Mechanical arm safety protection and control system based on video monitoring

Abstract

The invention discloses a mechanical arm safety protection and control system based on video monitoring, and relates to the technical field of mechanical arm safety protection.A video analysis module is arranged to periodically analyze video monitoring data of a plurality of mechanical arm working partitions, and the time period when personnel are active and the corresponding active mechanical arm working partitions are determined; the recognition control module selects a mechanical arm locking type according to the conditions that an operator exists in an operation area at the current moment and the outline of the operator is recognized in a mechanical arm working area at the current moment, forcibly locks the mechanical arm according to a mechanical arm working area of a specific risk area, ensures that the safety of the operator is not threatened, and improves the safety of the operator. On the contrary, the mechanical arm is temporarily locked, and the locking time is set, so that the potential safety hazard caused by non-standard operation of an operator when part of personnel enter and exit the frequent subareas is avoided, and meanwhile, the potential non-standard operation is also prevented.

Description

Technical Field

[0001] The present invention relates to the technical field of robot arm safety protection, and in particular to a robot arm safety protection and control system based on video monitoring. Background Art

[0002] In the context of the rapid development of industrial automation and robotics technology, the application scope of robotic arms is rapidly expanding. These high-precision and high-flexibility mechanical equipment play a vital role in improving production efficiency and quality. However, along with this come the potential safety hazards they may bring during operation, especially in the complex and ever-changing construction site environment; The high mobility of personnel at the construction site, the changing environment, and the unpredictability of human operations all pose challenges to the safe operation of the robotic arm. A common practice at present is to lock the robotic arm before the operator arrives at the operating area until the operator arrives and is ready to take over control; In order to accurately identify the operator and give other personnel on site enough time to evacuate, real-time facial recognition technology was used to monitor personnel within the robotic arm’s working area; this technology not only enables quick and accurate positioning of the operator who is about to take over the robotic arm, but also ensures that other personnel have sufficient time to safely leave the danger zone; However, in actual operation, operators usually follow a predetermined path from entering the working area of ​​the robot arm to finally reaching the operating position. If the system performs face recognition on all personnel in the working area, this will undoubtedly lead to a significant consumption of computing resources and increase processing time, resulting in unnecessary waste of resources. In order to solve the above problems, the present invention proposes a solution. Summary of the invention

[0003] The purpose of the present invention is to provide a robotic arm safety protection and control system based on video surveillance. In order to solve the problem in the prior art that in order to accurately identify the operator before the operator arrives at the operating area and give other personnel on site enough time to evacuate, real-time face recognition technology is used on site to monitor the personnel in the robotic arm working area without considering that the operator usually follows a predetermined path from entering the robotic arm working area to finally reaching the operating position. If the system performs face recognition on all personnel in the working area, this will undoubtedly lead to a significant consumption of computing resources, and will also increase processing time, resulting in unnecessary waste of resources. The purpose of the present invention can be achieved through the following technical solutions: A robotic arm safety protection and control system based on video monitoring, comprising: In the current analysis cycle, the video analysis module extracts several frame image sets from the video monitoring data of each robot arm working partition stored in the current analysis cycle. By analyzing the shooting time and the robot arm work partition corresponding to each frame of the image set, a trajectory list of the operator in the current analysis period is determined, and a plurality of robot arm work partitions are stored and stored from left to right in the trajectory list; After receiving the video surveillance data of each robot arm working area at the current moment, the recognition and determination module first determines whether there is an operator in the robot arm's operating area: If there is no operator in the operation area, all the robot arm work partitions stored in the trajectory list are read from left to right in sequence, and human outline recognition is performed on each frame of the video surveillance data of each robot arm work partition read at the current moment in the order of reading. If a human outline is recognized, facial recognition is performed on the person corresponding to each human outline to determine whether it is an operator. If a person is determined to be an operator, the person is locked and the person's human feature data is extracted, and the human feature data includes height, top type and color, pants type and color, and gender; When a person is locked, starting from the moment the person is locked, the recognition and judgment module will lock the person based on the person's human feature data from the video surveillance of each robotic arm working zone received at each subsequent moment until the person enters the operation area. When the person is locked, facial recognition will not be performed on other persons.

