CN114313728B - Anti-collision system of tunnel stacker - Google Patents
Anti-collision system of tunnel stacker Download PDFInfo
- Publication number
- CN114313728B CN114313728B CN202111566715.XA CN202111566715A CN114313728B CN 114313728 B CN114313728 B CN 114313728B CN 202111566715 A CN202111566715 A CN 202111566715A CN 114313728 B CN114313728 B CN 114313728B
- Authority
- CN
- China
- Prior art keywords
- image
- stacker
- tunnel
- industrial computer
- programmable logic
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000001514 detection method Methods 0.000 claims abstract description 38
- 238000000034 method Methods 0.000 claims abstract description 18
- 230000008569 process Effects 0.000 claims abstract description 7
- 238000012545 processing Methods 0.000 claims description 40
- 238000004891 communication Methods 0.000 claims description 19
- 238000012549 training Methods 0.000 claims description 7
- 238000005286 illumination Methods 0.000 claims description 6
- 238000010801 machine learning Methods 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 5
- 230000001276 controlling effect Effects 0.000 description 6
- 230000001965 increasing effect Effects 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 230000005540 biological transmission Effects 0.000 description 4
- 230000007423 decrease Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 230000009467 reduction Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 241001292396 Cirrhitidae Species 0.000 description 1
- 230000002238 attenuated effect Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Landscapes
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
- Traffic Control Systems (AREA)
Abstract
The embodiment of the invention discloses a collision avoidance system of a tunnel stacker. The system comprises: the system comprises at least one tunnel stacker, an industrial computer and a programmable logic controller, wherein an image acquisition unit for acquiring a front environment image is arranged on the tunnel stacker; the tunnel stacker is used for sending the advancing front image acquired by the image acquisition unit to the industrial computer in real time in the advancing process in the tunnel; the industrial computer is used for detecting human bodies according to the advancing front image sent by the tunnel stacker, forming human body detection results, and sending the target results of the detected human bodies to the matched programmable logic controller; and the programmable logic controller is used for controlling the matched tunnel stackers to execute a deceleration parking strategy according to the target result so as to prevent the tunnel stackers from colliding pedestrians. The technical scheme of the embodiment of the invention realizes the effect of avoiding collision with pedestrians.
Description
Technical Field
The embodiment of the invention relates to an industrial automation control technology, in particular to a collision avoidance system of a tunnel stacker.
Background
At present, a roadway stacker is used as hoisting and transporting equipment of a stereoscopic warehouse, and mainly works in narrow roadways to transport goods to high-rise shelves.
In the travelling process of the tunnel stacker, the tunnel stacker has high self-height and automatic control, so that potential safety hazards exist for pedestrians approaching to the equipment. Therefore, a new system needs to be proposed to meet the requirement of automatic control safety and ensure the safety of industrial operation.
Disclosure of Invention
The embodiment of the invention provides a collision avoidance system of a tunnel stacker, which is used for realizing the effect of avoiding collision with pedestrians.
The embodiment of the invention provides a collision avoidance system of a tunnel stacker, which comprises: the system comprises at least one tunnel stacker, an industrial computer and a programmable logic device, wherein an image acquisition unit for acquiring a front environment image is arranged on the tunnel stacker;
the tunnel stacker is used for sending the advancing front image acquired by the image acquisition unit to the industrial computer in real time in the advancing process in the tunnel;
The industrial computer is used for detecting human bodies according to the advancing front image sent by the tunnel stacker, forming human body detection results, and sending the target results of the detected human bodies to the matched programmable logic controller;
and the programmable logic controller is used for controlling the matched tunnel stackers to execute a deceleration parking strategy according to the target result so as to prevent the tunnel stackers from colliding pedestrians.
Further, the collision avoidance system of the tunnel stacker includes: the system comprises a unique industrial computer and a unique programmable logic controller, wherein the industrial computer and the programmable logic controller are integrated in the same remote equipment, and the remote equipment is separated from each roadway stacker for deployment; or alternatively
The anti-collision system of the tunnel stacker comprises: the system comprises a unique industrial computer and programmable logic controllers matched with the number of the tunnel stackers, wherein each programmable logic controller is integrated in each tunnel stacker, and the industrial computer is separated from each tunnel stacker for deployment; or alternatively
The anti-collision system of the tunnel stacker comprises: and the programmable logic controllers and the industrial computers are matched with the number of the tunnel stackers, and are respectively integrated in each tunnel stacker.
Further, the industrial computer is specifically for:
Inputting the received target advancing front image into a pre-trained human body detection model, acquiring whether the target advancing front image contains a model output result of a human body or not, and forming a human body detection result in a switching value form aiming at the model output result;
The human body detection model is obtained after a preset machine learning model is trained by using a plurality of pre-labeled training samples, and a first state of the switching value is a target result of detecting a human body.
Further, the industrial computer is specifically further configured to:
Before the received target advancing front image is input into a pre-trained human body detection model, performing image enhancement processing on the target advancing front image so as to adapt to roadway illumination environment; and/or
Before the received target advancing front image is input into a pre-trained human body detection model, anti-shake processing is carried out on the target advancing front image so as to adapt to an image acquisition scene in operation of the roadway stacker.
Further, the industrial computer is further specifically configured to:
Image brightness and/or image contrast of the image in front of the target travel; and when the image enhancement condition is determined to be met, carrying out histogram equalization processing on the gray level image corresponding to the I channel data of the image in front of the target advancing in the HSI color space so as to realize the image enhancement processing on the image in front of the target advancing.
