CN219107559U - Artificial intelligence-based safety operation control circuit - Google Patents

Abstract

The utility model provides a safety operation control circuit based on artificial intelligence, which is used for solving the problem that the accuracy of active early warning is affected because signals acquired by a camera are not processed and are directly identified by the existing patent technology. The safety operation circuit also comprises a preprocessing module, wherein the signal output by the camera is subjected to the preprocessing module and then is output to the identification module, the preprocessing module comprises an interference detection circuit and an interference elimination circuit, the interference detection circuit is used for amplifying, calculating and filtering the signal and then outputting an interference signal, and the interference elimination circuit is used for calculating and filtering the interference signal and then obtaining the image signal, so that the accuracy of active early warning is improved.

Description

Artificial intelligence-based safety operation control circuit

technical field

The utility model relates to the field of safe operation, in particular to a safety operation control circuit based on artificial intelligence.

Background technique

In order to ensure the standard of action of electric workers during operation, and thus ensure the safety of electric power construction, many construction sites have installed electric power work site safety management and control systems. The patented technology of Active Early Warning and Safety Monitoring System for Live Work has set up the human body key point identification system, charged body identification system, data fusion system and spatial position judgment system. Here, the human body key point identification system, charged body identification system, data The fusion system is used as the recognition module, among which the key point recognition system of the human body and the charged body recognition system need to detect and process the signals collected by the camera, and the data fusion system can judge the spatial position of the charged body and the spatial position of the acting person, and judge the space Whether the position is normal, and the camera generally transmits the collected signals to the human body key point recognition system, charged body recognition system, and data fusion system through the wireless network to facilitate data transmission and reduce line laying.

The human body key point recognition system and the charged body recognition system process the signal algorithmically, but there are also cases of misjudgment. The reason is that the signal output by the camera is found to be extracted by the human body key point recognition system and the charged body recognition system. , because the signal encounters interference sources such as AC wires and strong electromagnetic fields during the transmission process, the recognition module encounters an unrecognizable phenomenon when performing action extraction, which leads to misjudgment, resulting in human body key point recognition systems and charged body recognition systems. The accuracy rate of identification has declined, which affects the accuracy rate of active early warning of patented technology.

That is, the key point recognition system of the human body and the charged body recognition system in the existing patented technology directly recognize the signal collected by the camera without processing the signal, resulting in the interference encountered in the signal transmission process, which leads to the failure of motion extraction. Unrecognizable phenomena will affect the accuracy of active early warning.

Therefore the utility model provides a kind of novel solution to solve this problem.

Contents of the invention

In view of the deficiencies in the existing technology, the purpose of this utility model is to provide a safety operation control circuit based on artificial intelligence, which effectively solves the problem that the existing patented technology directly recognizes the signal collected by the camera without processing it, which affects the The accuracy rate of active warning.

The technical solution is that the safety operation control circuit based on artificial intelligence includes an identification module and a camera. The identification module includes a human body key point identification system, a charged body identification system, and a data fusion system. A processing module, the signal output by the camera passes through the preprocessing module and then outputs an image signal and transmits it to the identification module;

The preprocessing module includes an interference detection circuit and an interference elimination circuit;

The interference detection circuit amplifies, calculates and filters the signal to output the interference signal, and outputs the interference signal to the interference elimination circuit.

Further, one end of the interference detection circuit is connected to the camera, and the other end is connected to one end of the interference elimination circuit.

Further, the interference detection circuit amplifies the signal, performs multiplication, and then performs filtering to obtain the interference signal.

Further, the interference detection circuit amplifies the signal and outputs it to the interference elimination circuit.

Further, the other end of the interference elimination circuit is connected to the identification module, and the interference elimination circuit performs calculation and filtering on the interference signal to obtain an image signal.

Further, the interference elimination circuit multiplies the interference signal and then performs filtering.

Further, the interference elimination circuit outputs the image signal to the identification module after voltage stabilization and impedance matching.

The utility model has realized following beneficial effect:

By arranging a preprocessing module between the camera and the recognition module, i.e., the human body key point recognition system, the charged body recognition system, and the data fusion system, the preprocessing module includes an interference detection circuit and an interference elimination circuit, and the signal output by the camera is To detect and judge whether the interference in the signal will affect the identification result of the identification module, and set up an interference elimination circuit to eliminate the interference in the signal, so that the identification module receives the image signal, and the image signal has no interference, thereby ensuring The recognition accuracy of the recognition module avoids the behavior of the existing patented technology that directly recognizes the signal without processing the signal collected by the camera, thereby improving the accuracy of the active warning.