[0004] Furthermore, when there is no operator in the operating area, the robotic arm is locked.

[0005] Furthermore, it also includes an area monitoring module for collecting media data of the working area of ​​the robot arm in real time, and the media data includes video monitoring data of each working partition of the robot arm.

[0006] Beneficial effects of the present invention: (1) The present invention divides the working area of ​​the robot arm into a number of working areas of the robot arm, and deploys a high-definition network camera for each working area of ​​the robot arm, so as to obtain the video content of the corresponding working area of ​​the robot arm, thereby ensuring all-round monitoring of the working area of ​​the robot arm without blind spots; (2) The present invention sets a video analysis module to periodically analyze the video surveillance data of several robot arm work partitions, and determines the time period when personnel are active and the corresponding active robot arm work partition according to the camera moment corresponding to all frame images in which human outlines can be identified and the number of human outlines in the frame images. The recognition control module is set to select the robot arm locking type according to the calibration type corresponding to the time period at the current moment and the robot arm work partition corresponding to the frame image corresponding to the identified human outline. For the robot arm work partition in the specific risk area, the robot arm is forcibly locked to ensure that the safety of personnel is not threatened. Otherwise, the robot arm is temporarily locked and the locking time is set to avoid the safety hazards caused by the irregular operation of the operator in the partition where some personnel frequently enter and exit, and also prevent potential irregular operation. (3) The present invention uses a video analysis module to analyze the operator's path from entering the robot arm's working area to finally arriving at the operating area to determine a travel trajectory list. The recognition control module prioritizes facial recognition of personnel in several robot arm working areas included in the travel trajectory list when there is no operator in the operating area at the current moment, and locks the personnel. In this way, unnecessary waste of computing resources and time resources is avoided. After a person is locked, an alarm is sounded to give the remaining personnel time to evacuate, thereby avoiding the situation where the operator arrives at the operating area and waits for other personnel to evacuate. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] The present invention will be further described below in conjunction with the accompanying drawings.

[0008] Figure 1 It is a system block diagram of the present invention. DETAILED DESCRIPTION