Further, the industrial computer is further specifically configured to:
Repositioning the target advancing front image when the anti-shake condition is determined to be met according to the parallax between the target advancing front image and the front frame comparison image; and according to the repositioning result, performing image clipping processing on the image in front of the target traveling so as to realize anti-shake processing on the image in front of the target traveling.
Further, the programmable logic controller is specifically configured to:
when the switching value of the first state sent by the industrial computer is received, the servo motor in the matched tunnel stacker is controlled to attenuate the output current to zero in a preset time length according to a preset time attenuation curve, so that the speed reduction and stopping are realized.
Further, the industrial computer is also for:
Calculating a safe anti-collision distance according to a preset deceleration parking time length and a standard advancing speed of a tunnel stacker; and calculating according to the safe anti-collision distance to obtain the configuration height and the pitch angle of the image acquisition unit on the roadway stacker, and prompting a user on the calculated configuration height and pitch angle.
Further, the industrial computer is also for:
collecting the historical parking distance from the switching value of the received first state to the running of the successful parking of the roadway stacker, and calculating to obtain the actual average parking distance according to the historical parking distance; if the difference value of the actual average parking distance and the safe anti-collision distance is larger than or equal to a preset threshold value, updating a time attenuation curve set by a programmable logic controller according to the actual average parking distance, and/or calculating to obtain a new configuration height and a new pitch angle of the image acquisition unit on the roadway stacker according to the actual average parking distance, and prompting a user for the new configuration height and the new pitch angle.
Further, for the anti-collision system in which the programmable logic controller and/or the industrial computer are separately deployed from each roadway stacker, the anti-collision system further comprises: the wireless exchanger is also provided with wireless transceiver modules on each tunnel stacker;
The wireless switch is used for building a wireless communication network so as to build communication connection between each tunnel stacker and the industrial computer and/or between each tunnel stacker and the programmable logic controller;
the wireless transceiver module is used for transmitting the advancing front image acquired by the image acquisition unit in real time to the industrial computer;
The wireless transceiver module is also used for receiving the first result of the human body remotely sent by the industrial computer and forwarding the first result to the programmable logic controller in the tunnel stacker or receiving a remote control instruction of the programmable logic controller and forwarding the remote control instruction to the servo motor in the tunnel stacker.
According to the embodiment of the invention, at least one tunnel stacker, an industrial computer, a programmable logic controller and an image acquisition unit are arranged in an anti-collision system of the tunnel stacker, the image acquisition unit arranged on the tunnel stacker acquires images of the advancing front of the tunnel stacker in real time and sends the images to the industrial computer, so that the industrial computer detects human bodies of the received images and sends target results of the detected human bodies to the matched programmable logic controller, the programmable logic controller controls the matched tunnel stacker to execute a deceleration parking strategy according to the target results, a mode for identifying pedestrians in the advancing front of the tunnel stacker is creatively provided, the technical scheme for controlling the tunnel stacker to safely park is achieved, the effect of avoiding collision with pedestrians is achieved, the requirement of automatic control safety is met, no dead angle monitoring of a tunnel is realized, and the safety of industrial operation is ensured.
Drawings
Fig. 1 is a schematic structural view of a pedestrian protection system of a tunnel stacker in a first embodiment of the present invention;
FIG. 2 is a flow chart of a method for detecting a human body by an industrial computer in accordance with a first embodiment of the present invention;
FIG. 3 is a flowchart of a method for enhancing an image of a front image of a target traveling by an industrial computer according to a first embodiment of the present invention;
FIG. 4 is a flowchart of a method for performing anti-shake processing on an image in front of a target travel by an industrial computer according to a first embodiment of the invention;
Fig. 5 is a schematic structural diagram of a collision avoidance system of another roadway stacker in the second embodiment of the present invention.
Detailed Description
Embodiments of the present invention will be described in further detail below with reference to the drawings and examples. It should be understood that the particular embodiments described herein are illustrative only and are not limiting of embodiments of the invention. It should be further noted that, for convenience of description, only some, but not all of the structures related to the embodiments of the present invention are shown in the drawings.
Example 1
Fig. 1 is a schematic structural diagram of a pedestrian collision avoidance system of a tunnel stacker according to a first embodiment of the present invention, where the present embodiment is applicable to situations where the tunnel stacker performs effective deceleration and parking for pedestrians in front when the tunnel stacker works. Taking a roadway stacker as an example, referring to fig. 1, the system may include:
The tunnel stacker 110, the industrial computer 120 and the programmable logic controller 130, an image acquisition unit 140 for acquiring a front environment image is configured on each tunnel stacker 110.
The roadway stacker 110 is configured to send the advancing front image acquired by the image acquisition unit 140 in real time to the industrial computer 120 in the advancing process in the roadway;
The industrial computer 120 is configured to perform human body detection according to the traveling front image sent by the roadway stacker, form a human body detection result, and send a target result of detecting a human body to the matched programmable logic controller 130;
and the programmable logic controller 130 is used for controlling the matched roadway stacker to execute a deceleration parking strategy according to the target result so as to avoid the roadway stacker from colliding pedestrians.
The roadway stacker can be a device for conveying goods among high-rise shelves in a roadway. The human body detection result may be information generated after the industrial computer checks whether there is a human body in the image in front of the travel transmitted by the lane stacker. The human body detection result may include two detection results: the image in front of the roadway stacker comprises a human body, and the image in front of the roadway stacker does not comprise a human body. The target result may be a detection result of the human body contained in the traveling front image sent by the industrial computer inspection roadway stacker, and the target result may be obtained by the industrial computer by screening all the human body detection results. The deceleration parking strategy may be a method that the programmable logic controller generates for the lane stacker according to the target result, which is performed after pedestrians appear in front of the traveling, and parks.
