucket teeth at the corresponding positions have the bucket tooth abnormality at N second moments, and the bucket is in the vertically downward state at the N second moments; N is an integer greater than 1;

[0104] A quantity statistics module 202, configured to count the first quantity and the second quantity of the bucket teeth at each position; the first quantity is the quantity of a first preset value in the first queue of the bucket teeth at the corresponding position, and the first flag bit being the first preset value represents that the bucket teeth at the corresponding position have the bucket tooth abnormality at the corresponding first moment; the second quantity is the quantity of a second preset value in the second queue of the bucket teeth at the corresponding position, and the second flag bit being the second preset value represents that the bucket teeth at the corresponding position have the bucket tooth abnormality at the corresponding second moment;

[0105] Anomaly determination module 203, configured to determine that there is an anomaly event for the target bucket teeth if there are target bucket teeth among the bucket teeth at each position, where the target bucket teeth are the bucket teeth for which both the first quantity and the second quantity are greater than a first threshold, and the anomaly event indicates the possibility that the target bucket teeth have the bucket tooth anomaly.

[0106] Optionally, the above device further includes:

[0107] A first processing module, configured to update the third flag bit of the target bucket teeth to a third preset value, and clear the first queue and the second queue of the target bucket teeth, where the third flag bit being the third preset value indicates that the target bucket teeth have the anomaly event.

[0108] Optionally, the above device further includes:

[0109] A return execution module, configured to, if the third flag bit of the target bucket teeth is the third preset value, return and execute the steps of storing the N first flag bits of the target bucket teeth in the corresponding first queue, storing the N second flag bits of the target bucket teeth in the corresponding second queue, and counting the first quantity and the second quantity of the target bucket teeth for the bucket tooth anomaly and the target bucket teeth;

[0110] An alarm trigger module, configured to trigger an anomaly alarm for the target bucket teeth if the first quantity of the target bucket teeth is greater than a second threshold, or the second quantity of the target bucket teeth is greater than the second threshold.

[0111] Optionally, the above device further includes:

[0112] A second processing module, configured to update the third flag bit of the target bucket teeth to a fourth preset value, and clear the first queue and the second queue of the target bucket teeth, where the third flag bit being the fourth preset value indicates that the target bucket teeth do not have the anomaly event.

[0113] Optionally, the above device further includes:

[0114] A target statistics module, configured to count the third quantity or the fourth quantity of the target bucket teeth; the third quantity is the quantity of a fifth preset value in the first queue of the target bucket teeth, and the first flag bit being the fifth preset value indicates that the target bucket teeth do not have the bucket tooth anomaly at the corresponding first moment; the fourth quantity is the quantity of a sixth preset value in the second queue of the target bucket teeth, and the second flag bit being the sixth preset value indicates that the target bucket teeth do not have the bucket tooth anomaly at the corresponding second moment;

[0115] A flag bit update module, configured to update the third flag bit of the target bucket tooth to a fourth preset value if the third quantity of the target bucket tooth is greater than a third threshold, or the fourth quantity of the target bucket tooth is greater than the third threshold, where the third flag bit being the fourth preset value indicates that the abnormal event does not exist for the target bucket tooth.

[0116] Optionally, the above-mentioned flag bit storage module 201 includes:

[0117] An image acquisition unit, configured to acquire a current frame of the bucket image and use the current frame of the bucket image as an alternative image;

[0118] A state recognition unit, configured to perform state recognition on the bucket in the alternative image;

[0119] If it is recognized that the bucket is in a target state, perform bucket tooth detection on the alternative image to obtain a bucket tooth detection result. Based on the bucket tooth detection result and the coordinate ranges of the bucket teeth at each position, determine the flag bits of the bucket teeth at each position at the corresponding moment, and store the flag bits at the corresponding moment in the corresponding queue. If the number of flag bits in the corresponding queue does not reach N, use the next frame of the bucket image of the alternative image as the alternative image, and return to execute the step of performing state recognition on the bucket in the alternative image and subsequent steps until the number of flag bits in the corresponding queue reaches N;

[0120] Wherein, the target state includes a vertically upward state and a vertically downward state; when the bucket is in the vertically upward state, the corresponding moment is the first moment, the flag bit at the corresponding moment is the first flag bit, and the corresponding queue is the first queue; when the bucket is in the vertically downward state, the corresponding moment is the second moment, the flag bit at the corresponding moment is the second flag bit, and the corresponding queue is the second queue.