[0009] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0010] like Figure 1 As shown, a robotic arm safety protection and control system based on video monitoring includes an area monitoring module, an identification control module and a video analysis module; The regional monitoring module is used to perform video monitoring on the working area of ​​the robot arm. The regional monitoring module includes a plurality of regional monitoring units. One regional monitoring unit corresponds to one working partition of the robot arm. The regional monitoring unit collects video monitoring data of the corresponding working partition of the robot arm in real time. It should be noted that the real-time here refers to every moment. In this embodiment, in order to monitor the working area of ​​the robot arm in all directions without blind spots, the management personnel divide the working area of ​​the robot arm into several working areas of the robot arm, and deploy a high-definition network camera for each working area of ​​the robot arm, so as to obtain the video content of the corresponding working area of ​​the robot arm; In this embodiment, the specifications of the high-definition network cameras arranged for each robot arm working zone are the same; The area monitoring module generates real-time media data of the working area of ​​the robot arm based on the video monitoring data of all robot arm working partitions collected in real time, and transmits the real-time media data of the working area of ​​the robot arm to the recognition control module and the video analysis module respectively; An identification control module, used to identify media data of the working area of ​​the robot arm and to perform safety control on the robot arm based on the identification result, wherein the identification control module pre-stores facial image data of the operator operating the robot arm, a risk analysis table, and a list of the operator's travel trajectories; After receiving the transmitted media data of the working area of ​​the robot arm at the current moment, the recognition control module first determines whether there is an operator in the operating area of ​​the robot arm; If there is an operator in the operation area of ​​the robot arm at the current moment, the robot arm is safely controlled according to the preset first control rule. The preset first control rule is as follows: S21: Obtain the type corresponding to the time period to which the current moment belongs from the risk analysis table stored in the identification control module; if the time period to which the current moment belongs is a risk time period, obtain all the robot arm work partitions marked as specific risk areas corresponding to the time period to which the current moment belongs from the risk identification table; S22: extracting the video surveillance data of all robot arm working areas marked as specific risk areas corresponding to the time period to which the current moment belongs from the received media data of the robot arm working area at the current moment, and identifying them: S221: If a human body outline is recognized in any of the video surveillance data, a sound alarm lasting 10 seconds is immediately issued, and the operation authority of the robot arm is forcibly locked. The forced locking duration is set to P2. This method can avoid potential hazards while avoiding mechanical damage caused by repeated startup. P2 is the forced locking duration threshold of a preset specific risk area. It should be noted that during the forced locking of the robot arm, even authorized personnel cannot force unlocking, and human body outline recognition is not performed on the video surveillance data of all robot arm working partitions received during the locking period; S222: If the human body contour is not recognized in any of the video surveillance data, the human body contour is recognized for the remaining video surveillance data of all the robot arm working partitions that have not been extracted. If the human body contour is recognized, a sound alarm lasting 10S is immediately issued, and the operation authority of the robot arm is temporarily locked. The temporary lock duration is set to P3. This method can avoid potential hazards while avoiding mechanical damage caused by repeated startup. P3 is the temporary lock duration threshold of the preset specific safety zone. It should be noted that during the temporary lock period of the robot arm, the authorized personnel can force unlocking, and the human body contour recognition is not performed on the video surveillance data of all the robot arm working partitions received during the lock period; If there is no operator in the operation area of ​​the robot arm at the current moment, it means that the robot arm is not working at the current moment. At this time, the robot arm is locked and needs to be unlocked by the operator. The robot arm is safely controlled according to the preset second control rule. The preset second control rule is as follows: S31: Based on the operator's travel trajectory list stored in the recognition control module, all the robot arm work partitions contained therein are marked as T1, T2, ..., Tt in descending order of the element subscripts therein, where t≥1; S32: Firstly extract the video surveillance data of the working area T1 of the robot arm at the current moment from the received media data of the working area of ​​the robot arm at the current moment, and perform human figure contour recognition on each frame of the video surveillance data of the working area T1 of the robot arm at the current moment according to the preset judgment rule. The preset judgment rule is as follows: S321: extracting facial feature data of the operator from the facial image data of the operator stored in the recognition control module; S322: According to the sequence of the camera shooting time, the first frame of the image contained in the video monitoring data of the robot arm working area T1 at the current moment is firstly subjected to human figure contour recognition: If a human outline is recognized, facial feature data of all persons in the first frame image are extracted, and similarity calculation is performed with the extracted facial feature data of the operator in turn. If the facial feature data of a certain person is calculated to have a similarity greater than or equal to P5 with the facial feature data of the operator, the person is determined to be the operator and is locked. On the contrary, if the facial feature data of each person is calculated to have a similarity less than P5 with the facial feature data of the operator, it is determined that there is no operator in the first frame image, and P5 is a preset facial recognition comparison threshold. S323: Under the premise that it is determined in S322 that there is no operator in the first frame image, human outline recognition is performed again on the second frame image contained in the video surveillance data of the robot arm working partition T1 at the current moment according