In the embodiment of the invention, the image acquisition unit configured on the tunnel stacker can acquire the image in front of the tunnel stacker in real time, and the image is sent to the matched industrial computer; the industrial computer detects whether pedestrians appear in the advancing front of the tunnel stacker according to the images, so that human body detection results are generated, and the target results of detecting the human body are screened out and sent to the matched programmable logic controller; the programmable logic controller determines that pedestrians appear in front of the advancing direction of the current tunnel stacker according to the target result, so that the tunnel stacker can be controlled to decelerate and stop so as to avoid collision with pedestrians. Correspondingly, if no pedestrian appears in the advancing front, the roadway stacker can continue to work normally.
In one case, the collision avoidance system of the tunnel stacker may include: the system comprises a unique industrial computer and a unique programmable logic controller, wherein the industrial computer and the programmable logic controller are integrated in the same remote equipment, and the remote equipment is separated from each roadway stacker for deployment;
Through the arrangement, hardware investment can be saved to the greatest extent, hardware resources are saved, and particularly, the programmable logic controller is used, and a plurality of tunnel stackers in a tunnel environment can be uniformly controlled through one industrial computer and the programmable logic controller which are integrated in remote equipment, wherein the programmable logic controller and the industrial computer can be in communication connection with each tunnel stacker based on various industrial bus protocols.
In another case, the collision avoidance system of the tunnel stacker may include: the system comprises a unique industrial computer and programmable logic controllers matched with the number of the tunnel stackers, wherein each programmable logic controller is integrated in each tunnel stacker, and the industrial computer is separated from each tunnel stacker for deployment;
Through the arrangement, the communication time delay between the programmable logic controllers and the tunnel stackers is reduced in a mode of increasing the number of the programmable logic controllers, and the programmable logic controllers can timely and effectively control the speed reduction and the parking of the tunnel stackers when receiving the target result of the industrial computer, which is detected by the human body.
In another case, the collision avoidance system of the tunnel stacker may include: and the programmable logic controllers and the industrial computers are matched with the number of the tunnel stackers, and are respectively integrated in each tunnel stacker. That is, a single industrial computer and a single programmable logic controller are used only to control a single lane stacker. At this time, the roadway stacker can complete human body detection and corresponding deceleration parking strategies by the industrial computer and the programmable logic controller which are integrated by the roadway stacker through the advancing front image which is acquired in real time by the image acquisition unit.
Through the arrangement, the number of the programmable logic controllers and the number of the industrial computers are increased, meanwhile, the communication time delay of the programmable logic controllers for remotely sending the advancing front image to the industrial computers and remotely controlling the tunnel stackers is reduced, and the anti-collision speed of the tunnel stackers is optimized to the greatest extent.
Optionally, fig. 2 is a flowchart of human body detection on an image in front of a target traveling by an industrial computer according to a first embodiment of the present invention, and referring to fig. 2, the method specifically may include the following steps:
s210, performing image enhancement processing on the image in front of the target advancing by the industrial computer so as to adapt to roadway illumination environments; and/or performing anti-shake processing on the image in front of the target traveling so as to adapt to the image acquisition scene in the running of the roadway stacker.
Optionally, the industrial computer receives the target advancing front image sent by the tunnel stacker, and may perform image enhancement processing on the target advancing front image only to eliminate the influence (such as image overexposure or darkness) of illumination change (such as daytime or nighttime) on the acquired target advancing front image; the anti-shake processing can be performed only on the image in front of the target traveling so as to eliminate the blurring problem of the image in front of the target traveling, which is acquired by the image acquisition unit due to the motion; the image in front of the target traveling can be subjected to the influence enhancement processing and the anti-shake processing at the same time, so that the image in front of the target traveling can be clearly displayed.
On the basis of the above embodiment, fig. 3 is a flowchart of a method for performing image enhancement processing on an image in front of a target traveling by an industrial computer according to an embodiment of the present invention, and referring to fig. 3, the method may specifically include: image brightness and/or image contrast of the image in front of the target travel; and when the image enhancement condition is determined to be met, carrying out histogram equalization processing on the gray level image corresponding to the I channel data of the image in front of the target advancing in the HSI color space so as to realize the image enhancement processing on the image in front of the target advancing.
The image enhancement condition may be image overexposure or image darkness. Image overexposure may be a loss or complete absence of detail in the highlight portion of the image. Too dark image may be that the brightness of the photographed object is insufficient or that the brightness of the surrounding space is insufficient to cause the brightness of the photographed image to be too low.
Specifically, after receiving the target traveling front image, the industrial computer may acquire the image brightness and/or the image contrast of the target traveling front image, may determine whether the target traveling front image satisfies the image enhancement condition only according to the image brightness, may determine whether the target traveling front image satisfies the image enhancement condition only according to the image contrast, or may determine whether the target traveling front image satisfies the image enhancement condition according to both the image brightness and the image contrast (for example, may set a threshold to determine whether the image brightness or the image contrast satisfies the image enhancement condition). If the image enhancement condition is met, the target advancing front image can be converted into an HSI color space, a gray image corresponding to the I channel data is obtained, and histogram equalization processing is further carried out on the obtained gray image, so that the I channel data of the target advancing front image is updated by using the gray image after the equalization processing, and the image enhancement processing of the target advancing front image is realized.
The method has the advantages that the influence of illumination change on the front image of the target can be eliminated through image enhancement processing according to the actual condition of insufficient illumination in the roadway environment, and then the industrial computer can more accurately detect the human body based on the front image of the target after the image enhancement processing.