[0121] It should be noted that for the information interaction, execution process, etc. between the above-mentioned devices / units, since they are based on the same concept as the method embodiment of the present application, for their specific functions and the technical effects brought, please refer to the method embodiment part for details, and will not be elaborated here.

[0122] Figure 3 It is a schematic structural diagram of an electronic device provided by an embodiment of the present application. As Figure 3 shown, the electronic device 3 in this embodiment includes: at least one processor 30 ( Figure 3 only one is shown in the figure), a memory 31, and a computer program 32 stored in the memory 31 and executable on the at least one processor 30. When the processor 30 executes the computer program 32, the steps in any of the above-mentioned method embodiments are implemented.

[0123] The electronic device may include, but is not limited to, a processor 30 and a memory 31. Those skilled in the art can understand that Figure 3 This is only an example of the electronic device 3 and does not constitute a limitation on the electronic device 3. It may include more or fewer components than shown in the figure, or combine some components, or different components. For example, it may also include input / output devices, network access devices, etc.

[0124] The so-called processor 30 may be a central processing unit (CPU), and the processor 30 may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0125] The memory 31 may be an internal storage unit of the electronic device 3 in some embodiments, such as the hard disk or memory of the electronic device 3. The memory 31 may also be an external storage device of the electronic device 3 in other embodiments, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 3. Further, the memory 31 may also include both the internal storage unit and the external storage device of the electronic device 3. The memory 31 is used to store an operating system, application programs, a boot loader, data, and other programs, such as the program code of the computer program, etc. The memory 31 may also be used to temporarily store data that has been output or will be output.

[0126] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of each functional unit and module is used as an example. In practical applications, the above-mentioned functions can be allocated to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of this application. The specific working process of the units and modules in the above system can refer to the corresponding process in the foregoing method embodiment and will not be elaborated herein.

[0127] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above-mentioned method embodiments of this application, a computer program can be used to instruct the relevant hardware to complete. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can at least include: any entity or device that can carry the computer program code to the device / electronic device, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disc, etc. In some jurisdictions, according to legislation and patent practice, the computer-readable medium cannot be an electrical carrier signal and a telecommunication signal.

[0128] In the above embodiments, the descriptions of each embodiment have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0129] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in connection with the embodiments disclosed herein can be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Skilled artisans may use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of this application.

[0130] In the embodiments provided in this application, it should be understood that the disclosed apparatus / electronic device and method can be implemented in other ways. For example, the apparatus / electronic device embodiments described above are merely illustrative. For example, the division of the modules or units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces, and the indirect couplings or communication connections of the devices or units can be in electrical, mechanical or other forms.

[0131] The units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0132] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them; although this application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included in the protection scope of this application.