to the sequence of shooting time according to step S322, until a certain person is locked, or all frame images contained in the video surveillance data of the robot arm working partition T1 at the current moment are recognized and no person is still locked; S33: In S323, in the case where all the frame images contained in the video surveillance data of the robot arm working partition T1 at the current moment have been identified and no person has been locked, the video surveillance data of the robot arm working partitions T2, T3, ..., Tt at the current moment are extracted from the media data of the robot arm working area at the current moment in accordance with step S32, and the human figure contour is recognized for each frame image contained therein until a person is locked; If no person is locked after the human figure contour recognition is completed for each frame of the video surveillance data of the robot arm working partition Tt at the current moment, it is determined that the operator does not appear at the current moment, and no processing is performed; When a person is locked, a sound alarm lasting 10 seconds is first issued to notify other personnel to evacuate the robot arm work area immediately. Then, the person's human feature data is extracted from the video surveillance data of a frame of image that determines that the person is the operator. The human feature data includes height, top type and color, pants type and color, and gender. The person is then locked in the subsequent received media data of the working area of ​​the robot arm according to the person's human feature data until he enters the operation area. When the person is locked, facial recognition is not performed on other persons. In this way, unnecessary facial recognition can be avoided and computing resources can be saved. A video analysis module is used to store and analyze the media data of the working area of ​​the robot arm. The video analysis module stores the media data of the working area of ​​the robot arm after receiving the real-time transmission; The video analysis module analyzes the media data of the robot working area stored in each analysis cycle. In this embodiment, the interval of the analysis cycle is P1, and P1 is a preset interval threshold of the analysis cycle. In the current analysis cycle, the video analysis module analyzes the media data of the robot working area stored in the current analysis cycle according to the preset first analysis rule and the second analysis rule. The preset first analysis rule is as follows: S11: Marking a number of robot arm work partitions into which the robot arm work area is divided, respectively marked as A1, A2, ..., Aa, where a≥1, and a refers to the total number of the robot arm work partitions; S12: Mark all the media data of the working area of ​​the robot arm stored in the video analysis module in the current analysis period as B1, B2, ..., Bb in sequence according to the order in which they are stored, where b≥1; S13: Divide the interval of the current analysis cycle into several monitoring cycles, marked as Y1, Y2, ..., Yy, where y≥1; then divide the monitoring segments, divide the time of one monitoring cycle into c monitoring segments of equal length, and mark the c monitoring segments of one monitoring cycle as C1, C2, ..., Cc, where c≥1; in this embodiment, one monitoring cycle is 1 day, and one monitoring segment is 1 hour; S14: Calculate and obtain the personnel activity index J1 of the robot arm work area A1 according to the preset calculation rules, as follows: S141: sequentially obtain the video monitoring data of the robot arm working area A1 from the robot arm working area media data B1, B2, ..., Bb, and mark them as D1, D2, ..., Db; S142: Select monitoring cycle Y1 as the screening cycle, extract all video surveillance data whose collection time is within the monitoring segment C1 of the screening cycle from the video surveillance data D1, D2, ..., Db, and mark all the extracted video surveillance data as Z1, Z2, ..., Zz in the order of D1, D2, ..., Db, 1≤z≤b; S142: performing human body contour recognition on each frame of the video surveillance data Z1, Z2, ..., Zz in turn, and obtaining all images in which human body contours can be recognized; According to the order of the distance between the shooting time corresponding to each frame of image and the current time, all the images that can identify the human body contour are marked as F1, F2, ..., Ff in sequence from far to near, where f≥1, and the shooting time corresponding to each frame of image refers to the time corresponding to the shooting of each frame of image; S143: sequentially obtain the intervals between the image F1 and F2, F2 and F3, ..., Ff-1 and Ff corresponding to the shooting time, and mark them as G1, G2, ..., Gg, where g=1, 2, ..., f-1; S144: Utilize the formula , 1≤h≤g, calculate and obtain the discrete value H1 of the interval durations G1, G2, ..., Gg, and compare H1 with H, where G is the average value of Gh, and H is the preset interval duration discrete threshold; If H1 ≥ H, then delete the corresponding Gh in descending order of |Gh - G| and calculate the discrete value H1 of the remaining Gh. Compare H1 with H again until H1 < H. Obtain the average value of the remaining Gh participating in the calculation of the discrete value H1 at this time, and calibrate it as the personnel frequency I1 in the robotic arm working area A1 under the screening cycle monitoring section C1. S145: Use the formula to calculate and obtain the personnel activity index J1 in the robotic arm working area A1 under the screening cycle monitoring section C1: S15: Calculate and obtain the personnel activity indices J1, J2,..., Ja in the robotic arm working areas A1, A2,..., Aa under the screening cycle monitoring section C1 in sequence according to S14, and use the summation and averaging formula to calculate and obtain their average value. Calibrate the calculated average value as the average personnel activity index K1 of the screening cycle monitoring section C1. S16: Select the monitoring cycles Y1, Y2,..., Yy as the screening cycles in sequence, and calculate and obtain the average personnel activity indices K1, K2,..., Ky of the monitoring sections C1 of the monitoring cycles Y1, Y2,..., Yy in sequence according to S15. Use the formula , 1 ≤ m ≤ y, to calculate and obtain the discrete value M1 of the average personnel activity indices K1, K2,..., Ky. Compare M1 with M, where K is the average value of Km and M is the preset discrete threshold of the average personnel activity index. If M1 ≥ M, then delete the corresponding Km in descending order of |Km - K| and calculate the discrete value M1 of the remaining Km. Compare M1 with M again until M1 < M. Obtain the average value of the remaining Km participating in the calculation of the discrete value M1 at this time, and calibrate it as the activity evaluation index L1 of the monitoring section C1. S17: Compare L1 with L. If L1 ≥ L, then determine that the personnel access in each robotic arm working area within the monitoring