On the basis of the foregoing embodiment, fig. 4 is a flowchart of a method for performing anti-shake processing on an image in front of a target traveling by an industrial computer according to an embodiment of the present invention, and referring to fig. 4, the method may specifically include: repositioning the target advancing front image when the anti-shake condition is determined to be met according to the parallax between the target advancing front image and the front frame comparison image; and according to the repositioning result, performing image clipping processing on the image in front of the target traveling so as to realize anti-shake processing on the image in front of the target traveling.
Alternatively, a previous frame comparison image associated with the target travel front image may be acquired; according to the region of interest in the target advancing front image and the front frame comparison image, calculating parallax between the target advancing front image and the front frame comparison image; if the anti-shake processing condition is met according to the parallax, carrying out feature point matching on each feature point in each region of interest; repositioning the region of interest on the image in front of the target travel according to the matching result; and according to the repositioning result, performing image clipping processing on the image in front of the target traveling so as to realize anti-shake processing on the image in front of the target traveling.
The previous frame comparison image may be a frame of a previous frame adjacent to the target advancing front image acquired by a roadway stacker that acquires the target advancing front image, and may be used for comparing with the target advancing front image. The region of interest may be the region of the target that needs to be processed in the forward image and the forward frame alignment image. The anti-shake condition may be that the edge texture of the region of interest is blurred or incomplete. The feature point may be a point where the gray value of the image changes drastically in the region of interest of the target forward image and the forward frame comparison image or a point where the curvature is large on the image edge (i.e., the intersection of two edges).
The region of interest (ROI, region of interest) is specifically a region set in an image by means of a square, circle, ellipse, or irregular polygon, and various operators and functions are commonly used in machine vision software such as Halcon, openCV, matlab to obtain the region of interest, and generally, the region of interest is a region where a moving object, typically a pedestrian, is located.
Specifically, after receiving the target traveling front image, the industrial computer may acquire a front frame comparison image of the target traveling front image, and outline a region of interest of the target traveling front image and the front frame comparison image, thereby calculating parallax of the target traveling front image and the front frame comparison image. Further, whether or not there is shake is judged according to the calculated parallax (for example, a threshold value of the parallax may be set, the existence of shake may be determined if the threshold value is exceeded, the absence of shake may be determined if the threshold value is not exceeded), that is, whether or not the condition of anti-shake processing is satisfied, and if it is determined that the condition of anti-shake processing is satisfied, feature point matching may be performed on each feature point within the region of interest in the target traveling front image and the preceding frame comparison image, thereby repositioning the region of interest in the target traveling front image. Accordingly, image cropping processing is performed on the target traveling front image according to the repositioning result, so that anti-shake processing on the target traveling front image is realized.
The advantage of this arrangement is that the blur problem of the image in front of the target travel acquired by the image acquisition unit due to motion can be eliminated by the anti-shake processing, so that the industrial computer can more accurately detect the human body based on the region of interest in the image in front of the target travel.
S220, the industrial computer inputs the received target advancing front image into a pre-trained human body detection model, acquires whether the target advancing front image contains a model output result of a human body or not, and forms a human body detection result in a switching value form according to the model output result.
The human body detection model may be obtained by training a preset machine learning model using a plurality of pre-labeled training samples, for example, a YOLO v3 model, and of course, those skilled in the art will understand that, in addition to training using the YOLO v3 model to obtain a human body detection model, other machine learning models may be adopted, for example, a convolutional neural network or a support vector product, and training may be performed to obtain the human body detection model, which is not limited in this embodiment. The first state of the switching value may be a target result of detecting a human body. The first state of the switching value may be used to identify that the target forward-of-travel image contains a human body.
The target advancing front image can be an image of advancing front acquired in real time, which is sent to an industrial computer by a roadway stacker. The human body detection model may be a model for detecting whether a human body is contained in the image ahead of the target travel. The model output result may be a detection result of whether the human body is included in the target travel front image by the human body detection model. The first state of the switching value may be a state in which the industrial computer detects that the image ahead of the target travel includes a human body, and may be represented by "1".
Specifically, the target advancing front image through the image enhancement processing and/or the anti-shake processing may be input into a human body detection model trained in advance, whether the target advancing front image contains a human body is detected, and the result is output. Further, the target result of detecting the human body can be sent to a programmable logic device matched with the currently processed roadway stacker in the form of switching value (1). Illustratively, the industrial computer sends a "1" to the matched programmable logic period according to the lane stacker that sent the target forward-of-travel image, indicating that the target forward-of-travel image contains a human body. If the industrial computer judges that the image does not contain a human body according to the target advancing front image sent by the tunnel stacker, the industrial computer can not send any instruction information to the matched programmable logic device.
According to the technical scheme, at least one tunnel stacker, an industrial computer, a programmable logic device and an image acquisition unit are arranged in an anti-collision human system of the tunnel stacker, the image acquisition unit arranged on the tunnel stacker acquires images of the advancing front of the tunnel stacker in real time and sends the images to the industrial computer, so that the industrial computer detects human bodies of the received images and sends target results of the detected human bodies to a matched programmable logic controller, the programmable logic controller controls the matched tunnel stacker to execute a deceleration parking strategy according to the target results, a mode of identifying pedestrians in the advancing front of the tunnel stacker is creatively provided, the technical scheme of controlling the tunnel stacker to safely park is achieved, the effect of avoiding collision of pedestrians by the tunnel stacker is achieved, the requirement of automatic control safety is met, no dead angle monitoring of the tunnel is realized, and the safety of industrial operation is ensured.