Description of drawings

Fig. 1 is a schematic diagram of a module of the present invention.

FIG. 2 is a schematic circuit diagram of the interference detection circuit of the present invention.

FIG. 3 is a schematic circuit diagram of the interference elimination circuit of the present invention.

Detailed ways

For the aforementioned and other technical contents, features and effects of the present utility model, they will be clearly presented in the following detailed description of the embodiments with reference to the accompanying drawings 1-3. The structural contents mentioned in the following embodiments are all based on the accompanying drawings of the description.

Various exemplary embodiments of the present utility model will be described below with reference to the accompanying drawings.

The artificial intelligence-based safety operation control circuit includes an identification module and a camera, and the identification module includes a human body key point identification system, a charged body identification system, and a data fusion system. It is characterized in that the safety operation circuit also includes a preprocessing module, After the signal output by the camera passes through the preprocessing module, the image signal is output and transmitted to the identification module;

The preprocessing module includes an interference detection circuit and an interference elimination circuit;

The interference detection circuit amplifies, calculates and filters the signal to output the interference signal, and outputs the interference signal to the interference elimination circuit.

One end of the interference detection circuit is connected to the camera, and the other end is connected to one end of the interference elimination circuit. The interference detection circuit uses the capacitor C1 to amplify the signal output by the camera with the operational amplifier U2B, so as to avoid the occurrence of a large amplitude during the transmission of the signal. The attenuation phenomenon makes the identification module unable to analyze the signal. The operational amplifier U1B follows the amplified signal through the transistor Q1 and then transmits it to the multiplier V1 for multiplication with the standard signal provided by the resistor R7. The standard signal is the preset signal. The signal without interference is placed on the 2 pin of the multiplier V1. The interference is the electromagnetic interference generated by the interference source such as the AC wire and the strong electromagnetic field during the transmission process of the signal, and the multiplier is multiplied by the resistor R5 and the capacitor C4. The interference signal output by the device V1 is low-pass filtered, and the interference signal is judged by the transistor Q2 and the diode D6. If the diode D6 is turned on by the interference signal, it indicates that there is a large interference in the signal at this time, which will cause a problem to the identification module. If the accuracy of the identification results is affected, the diode D6 will conduct the interference elimination circuit, and when the interference signal conducts the triode Q2, it indicates that the interference in the signal is very small, and it will not affect the signal collected by the camera. It will affect the accuracy of the identification result generated by the identification module. At this time, the triode Q2 conducts the thyristor Q3 through the diode D2 and the capacitor C3, and the thyristor Q3 outputs the signal to the interference elimination circuit;

The interference detection circuit includes a resistor R1, one end of the resistor R1 is connected to the camera, the other end of the resistor R1 is connected to the non-inverting terminal of the operational amplifier U2B, and the inverting terminal of the operational amplifier U2B is connected to one end of the resistor R4 and the terminal of the resistor R2 respectively. At one end, the output end of the operational amplifier U2B is respectively connected to the other end of the resistor R4 and the base of the transistor Q1, the collector of the transistor Q1 is connected to one end of the resistor R13, and the emitter of the transistor Q1 is respectively connected to one end of the resistor R3, the multiplier Pin 1 of V1 and the collector of transistor Q1 are respectively connected to one end of resistor R13, and the other end of resistor R13 is respectively connected to one end of resistor R7, one end of resistor R6, the emitter of transistor Q2, the positive power supply VCC, and the multiplier V1 2 pins are connected to the other end of the resistor R7, the output end of the multiplier V1 is connected to one end of the resistor R5, and the other end of the resistor R5 is respectively connected to one end of the capacitor C4, the positive pole of the diode D6, the base of the transistor Q2, the resistor The other end of R6 and the collector of transistor Q2 are respectively connected to one end of resistor R8, the anode of diode D2, and the cathode of diode D2 are respectively connected to one end of capacitor C3 and the control electrode of thyristor Q3, and the other end of capacitor C3 is respectively connected to the other end of resistor R8. One end, the other end of the capacitor C4, the other end of the resistor R3, and the other end of the resistor R2 are connected to the ground.