section C1 is active, and calibrate the monitoring section C1 as a risk time period. Otherwise, determine that the personnel access in each robotic arm working area within the monitoring section C1 is scarce, and calibrate the monitoring section C1 as a safe time period. S18: According to S11 to S17, determine the personnel access situation in each robotic arm working area within the monitoring sections C1, C2,..., Cc in sequence, and determine whether the corresponding monitoring section is a risk time period or a safe time period. S19: According to S14, calculate in sequence to obtain the personnel activity indices N1, N2, N3, …, Ny of the robotic arm working area A1 under the monitoring section C1 of the monitoring period Y1, under the monitoring section C1 of the monitoring period Y2, …, under the monitoring section C1 of the monitoring period Yy. Among them, in S145, the personnel activity index of the robotic arm working area A1 under the monitoring section C1 of the monitoring period Y1 has been marked as J1. Here, for the convenience of subsequent step operations, it is re - marked and re - marked as N1; S110: Use the formula , 1 ≤ n ≤ y, to calculate and obtain the discrete value O1 of the personnel activity indices N1, N2, N3, …, Ny, and compare the size of O1 and O, where N is the average value of Nn, and O is the preset discrete threshold of the personnel activity index; If O1 ≥ O, then delete the corresponding Nn in descending order of |Nn - N| in sequence and calculate the discrete value O1 of the remaining Nn, and compare the size of O1 and O again until O1 < O. Obtain the average value of the remaining Nn participating in the calculation of the discrete value O1 at this time, and calibrate it as the activity index Q1 of the robotic arm working area A1 under the monitoring section C1; S111: Compare the size of Q1 and Q. If Q1 ≥ Q, then determine that the personnel access in the robotic arm working area A1 under the monitoring section C1 is active, and calibrate the robotic arm working area A1 under the monitoring section C1 as a specific risk area. Otherwise, determine that the personnel access in the robotic arm working area A1 under the monitoring section C1 is scarce, and calibrate the robotic arm working area A1 under the monitoring section C1 as a specific safety area; S112: According to S19 to S111, calculate in sequence to obtain the activity indices of the robotic arm working area A1 under the monitoring sections C1, C2, …, Cc, and based on the activity indices of the robotic arm working area A1 under the monitoring sections C1, C2, …, Cc, select whether to calibrate the robotic arm working area A1 under the corresponding monitoring section as a specific risk area or a specific safety area; S113: According to S112, calculate in sequence the activity indices of the robotic arm working areas A1, A2, …, Aa under the monitoring sections C1, C2, …, Cc, and based on the activity indices of each robotic arm working area under each monitoring section, select whether to calibrate each robotic arm working area under each monitoring section as a specific risk area or a specific safety area; The video analysis module generates a risk analysis table for the current analysis period based on all the robotic arm working areas calibrated as specific risk areas and specific safety areas under each monitoring section, and all the time periods calibrated as risk time periods and safety time periods, and transmits it to the recognition control module for update and storage; The risk analysis table for the current analysis period includes a time period field, a risk area field, a safety area field, and a type field; The time period field stores monitoring sections C1, C2, ..., Cc respectively; the type field stores the type of the corresponding monitoring section, where the types include risk time period and safe time period; The risk zone field stores all the robot arm work partitions marked as specific risk zones under the corresponding monitoring segment; the safety zone field stores all the robot arm work partitions marked as specific safety zones under the corresponding monitoring segment; The video analysis module pre-stores the facial image data of the operator currently operating the robotic arm. The second analysis step is as follows: S41: extracting a set of frame images of several track recognition cycles from all the media data of the robot arm working area stored in the video analysis module in the current analysis cycle; A frame image set of a track recognition cycle includes a number of frame images that can identify the operator's body contour. All frame images in a frame image set of a track recognition cycle are arranged from left to right in the order of shooting time. The time interval difference between two adjacent frame images in a frame image set of a track recognition cycle is 1s; S42: from all frame image sets contained in a frame image set of a track recognition cycle, obtain the robot arm work partitions corresponding to the frame images therein, and mark the corresponding robot arm work partitions as R1, R2, ..., Rr in sequence according to the sequence of the frame image shooting time, where r≥1; Among them, for the robot arm work partitions corresponding to multiple frames of images that are the same, only the robot arm work partition is marked once, and when marking, the first shooting moment is selected as the marking sequence calibration; The robotic arm work partition corresponding to the frame image refers to the robotic arm work partition corresponding to the high-definition network camera that takes the frame image; S43: adding the robot arm work partitions R1, R2, ..., Rr into an empty list in sequence, and obtaining a trajectory list of the operator in the track recognition cycle; S44: according to S41 to S43, the trajectory lists of operators in all track identification cycles are calculated and obtained in sequence, and the trajectory list with the largest number of occurrences is selected from the trajectory lists, and the trajectory list is marked as the moving trajectory list of the operator in the current analysis cycle, wherein the trajectory list with the largest number of occurrences refers to the trajectory list with the largest number of trajectories in the trajectory lists of operators in all track identification cycles that is completely identical to the trajectory list; The video analysis module transmits the list of the operator's travel trajectories in the current analysis period to the recognition control module, and the recognition control module receives the list of the operator's travel trajectories in the current analysis period and updates and stores it; In the description of the specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0011] The above contents are merely examples and explanations of the present invention. Those skilled in the art may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the invention or exceed the scope defined by the claims, they shall all fall within the protection scope of the present invention.