Example two
Fig. 5 is a schematic structural diagram of another anti-collision system of a tunnel stacker according to a second embodiment of the present invention, and the present embodiment is further detailed on the above technical solutions, and the technical solutions in the present embodiment may be combined with each of the alternatives in the above one or more embodiments, for the anti-collision system that is disposed separately from each of the tunnel stackers by a programmable logic controller and/or an industrial computer. Taking a roadway stacker as an example, referring to fig. 5, the system may include:
The tunnel stacker 510, the industrial computer 520 and the programmable logic controller 530, wherein the tunnel stacker 510 is provided with an image acquisition unit 540 for acquiring a front environment image;
the roadway stacker 510 is configured to send, to the industrial computer 520, an image of a traveling front acquired in real time by the image acquisition unit 540 during a traveling process in a roadway;
the industrial computer 520 is configured to perform human body detection according to the traveling front image sent by each roadway stacker 510, form a human body detection result, and send a target result of detecting a human body to the matched programmable logic controller 530;
And the programmable logic controller 530 is configured to control the matched roadway stacker 510 to execute a deceleration parking strategy according to the target result, so as to avoid collision with the pedestrian.
Further, the system further comprises a wireless switch 550, and meanwhile, each roadway stacker 510 is further provided with a wireless transceiver module 560;
A wireless switch 550 for establishing a wireless communication network to establish communication connection between each tunnel stacker 510 and the industrial computer 520, and/or between each tunnel stacker and a programmable logic controller;
The wireless transceiver module 560 is configured to send the traveling front image acquired by the image acquisition unit 540 in real time to the industrial computer 520;
The wireless transceiver module 560 is further configured to receive the first result of the human body remotely sent by the industrial computer 520, and forward the first result to the programmable logic controller 530 in the roadway stacker 510, or receive a remote control instruction of the programmable logic controller 530, and forward the remote control instruction to the servo motor in the roadway stacker 510.
In the embodiment of the invention, a wireless switch can be arranged between each tunnel stacker and an industrial computer to assemble a wireless communication network, so that communication connection between each tunnel stacker and the industrial computer is established, an image in front of the tunnel stacker can be acquired in real time through an image acquisition unit configured on the tunnel stacker, the acquired image is sent to a matched industrial computer through a wireless transceiver module, the industrial computer detects whether pedestrians appear in front of the tunnel stacker according to the image, thereby generating a human body detection result, and a target result of detecting a human body is screened out and sent to a matched programmable logic controller; the programmable logic controller determines that pedestrians appear in front of the advancing direction of the current tunnel stacker according to the target result, so that the tunnel stacker can be controlled to decelerate and stop so as to avoid collision with pedestrians. Correspondingly, if no pedestrian appears in the advancing front, the roadway stacker can continue to work normally.
Under the condition, a unique industrial computer and a unique programmable logic controller are arranged in an anti-collision system of the tunnel stacker, the industrial computer and the programmable logic controller are integrated in the same remote equipment, and when the remote equipment is separated from each tunnel stacker, the wireless transceiver module can be used for receiving a remote control instruction of the programmable logic controller and forwarding the remote control instruction to a servo motor in the tunnel stacker.
In another case, when the programmable logic controllers of the anti-collision system of the tunnel stackers are matched with the number of the tunnel stackers, and each programmable logic controller is integrated in each tunnel stackers, the wireless transceiver module can be used for receiving the first result of the human body remotely sent by the industrial computer and forwarding the first result to the programmable logic controller in the tunnel stackers.
In an alternative embodiment of the invention, the lane stacker may be specifically configured to: when the switching value of the first state sent by the industrial computer is received, the servo motor in the matched tunnel stacker is controlled to attenuate the output current to zero in a preset time length according to a preset time attenuation curve, so that the speed reduction and stopping are realized.
The time attenuation curve can be a curve that the control current of the programmable logic controller gradually decreases to 0 along with time, and the control current is used for proportionally controlling the output current of the servo motor in the tunnel stacker to gradually decrease to 0 along with time. Specifically, the programmable logic controller receives the target result of detecting the human body, which is sent by the industrial computer and displayed in the form of switching value, and the programmable logic controller can control the output current of the servo motor in the tunnel stacker to start to decay through small current, and the output current decays to zero in preset time (for example, 1 minute or 20 seconds and the like) according to a preset time decay curve, so that the servo motor stops running, and the tunnel stacker is decelerated and stopped.
In an alternative embodiment of the invention, the industrial computer may also be used to: calculating a safe anti-collision distance according to a preset deceleration parking time length and a standard advancing speed of a tunnel stacker; and calculating according to the safe anti-collision distance to obtain the configuration height and the pitch angle of the image acquisition unit on the roadway stacker, and prompting a user on the calculated configuration height and pitch angle.
The deceleration parking duration may be a total duration from starting to stopping of the traveling speed of the tunnel stacker. The standard travel speed may be a uniformly prescribed travel speed of the lane stacker. The safe anti-collision distance can be the necessary spacing distance between the roadway stacker and the pedestrian in front in the process of traveling to avoid collision with the pedestrian in front when the roadway stacker determines that the pedestrian exists in front of traveling.
Specifically, the deceleration parking duration may be the same as the duration in which the control current set in the time decay curve gradually decreases to 0, or a set proportion of the duration, for example, 90% or 95%, etc.; the standard travel speed may be an average travel speed of a lane stacker during gradual deceleration from a set speed value to 0. Further, a product value of the standard travel speed multiplied by the deceleration parking duration may be used as the safe collision avoidance distance.