When the interference elimination circuit is turned on by the diode D6, the diode D6 conducts the thyristor Q4 through the capacitor C5 in the interference elimination circuit, and the thyristor Q4 transmits the signal at this time to the multiplier V2, and the multiplier V2 will The signal and the interference signal are multiplied, and the capacitor C8 and the resistor R9 are used to perform low-pass filtering on the output of the multiplier V2 to obtain the image signal, that is, the signal collected by the camera without interference, so as to avoid the recognition module from detecting the signal collected by the camera. When the image is calculated and analyzed, there are errors. The image signal is stabilized by the triode Q5 and the voltage regulator D3, and the signal output by the interference detection circuit is directly output to the transistor Q5 and the voltage regulator D3 as an image through the thyristor Q3. Stabilize the voltage to avoid excessive amplitude of the image signal, which may cause a surge phenomenon in the identification module, and use capacitor C7, capacitor C6, and inductor L1 to perform impedance matching on the image signal to avoid loss when the image signal is transmitted to the identification module. The problem of streak interference due to the impedance mismatch between the interference elimination circuit and the identification module is avoided;

Described interference elimination circuit comprises multiplier V2, and 1 pin of multiplier V2 is respectively connected the control electrode of thyristor Q4, one end of capacitor C5, the other end of resistance R9 in the interference detection circuit, 2 pins of multiplier V2 and thyristor The cathode of Q4 is connected, the anode of thyristor Q4 is connected with the other end of resistor R5 and one end of capacitor C4 in the interference detection circuit, the output end of multiplier V2 is connected with the other end of resistor R9, and the other ends of resistor R9 are respectively Connect one end of the resistor R10 and one end of the capacitor C8, the other end of the resistor R10 is respectively connected to one end of the resistor R11, the collector of the triode Q5, and the cathode of the thyristor Q3 in the interference detection circuit, and the base of the triode Q5 is respectively connected to the other end of the resistor R11 One end, the negative pole of the regulator tube D3, and the emitter of the triode Q5 are respectively connected to one end of the capacitor C6 and one end of the inductor L1, and the other end of the inductor L1 is respectively connected to one end of the capacitor C7 and the identification module, and the other end of the capacitor C7 is respectively connected to the capacitor C8 The other end of the voltage regulator tube D3, the other end of the capacitor C6, and the other end of the capacitor C3 in the interference detection circuit are connected to the ground.

For example, in actual use, the interference detection circuit receives a wirelessly transmitted signal with an amplitude of 0.8V and a frequency of 480KHz, which also contains 240KHz-320KHz interference, which is amplified by the operational amplifier U1B and then amplified to 3V. At this time, the multiplier V1 multiplies the signal with the standard signal with a frequency of 480KHz and performs low-pass filtering through the resistor R5 and capacitor C4, and the remaining 240KHz-320 KHz interference signal, when the amplitude of the interference signal is 0.5V, Then the transistor Q2 is turned on, which means that the interference in the signal is very small, and it will not affect the signal collected by the camera. At this time, the signal is directly output to the noise elimination circuit. The voltage is stabilized by the transistor Q5 and the regulator D3. When the amplitude of the interference signal is 2.5V, the diode D6 is turned on. At this time, the signal is transmitted to the interference elimination circuit and the interference signal is multiplied by the multiplier V2, and the multiplier V2 is output by the capacitor C8 and the resistor R12. The image signal is obtained by low-pass filtering. At this time, the frequency of the image signal is 480KHz. The amplitude of the image signal is 4.5V after being stabilized by the transistor Q5 and the voltage regulator D3. Impedance is performed by the capacitor C7, the capacitor C6, and the inductor L1. Matches are transmitted to the identification module for corresponding processing.