[0012] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A robotic arm safety protection and control system based on video monitoring, characterized in that: include: In the current analysis cycle, the video analysis module extracts a number of frame image sets from the video monitoring data of each robot arm working partition stored in the current analysis cycle; Determine a trajectory list of the operator in the current analysis period according to the shooting time corresponding to each frame of the image set and the robot arm work partition, wherein the trajectory list stores a plurality of robot arm work partitions from left to right; After receiving the video surveillance data of each robot arm working area at the current moment, the recognition and determination module first determines whether there is an operator in the robot arm's operating area: If it is determined that there is no operator in the operation area, all the robot arm work partitions stored in the trajectory list are read from left to right in sequence, and human outline recognition is performed on each frame of the video surveillance data of each robot arm work partition read at the current moment in the order of reading. If a human outline is recognized, facial recognition is performed on the person corresponding to each human outline to determine whether it is an operator. If a person is determined to be an operator, the person is locked and the human feature data of the person is extracted; When a person is locked, starting from the moment the person is locked, the recognition and judgment module locks the person based on the person's human feature data from the video surveillance of each robot arm working zone received at each subsequent moment until the person enters the operation area.

2. According to the video surveillance-based robotic arm safety protection and control system of claim 1, it is characterized in that: When there is no operator in the operating area, the robot arm is locked.