Optionally, the industrial computer may calculate the safe collision avoidance distance of the tunnel stacker according to a preset deceleration parking duration of the tunnel stacker and a standard traveling speed of the tunnel stacker. Further, the scientific configuration height and pitch angle of the image acquisition unit on the tunnel stacker can be calculated according to the safe anti-collision distance of the tunnel stacker, and the calculated configuration height and pitch angle are used for prompting a user of the tunnel stacker. The image acquisition units are arranged on the roadway stacker, and the difference of the installation height and the installation angle can influence whether people can be seen or not. The distance between the farthest pedestrian collected by the image collecting unit and the roadway stacker is matched with the safe anti-collision distance.
For example, if the safe crashproof distance is calculated to be 5 meters, the position of the image acquisition unit is installed on the roadway stacker at a position 2 meters away from the ground, the pitch angle is = -30 degrees, and at this time, the image acquisition unit can be controlled to just see a person at a position of 0-5 meters. That is, when a pedestrian is 5 meters away from the roadway stacker, it is "seen" by the roadway stacker, and the roadway stacker starts to execute the deceleration parking strategy and completes parking before traveling forward 5 meters, so that the pedestrian can be prevented from being bumped.
The advantage of setting like this is that through calculating safe crashproof distance, the height and the pitch angle of scientific configuration image acquisition unit can gather the place ahead image of marcing in the target distance, can more effectively realize tunnel stacker crashproof people system anticollision purpose.
In an alternative embodiment of the invention, the industrial computer may also be used to: collecting the historical parking distance from the switching value of the received first state to the running of the successful parking of the roadway stacker, and calculating to obtain the actual average parking distance according to the historical parking distance; if the difference value of the actual average parking distance and the safe anti-collision distance is larger than or equal to a preset threshold value, updating a time attenuation curve set by the programmable logic controller according to the actual average parking distance, and/or calculating to obtain a new configuration height and a new pitch angle of the image acquisition unit on the roadway stacker according to the actual average parking distance, and prompting a user for the new configuration height and the new pitch angle.
The historical parking distance can be the distance traveled by each roadway stacker from the time of receiving the first state switching value to the time of successful parking. The actual average stopping distance may be the distance the lane stacker travels from receiving the first status switch amount to the actual stopping successfully. The actual average stopping distance may be a statistical average of a plurality of historical stopping distances.
Specifically, the industrial computer can collect the historical parking distance from the reception of the first state switching value to the successful parking travel of each tunnel stacker controlled by the industrial computer, so as to calculate the actual average parking distance. If the difference between the calculated actual average parking distance and the safe crashproof distance is greater than or equal to a preset threshold (for example, 0.1 meter), that is, the actual average parking distance is greater than the safe crashproof distance by a larger error value, the roadway stacker can not be guaranteed to effectively avoid the pedestrians according to the existing deceleration parking strategy, so that the actual average parking distance needs to be reduced or the safe crashproof distance needs to be increased;
Correspondingly, only the time attenuation curve set by the programmable logic controller can be updated, so that the control current of the programmable logic controller is attenuated to 0 in a shorter time, and the actual average parking distance of each tunnel stacker is reduced;
Or only the configuration height and pitch angle of the image acquisition unit on the roadway stacker can be recalculated, so that the image acquisition unit can see pedestrians at a longer distance, and the safe anti-collision distance can be further increased;
Or the time attenuation curve set by the programmable logic controller can be updated and regulated, and the configuration height and the pitch angle of the image acquisition unit on the tunnel stackers can be recalculated, so that the safe anti-collision distance is increased while the actual average parking distance of each tunnel stacker is reduced, the safety of each tunnel stacker can be further improved, and the collision probability is reduced to the greatest extent.
In addition, the new configuration height and pitch angle can be used for prompting the user of the tunnel stacker.
The advantage of this arrangement is that by updating the time decay curve and the height and pitch angle of the image acquisition unit, it is possible to avoid physical imperfections of the device itself leading to a failure of the theoretical safe anti-collision distance.
Optionally, a ModBus communication protocol may be used to generate a transmission data packet matched with the target result of the detected human body, and return the transmission data packet to the tunnel stacker matched with the target result.
The ModBus communication protocol may be a connection communication method commonly used between industrial electronic devices. The sending data packet can be a data packet generated by the industrial computer according to the human body detection result by adopting a ModBus communication protocol, and can be sent between the industrial computer and the roadway stacker.
Specifically, after the detection of the image in front of the target traveling is completed by the industrial computer, a ModBus communication protocol can be adopted to generate a transmission data packet carrying the IP address of the tunnel stacker matched with the target result and the target result, and the transmission data packet is returned to a programmable logic control device in the matched tunnel stacker to complete the communication between the industrial computer and the tunnel stacker.
Or the industrial computer completes the detection of the image in front of the target advancing, generates a matched target result, then sends the target result to a programmable logic control device in the same remote equipment, after generating a corresponding remote control instruction based on a preset deceleration parking strategy, the programmable logic control device can adopt a ModBus communication protocol to generate a sending data packet carrying the IP address of the tunnel stacker matched with the target result and the target result, and returns the sending data packet to the matched tunnel stacker to complete the communication between the programmable logic control device and the tunnel stacker.