Claims

1. A method for detecting bucket tooth abnormality, characterized in that: include: For the same type of bucket tooth abnormality, N first flags of bucket teeth at various positions on the bucket are stored in the corresponding first queue, and N second flags of bucket teeth at various positions are stored in the corresponding second queue; the N first flags indicate whether bucket teeth at corresponding positions have bucket tooth abnormality at N first moments, and the bucket is in a vertical upward state at the N first moments; the N second flags indicate whether bucket teeth at corresponding positions have bucket tooth abnormality at N second moments, and the bucket is in a vertical downward state at the N second moments; N is an integer greater than 1; Counting the first number and the second number of bucket teeth at each position; the first number is the number of the first preset value in the first queue of bucket teeth at the corresponding position, and the first flag is the first preset value indicating that the bucket teeth at the corresponding position have the bucket teeth abnormality at the corresponding first moment; The second number is the number of the second preset value in the second queue of bucket teeth at the corresponding position, and the second flag is the second preset value indicating that the bucket teeth at the corresponding position have the bucket tooth abnormality at the corresponding second moment; If there is a target bucket tooth among the bucket teeth at each position, it is determined that an abnormal event exists in the target bucket tooth, and the target bucket tooth is a bucket tooth whose first quantity and second quantity are both greater than a first threshold value, and the abnormal event indicates the possibility that the target bucket tooth has the bucket tooth abnormality.

2. The method according to claim 1, characterized in that After determining that the target bucket tooth has an abnormal event, the method further includes: The third flag of the target bucket tooth is updated to a third preset value, and the first queue and the second queue of the target bucket tooth are cleared, wherein the third flag is the third preset value, indicating that the abnormal event exists in the target bucket tooth.

3. The method according to claim 2, characterized in that After clearing the first queue and the second queue of the target bucket teeth, the method further includes: If the third flag bit of the target bucket tooth is the third preset value, then for the bucket tooth abnormality and the target bucket tooth, return to execute the steps of storing the N first flag bits of the target bucket tooth in the corresponding first queue, storing the N second flag bits of the target bucket tooth in the corresponding second queue, and counting the first number and the second number of the target bucket tooth; If the first number of the target bucket teeth is greater than a second threshold, or the second number of the target bucket teeth is greater than the second threshold, an abnormal alarm for the target bucket teeth is triggered.

4. The method according to claim 3, characterized in that After triggering an abnormal alarm for the target bucket tooth, the method further includes: The third flag of the target bucket tooth is updated to a fourth preset value, and the first queue and the second queue of the target bucket tooth are cleared. The third flag is the fourth preset value, indicating that the target bucket tooth does not have the abnormal event.

5. The method according to claim 3, characterized in that: After returning to the step of storing the N first flags of the target bucket teeth in the corresponding first queue and storing the N second flags of the target bucket teeth in the corresponding second queue, the method further includes: The third number or the fourth number of the target bucket teeth is counted; the third number is the number of the fifth preset value in the first queue of the target bucket teeth, and the first flag is the fifth preset value, indicating that the target bucket teeth do not have the bucket tooth abnormality at the corresponding first moment; the fourth number is the number of the sixth preset value in the second queue of the target bucket teeth, and the second flag is the sixth preset value, indicating that the target bucket teeth do not have the bucket tooth abnormality at the corresponding second moment; If the third number of the target bucket teeth is greater than the third threshold, or the fourth number of the target bucket teeth is greater than the third threshold, the third flag of the target bucket teeth is updated to a fourth preset value, and the third flag is the fourth preset value, indicating that the abnormal event does not exist in the target bucket teeth.

6. The method according to any one of claims 1 to 5, characterized in that: The method of storing N first flags of bucket teeth at various positions on the bucket in a corresponding first queue, and storing N second flags of bucket teeth at various positions in a corresponding second queue, comprises: Acquire a bucket image of a current frame, and use the bucket image of the current frame as a candidate image; Performing state recognition on the bucket in the candidate image; If it is recognized that the bucket is in the target state, bucket teeth detection is performed on the candidate image to obtain bucket teeth detection results, and based on the bucket teeth detection results and the coordinate ranges of the bucket teeth at each position, the flag positions of the bucket teeth at each position at the corresponding time are determined, and the flag positions at the corresponding time are stored in the corresponding queue. If the number of flag positions in the corresponding queue does not reach N, the next frame bucket image of the candidate image is used as the candidate image, and the step of performing state recognition on the bucket in the candidate image and subsequent steps are returned to execute until the number of flag positions in the corresponding queue reaches N; Among them, the target state includes a vertical upward state and a vertical downward state; when the bucket is in the vertical upward state, the corresponding moment is the first moment, the flag bit of the corresponding moment is the first flag bit, and the corresponding queue is the first queue; when the bucket is in the vertical downward state, the corresponding moment is the second moment, the flag bit of the corresponding moment is the second flag bit, and the corresponding queue is the second queue.