3. According to the video surveillance-based robotic arm safety protection and control system of claim 1, it is characterized in that: It also includes an area monitoring module for collecting media data of the working area of ​​the robot arm in real time, and the media data includes video monitoring data of each working partition of the robot arm.

4. The robotic arm safety protection and control system based on video monitoring according to claim 1 is characterized in that: A frame image set contains several frame images that can identify the operator's body contour. The difference in shooting time corresponding to the frame images arranged adjacent to each other in a frame image set is 1s. All frame images in a frame image set are arranged from left to right in the order of corresponding shooting time.

5. The robotic arm safety protection and control system based on video monitoring according to claim 1 is characterized in that: The video analysis module is also used to divide the monitoring segments into a number of equal lengths according to the interval length of the current analysis cycle; Then, all the frame images in which the human body contour can be identified are extracted from the video surveillance data of each robot arm working partition stored in the current analysis cycle. According to the shooting time corresponding to each extracted frame image and the total number of human body contours that can be identified in each frame image, the monitoring section and the robot arm working partition are calibrated to obtain the risk analysis table of the current analysis cycle. There are two types of monitoring section calibration: risk time period and safety time period. There are two types of robot arm work area calibration: specific risk area and specific safety area.

6. A robotic arm safety protection and control system based on video monitoring according to claim 5, characterized in that: When the recognition and determination module receives the video surveillance data of each robot arm working partition at the current moment and determines that there is an operator in the operation area of ​​the robot arm, the robot arm is safely controlled according to the preset first control rule. The preset first control rule is as follows: S21: Obtain the type of the time period to which the current moment belongs from the risk analysis table stored in the identification control module. If the type of the time period to which the current moment belongs is a risk time period, obtain all the robot arm work partitions marked as specific risk areas corresponding to the time period to which the current moment belongs from the risk identification table; S22: extracting the video surveillance data of all robot arm working areas marked as specific risk areas corresponding to the time period of the current moment from the received media data of the robot arm working area at the current moment, and identifying them: S221: If a human body outline is recognized in any of the video surveillance data, a sound alarm lasting 10 seconds is immediately issued, and the robot arm is forcibly locked. The forced locking duration is set to P2, where P2 is the forced locking duration threshold of the preset specific risk area. During the forced locking of the robot arm, even authorized personnel cannot force unlocking, and human body outline recognition is not performed on the video surveillance data of all robot arm working partitions received during the locking period; S222: If any of the video surveillance data fails to identify the human body outline, human body outline recognition is performed on the remaining video surveillance data of all the robot arm working partitions that have not been extracted. If the human body outline is recognized, a sound alarm lasting 10S is immediately issued, and the robot arm is temporarily locked. The temporary locking duration is set to P3, and P3 is the temporary locking duration threshold of the preset specific safety zone. During the temporary locking of the robot arm, authorized personnel can forcibly unlock it, and human body outline recognition is not performed on the video surveillance data of all the robot arm working partitions received during the locking period.

7. The robotic arm safety protection and control system based on video monitoring according to claim 1 is characterized in that: When the recognition and determination module receives the video surveillance data of each robot arm working partition at the current moment and determines that there is no operator in the operation area of ​​the robot arm, the steps of locking the operator until the operator enters the operation area are as follows: S31: Based on the operator's travel trajectory list stored in the recognition control module, all the robot arm work partitions contained therein are marked as T1, T2, ..., Tt in descending order of the element subscripts therein, where t≥1; S32: Firstly, extract the video surveillance data of the working area T1 of the robot arm at the current moment from the received media data of the working area of ​​the robot arm at the current moment, and perform personnel contour recognition on each frame of the video surveillance data of the working area T1 of the robot arm at the current moment according to the preset judgment rule. The preset judgment rule is as follows: S321: extracting facial feature data of the operator from the facial image data of the operator stored in the recognition control module; S322: According to the order of the shooting time, firstly, the first frame image contained in the video monitoring data of the robot arm working area T1 at the current moment is used to identify the human contour: If the outline of a person is recognized, the facial feature data of all persons in the first frame image are extracted, and the similarity is calculated with the extracted facial feature data of the operator in turn. If the facial feature data of a certain person is calculated to have a similarity greater than or equal to P5 with the facial feature data of the operator, the person is determined to be the operator and locked. On the contrary, if the facial feature data of each person is calculated to have a similarity less than P5 with the facial feature data of the operator, it is determined that there is no operator in the first frame image, and P5 is a preset facial recognition comparison threshold. S323: Under the premise that it is determined in S322 that there is no operator in the first frame image, according to the order of the shooting time, the second frame image contained in the video monitoring data of the robot arm working partition T1 at the current moment is again identified according to step S322 until a certain person is locked, or all the frame images contained in the video monitoring data of the robot arm working partition T1 at the current moment are identified and no person is still locked; S33: In S323, in the case where all the frame images contained in the video surveillance data of the robot arm working partition T1 at the current moment have been identified and no person has been locked, the video surveillance data of the robot arm working partitions T2, T3, ..., Tt at the current moment are extracted from the media data of the robot arm working area at the current moment in accordance with step S32 in the order of T1, T2, ..., Tt, and the person contour is identified for each frame image contained therein until a person is locked; If no person is locked after the personnel contour recognition is completed for each frame of the image contained in the video surveillance data of the robot arm working partition Tt at the current moment, no processing is performed.

Images