According to the technical scheme, at least one tunnel stacker, an industrial computer, a programmable logic control device, an image acquisition unit, a wireless switch and a wireless receiving and transmitting module are arranged in an anti-collision human system of the tunnel stacker, the image acquisition unit configured on the tunnel stacker acquires images in front of the tunnel stacker in real time, the wireless receiving and transmitting module transmits the acquired images to the industrial computer through the wireless switch, so that the industrial computer detects human bodies of the received images, and transmits a detected target result of the human bodies to a matched programmable logic controller, the programmable logic controller transmits a remote control instruction to the matched tunnel stacker through the wireless receiving and transmitting module according to the target result, the control instruction is further transmitted to a servo motor in the tunnel stacker, the current tunnel stacker is controlled to execute a deceleration parking strategy, a technical scheme for identifying pedestrians in front of the tunnel stacker is creatively provided, the effect of preventing the tunnel stacker from collision is achieved, the requirement of automatic control safety is met, no dead angle is met, and safety of industrial operation is guaranteed.
Note that the above is only a preferred embodiment of the present invention and the technical principle applied. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, while the invention has been described in connection with the above embodiments, the invention is not limited to the embodiments, but may be embodied in many other equivalent forms without departing from the spirit or scope of the invention, which is set forth in the following claims.
Claims (6)
1. An anti-collision system for a roadway stacker, comprising: the system comprises at least one tunnel stacker, an industrial computer and a programmable logic controller, wherein an image acquisition unit for acquiring a front environment image is arranged on the tunnel stacker;
the tunnel stacker is used for sending the advancing front image acquired by the image acquisition unit to the industrial computer in real time in the advancing process in the tunnel;
The industrial computer is used for detecting human bodies according to the advancing front image sent by the tunnel stacker, forming human body detection results, and sending the target results of the detected human bodies to the matched programmable logic controller;
The programmable logic controller is used for controlling the matched tunnel stacker to execute a deceleration parking strategy according to the target result so as to prevent the tunnel stacker from colliding pedestrians;
industrial computers are used in particular for: inputting the received target advancing front image into a pre-trained human body detection model, acquiring whether the target advancing front image contains a model output result of a human body or not, and forming a human body detection result in a switching value form aiming at the model output result; the human body detection model is obtained by training a preset machine learning model by using a plurality of pre-labeled training samples, and the first state of the switching value is a target result of detecting a human body;
The programmable logic controller is specifically configured to: when the switching value of the first state sent by the industrial computer is received, controlling a servo motor in the matched tunnel stacker to attenuate the output current to zero in a preset time length according to a preset time attenuation curve so as to realize deceleration parking;
the industrial computer is also for: calculating a safe anti-collision distance according to a preset deceleration parking time length and a standard advancing speed of a tunnel stacker; calculating according to the safe anti-collision distance to obtain the configuration height and the pitch angle of the image acquisition unit on the roadway stacker, and prompting a user on the calculated configuration height and pitch angle;
The industrial computer is also for: collecting the historical parking distance from the switching value of the received first state to the running of the successful parking of the roadway stacker, and calculating to obtain the actual average parking distance according to the historical parking distance; if the difference value of the actual average parking distance and the safe anti-collision distance is larger than or equal to a preset threshold value, updating a time attenuation curve set by the programmable logic controller according to the actual average parking distance, and/or calculating to obtain a new configuration height and a new pitch angle of the image acquisition unit on the roadway stacker according to the actual average parking distance, and prompting a user for the new configuration height and the new pitch angle.
2. The system of claim 1, wherein the man-collision avoidance system of the roadway stacker comprises: the system comprises a unique industrial computer and a unique programmable logic controller, wherein the industrial computer and the programmable logic controller are integrated in the same remote equipment, and the remote equipment is separated from each roadway stacker for deployment; or alternatively
The anti-collision system of the tunnel stacker comprises: the system comprises a unique industrial computer and programmable logic controllers matched with the number of the tunnel stackers, wherein each programmable logic controller is integrated in each tunnel stacker, and the industrial computer is separated from each tunnel stacker for deployment; or alternatively
The anti-collision system of the tunnel stacker comprises: and the programmable logic controllers and the industrial computers are matched with the number of the tunnel stackers, and are respectively integrated in each tunnel stacker.
3. The human collision avoidance system of claim 1 wherein the industrial computer is further specifically configured to:
Before the received target advancing front image is input into a pre-trained human body detection model, performing image enhancement processing on the target advancing front image so as to adapt to roadway illumination environment; and/or
Before the received target advancing front image is input into a pre-trained human body detection model, anti-shake processing is carried out on the target advancing front image so as to adapt to an image acquisition scene in operation of the roadway stacker.
4. A human collision avoidance system as claimed in claim 3, wherein the industrial computer is further specifically for:
Image brightness and/or image contrast of the image in front of the target travel; and when the image enhancement condition is determined to be met, carrying out histogram equalization processing on the gray level image corresponding to the I channel data of the image in front of the target advancing in the HSI color space so as to realize the image enhancement processing on the image in front of the target advancing.
5. A human collision avoidance system as claimed in claim 3, wherein the industrial computer is further specifically for:
Repositioning the target advancing front image when the anti-shake condition is determined to be met according to the parallax between the target advancing front image and the front frame comparison image; and according to the repositioning result, performing image clipping processing on the image in front of the target traveling so as to realize anti-shake processing on the image in front of the target traveling.