7. The method according to claim 6, characterized in that The step of determining the flag position of the bucket teeth at each position at a corresponding time based on the bucket teeth detection result and the coordinate range of the bucket teeth at each position includes: For the bucket tooth falling-off abnormality, if there is a first bucket tooth among the bucket teeth at each position, it is determined that the flag position of the first bucket tooth at the corresponding time is a preset value indicating the existence of the bucket tooth falling-off abnormality; the first bucket tooth is a bucket tooth whose coordinate range matches the bucket tooth coordinates in the bucket tooth detection result and the bucket tooth label of the bucket tooth coordinates indicates the existence of the bucket tooth falling-off abnormality; if there is a second bucket tooth among the bucket teeth at each position, it is determined that the flag position of the second bucket tooth at the corresponding time is a preset value indicating the absence of the bucket tooth falling-off abnormality; the second bucket tooth is a bucket tooth whose coordinate range matches the bucket tooth coordinates in the bucket tooth detection result and the bucket tooth label of the bucket tooth coordinates indicates the absence of the bucket tooth falling-off abnormality, or a bucket tooth whose coordinate range does not match the bucket tooth coordinates in the bucket tooth detection result; For bucket tooth fracture abnormality, if there is a third bucket tooth among the bucket teeth at each position, the flag position of the third bucket tooth at the corresponding time is determined to be a preset value indicating the presence of the bucket tooth fracture abnormality; the third bucket tooth is a bucket tooth whose coordinate range does not match the bucket tooth coordinates in the bucket tooth detection result; if there is a fourth bucket tooth among the bucket teeth at each position, the flag position of the fourth bucket tooth at the corresponding time is determined to be a preset value indicating the absence of the bucket tooth fracture abnormality; the fourth bucket tooth is a bucket tooth whose coordinate range matches the bucket tooth coordinates in the bucket tooth detection result.

8. A bucket tooth abnormality detection device, characterized in that: include: A flag storage module is used for storing N first flags of bucket teeth at various positions on the bucket in a corresponding first queue, and storing N second flags of bucket teeth at various positions in a corresponding second queue for the same type of bucket tooth abnormalities; the N first flags indicate whether bucket teeth at corresponding positions have the bucket tooth abnormalities at N first moments, and the bucket is in a vertical upward state at the N first moments; the N second flags indicate whether bucket teeth at corresponding positions have the bucket tooth abnormalities at N second moments, and the bucket is in a vertical downward state at the N second moments; N is an integer greater than 1; A quantity statistics module is used for the first quantity and the second quantity of the bucket teeth at each position; the first quantity is the quantity of the first preset value in the first queue of the bucket teeth at the corresponding position, and the first flag is the first preset value indicating that the bucket teeth at the corresponding position have the bucket teeth abnormality at the corresponding first moment; The second number is the number of the second preset value in the second queue of bucket teeth at the corresponding position, and the second flag is the second preset value indicating that the bucket teeth at the corresponding position have the bucket tooth abnormality at the corresponding second moment; An abnormality determination module is used to determine that an abnormal event exists in the target bucket tooth if there is a target bucket tooth among the bucket teeth at each position, the target bucket tooth being a bucket tooth whose first number and second number are both greater than a first threshold, and the abnormal event indicates the possibility that the target bucket tooth has the bucket tooth abnormality.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the electronic device implements the method according to any one of claims 1 to 7.

10. A computer program product, characterized in that The invention comprises a computer program which, when executed, causes the method according to any one of claims 1 to 7 to be performed.

Images