When the utility model is in use, a preprocessing module is set between the camera and the recognition module, namely the human key point recognition system, the charged body recognition system, and the data fusion system. The preprocessing module includes an interference detection circuit and an interference elimination circuit, one end of the interference detection circuit is connected to the camera, and the other end is connected to one end of the interference elimination circuit. The interference detection circuit uses the capacitor C1 to amplify the signal output by the camera with the operational amplifier U2B, and the operational amplifier U1B amplifies the After the signal is followed by the transistor Q1, it is transmitted to the multiplier V1 and multiplied by the standard signal provided by the resistor R7, and the interference signal output by the multiplier V1 is low-pass filtered by the resistor R5 and the capacitor C4, and the transistor Q2, the diode D6 judges the interference signal. If the diode D6 is turned on by the interference signal, it indicates that there is a large interference in the signal at this time, then the diode D6 conducts the interference elimination circuit, and when the interference signal turns on the transistor Q2, it indicates that the signal The interference that exists in is very small, and does not affect the signal collected by the camera. At this time, the triode Q2 conducts the thyristor Q3 through the diode D2 and the capacitor C3, and the thyristor Q3 outputs the signal to the interference elimination circuit; the interference elimination circuit is in the When the diode D6 is turned on, the diode D6 turns on the thyristor Q4 through the capacitor C5 in the interference elimination circuit, and the thyristor Q4 transmits the signal at this time to the multiplier V2, and the multiplier V2 multiplies the signal and the interference signal operation, and use the capacitor C8 and resistor R12 to low-pass filter the output of the multiplier V2 to obtain the image signal. The image signal is stabilized by the transistor Q5 and the voltage regulator D3, and the signal output by the interference detection circuit is used as the image directly. Output through the thyristor Q3 to the triode Q5 and the voltage regulator D3 for voltage stabilization to avoid the excessive amplitude of the image signal, which may cause a surge phenomenon in the identification module, and use the capacitor C7, capacitor C6, and inductor L1 to perform impedance matching on the image signal , to avoid loss when the image signal is transmitted to the identification module, and also to avoid the problem of fringe interference due to the impedance mismatch between the interference elimination circuit and the identification module.

The utility model realizes the following beneficial effects:

(1) By setting a preprocessing module between the camera and the recognition module, namely the human key point recognition system, the charged body recognition system, and the data fusion system, the preprocessing module includes an interference detection circuit and an interference elimination circuit, and the communication camera The output signal is detected and judged, whether the interference in the signal will affect the identification result of the identification module, and the interference elimination circuit is set to eliminate the interference in the signal, so that the identification module receives the image signal without interference. , so as to ensure the accuracy of recognition by the recognition module, and avoid the occurrence of the existing patented technology that directly recognizes the signal without processing the signal collected by the camera, thereby improving the accuracy of the active warning;

(2) The set interference detection circuit uses the operational amplifier U1B to amplify the signal, and uses the multiplier V1, the resistor R5, and the capacitor C4 to obtain the interference signal, and uses the transistor Q2 and the diode D6 to judge whether the interference will be generated by the identification module The recognition results will affect the accuracy, and when it is judged that there will be an impact, the interference elimination circuit will be activated, so as to avoid the phenomenon of blindly eliminating interference to the new height in the camera, thereby ensuring the accuracy of the signal;

(3) The set interference elimination circuit uses multiplier V2, resistor R9, and capacitor C8 to eliminate interference on the signal, so as to obtain an image signal without interference, and stabilize the image signal to ensure the safety of the identification module, and use Capacitor C7, capacitor C6, and inductor L1 perform impedance matching on the image signal to avoid loss when the image signal is transmitted to the recognition module, and also to avoid the appearance of stripes on the image, thereby ensuring the recognition accuracy of the recognition module.

Claims (7)

1. The safety operation control circuit based on artificial intelligence comprises an identification module and a camera, wherein the identification module comprises a human body key point identification system, a charged body identification system and a data fusion system, and is characterized by further comprising a preprocessing module, and a signal output by the camera outputs an image signal after passing through the preprocessing module and is transmitted to the identification module;

the preprocessing module comprises an interference detection circuit and an interference elimination circuit;

the interference detection circuit outputs an interference signal after amplifying, calculating and filtering the signal, and outputs the interference signal to the interference elimination circuit.

2. The artificial intelligence based safety operation control circuit according to claim 1, wherein one end of the interference detection circuit is connected to the camera, and the other end is connected to one end of the interference cancellation circuit.

3. The artificial intelligence based safety operation control circuit according to claim 1, wherein the interference detection circuit amplifies the signal, multiplies the amplified signal, and then filters the amplified signal to obtain the interference signal.

4. The artificial intelligence based safety operation control circuit according to claim 1, wherein the interference detection circuit amplifies the signal and outputs the amplified signal to the interference cancellation circuit.

5. The artificial intelligence based safety operation control circuit according to claim 1, wherein the other end of the interference elimination circuit is connected with the identification module, and the interference elimination circuit calculates and filters the interference signal to obtain the image signal.

6. The artificial intelligence based safety operation control circuit according to claim 4, wherein the interference cancellation circuit multiplies the interference signal and then filters the interference signal.

7. The artificial intelligence based safety operation control circuit according to claim 1, wherein the interference cancellation circuit outputs the image signal to the recognition module after voltage stabilization and impedance matching.

Images