6. The pedestrian protection system of claim 2, wherein the pedestrian protection system for a separate deployment of a programmable logic controller and an industrial computer from each of the lane stackers, or a separate deployment of an industrial computer from each of the lane stackers, further comprises: the wireless exchanger is also provided with wireless transceiver modules on each tunnel stacker;
The wireless switch is used for building a wireless communication network so as to build communication connection between each tunnel stacker and the industrial computer and/or between each tunnel stacker and the programmable logic controller;
the wireless transceiver module is used for transmitting the advancing front image acquired by the image acquisition unit in real time to the industrial computer;
The wireless transceiver module is also used for receiving the first result of the human body remotely sent by the industrial computer and forwarding the first result to the programmable logic controller in the tunnel stacker or receiving a remote control instruction of the programmable logic controller and forwarding the remote control instruction to the servo motor in the tunnel stacker.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111566715.XA CN114313728B (en) | 2021-12-20 | 2021-12-20 | Anti-collision system of tunnel stacker |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111566715.XA CN114313728B (en) | 2021-12-20 | 2021-12-20 | Anti-collision system of tunnel stacker |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114313728A CN114313728A (en) | 2022-04-12 |
| CN114313728B true CN114313728B (en) | 2024-06-07 |
Family
ID=81055300
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111566715.XA Active CN114313728B (en) | 2021-12-20 | 2021-12-20 | Anti-collision system of tunnel stacker |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114313728B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103158620A (en) * | 2013-03-25 | 2013-06-19 | 中国电子科技集团公司第三十八研究所 | Vehicle pedestrian detection tracking early warning system |
| CN204197778U (en) * | 2014-05-19 | 2015-03-11 | 国家电网公司 | A kind of three-dimensional storehouse lane stacker anti-collision human closing appliance |
| CN107124542A (en) * | 2016-02-25 | 2017-09-01 | 珠海格力电器股份有限公司 | The stabilization treating method and apparatus of image |
| CN107886034A (en) * | 2016-09-30 | 2018-04-06 | 比亚迪股份有限公司 | Driving based reminding method, device and vehicle |
| CN109285122A (en) * | 2017-07-20 | 2019-01-29 | 阿里巴巴集团控股有限公司 | A kind of method and apparatus carrying out image procossing |
| CN110033417A (en) * | 2019-04-12 | 2019-07-19 | 江西财经大学 | A kind of image enchancing method based on deep learning |
| CN112406967A (en) * | 2019-08-23 | 2021-02-26 | 盟立自动化股份有限公司 | Railcar system, railcar, and visual sensing device |
| CN112784725A (en) * | 2021-01-15 | 2021-05-11 | 北京航天自动控制研究所 | Pedestrian anti-collision early warning method and device, storage medium and forklift |
-
2021
- 2021-12-20 CN CN202111566715.XA patent/CN114313728B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103158620A (en) * | 2013-03-25 | 2013-06-19 | 中国电子科技集团公司第三十八研究所 | Vehicle pedestrian detection tracking early warning system |
| CN204197778U (en) * | 2014-05-19 | 2015-03-11 | 国家电网公司 | A kind of three-dimensional storehouse lane stacker anti-collision human closing appliance |
| CN107124542A (en) * | 2016-02-25 | 2017-09-01 | 珠海格力电器股份有限公司 | The stabilization treating method and apparatus of image |
| CN107886034A (en) * | 2016-09-30 | 2018-04-06 | 比亚迪股份有限公司 | Driving based reminding method, device and vehicle |
| CN109285122A (en) * | 2017-07-20 | 2019-01-29 | 阿里巴巴集团控股有限公司 | A kind of method and apparatus carrying out image procossing |
| CN110033417A (en) * | 2019-04-12 | 2019-07-19 | 江西财经大学 | A kind of image enchancing method based on deep learning |
| CN112406967A (en) * | 2019-08-23 | 2021-02-26 | 盟立自动化股份有限公司 | Railcar system, railcar, and visual sensing device |
| CN112784725A (en) * | 2021-01-15 | 2021-05-11 | 北京航天自动控制研究所 | Pedestrian anti-collision early warning method and device, storage medium and forklift |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114313728A (en) | 2022-04-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| RU2735340C1 (en) | Parking control method and parking control device | |
| US9275545B2 (en) | System and method for monitoring vehicle traffic and controlling traffic signals | |
| US20170305335A1 (en) | Indent-Indication System For An Automated Vehicle | |
| CN110674733A (en) | Multi-target detection and identification method and driving assistance method and system | |
| CN108133484B (en) | Automatic driving processing method and device based on scene segmentation and computing equipment | |
| EP3451105B1 (en) | Automated speed control system | |
| CN113744564B (en) | Intelligent networking bus road cooperative control system based on edge calculation | |
| CN113853640B (en) | electronic control device | |
| CN111417561B (en) | Server for realizing automatic remote control of mobile transport means and automatic remote control method of mobile transport means | |
| CN110936953A (en) | Method and device for providing an image of the surroundings and motor vehicle having such a device | |
| EP3524935B1 (en) | Vehicle perception-data gathering system and method | |
| CN111984008A (en) | Robot control method, device, terminal and storage medium | |
| CN113228131A (en) | Method and system for providing ambient data | |
| CN114313728B (en) | Anti-collision system of tunnel stacker | |
| KR102158169B1 (en) | Lane detection apparatus | |
| JP2021163374A (en) | Operation management apparatus and operation management method of autonomous vehicle | |
| JP7115869B2 (en) | Map generation system | |
| CN110045721B (en) | Method for assisting vehicle in traveling and device therefor | |
| CN114877910A (en) | Driving planning method, electronic device and computer storage medium | |
| US20230252903A1 (en) | Autonomous driving system with air support | |
| WO2022267266A1 (en) | Vehicle control method based on visual recognition, and device | |
| CN111845724B (en) | Obstacle avoidance method and device for automatically driving vehicle and vehicle | |
| CN113126631A (en) | Automatic brake control method and device for AGV (automatic guided vehicle), electronic equipment and storage medium | |
| CN109102706B (en) | Method, device and system for controlling traffic light | |
| KR20220073874A (en) | Moving direction control system of autonomous driving vehicle using traffic environment information at short and long distance |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |