Construction equipment safety system and method for setting risk of object by using construction equipment safety system
The construction equipment safety system uses AI to identify safety devices and allows operators to disable known low-risk alarms, addressing visibility and noise challenges, enhancing safety and efficiency.
Patent Information
- Application Number
- PCT/KR2025/095035
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2024-08-07
- Filing Date
- 2025-03-20
- Publication Date
- 2026-02-12
AI Technical Summary
Construction equipment operators face challenges in recognizing all dangerous situations due to limited field of vision and high noise levels, leading to potential accidents from constant safety device alarms, which can be ignored, reducing their effectiveness.
A construction equipment safety system with a detection unit, control unit, and interface unit that uses AI neural networks to identify safety devices and allows operators to selectively disable collision risk warnings for known, low-risk objects.
Enhances operator convenience by preventing unnecessary alarms for known safety devices, improving work efficiency and safety by allowing controlled risk management.
Smart Images

Figure KR2025095035_12022026_PF_FP_ABST
Abstract
Description
Construction equipment safety system and method for setting the risk level of an object using the construction equipment safety system
[0001] The present invention relates to a construction equipment safety system configured to enable a worker inside construction equipment to select whether to release a risk for a safety device placed at a construction site, and a method for setting the risk level of an object using the construction equipment safety system.
[0002] With the recent rapid development of artificial intelligence, AI technology is being applied in various fields, and in the construction equipment field, a safety system is being introduced that analyzes camera images using artificial intelligence to recognize and distinguish between workers (people) and non-human objects around construction equipment.
[0003] Meanwhile, when working at a construction site, the noise level is high due to the nature of the site, which reduces concentration, and it is difficult for workers (drivers) working inside the construction equipment to recognize all dangerous situations on site because their field of vision is limited by the various work tools connected to the construction equipment.
[0004] To address these issues, various types of safety devices are deployed and installed at construction sites. One example of such safety devices is the installation of signalmen. Signalmen communicate with construction equipment operators to direct the operation and operation of construction equipment and detect danger signals to enable immediate response. Another example of safety devices is the installation of safety fences. Safety fences primarily function as barriers, preventing workers from entering hazardous areas or designating safe movement routes. Another example of safety devices is the installation of lava cones. These cones are installed in traffic areas of construction sites and serve as traffic safety facilities to control vehicles on site.
[0005] Likewise, when working on a construction site equipped with various types of safety devices using an AI-based safety system, the safety system recognizes the safety devices as objects and sounds an alarm. If the safety devices are placed adjacent to the construction equipment in operation, the constant sounding of alarms can cause inconvenience to the operator.
[0006] Furthermore, drivers are more likely to be aware of the safety fences and lava cones placed in the same location, as well as the signals that constantly communicate with the driver. However, if constant warnings sound, drivers may become increasingly fatigued and eventually turn off the safety system altogether. This can actually prevent them from detecting objects that pose a risk of collision, potentially leading to accidents.
[0007] The purpose of one disclosure of the present invention is to set a safety device that has a low risk of collision with construction equipment because the worker knows the location of various objects detected at a construction site, so that a warning notifying of the risk of collision is not displayed according to the worker's choice.
[0008] One object of the present invention is to maintain a risk-free state without having to repeatedly select risk-free for a safety device from which risk has been released.
[0009] However, the problems to be solved by the present invention are not limited to the problems mentioned above, and other problems not mentioned can be clearly understood based on the description below.
[0010] A construction equipment safety system according to one disclosure of the present invention may include a detection unit installed in a construction equipment and detecting a predetermined area around the construction equipment; a control unit receiving a detection result from the detection unit and detecting an object existing in the predetermined area; and an interface unit receiving information about an object detected by the control unit and warning a worker on board the construction equipment of a collision risk.
[0011] Alternatively, the control unit may determine whether the detected object is a safety device installed at a construction site to ensure safe operation of the construction equipment, and if the detected object is the safety device, may inquire of the worker through the interface unit whether to release the risk of the safety device.
[0012] Alternatively, the safety device may include at least one of a signal man, a safety fence, and a rubber cone that controls the operation of the construction equipment.
[0013] Alternatively, the control unit may include a processor that executes an artificial intelligence neural network that has completed pre-training to detect objects present in the predetermined area.
[0014] Alternatively, the control unit may control the interface unit to output a pop-up message to inquire whether the risk has been released, and the pop-up message may vary depending on the type of the safety device.
[0015] Alternatively, the control unit may receive a user input via the interface unit to set whether to release the detected safety device.
[0016] Alternatively, the control unit may turn off the collision risk warning for the safety device upon receiving user input approving the disabling of the detected safety device.
[0017] Alternatively, the control unit may determine whether the detected object is a safety device for which a risk release has been previously set, if the detected object is a safety device.
[0018] Alternatively, if the control unit determines that the detected object is a safety device for which a risk release has been previously set, it may immediately turn off the collision risk warning without inquiring whether the risk for the safety device has been released.
[0019] A method according to one disclosure of the present invention is a method for setting the risk level of an object detected in a certain area around construction equipment at a construction site, the method including the steps of: detecting an object existing in the certain area; and determining whether the detected object is a safety device installed at the construction site to ensure safe operation of the construction equipment, and setting the risk level for the safety device.
[0020] Alternatively, the step of setting the risk level may ask the worker whether to release the risk of the safety device through an interface unit provided in the construction equipment.
[0021] Alternatively, the step of detecting the object may execute an artificial intelligence neural network that has completed pre-training to detect objects existing in the predetermined area.
[0022] Alternatively, the step of setting the risk level may turn off the collision risk warning for the safety device upon receiving a user input approving the release of the risk of the safety device detected through the interface unit.
[0023] Alternatively, the step of setting the risk level may determine whether the detected object is a safety device for which a risk release has been previously set, if the detected object is a safety device.
[0024] Alternatively, the step of setting the risk level may immediately turn off the collision risk warning without inquiring whether the risk for the safety device has been released, if it is determined that the detected object is a safety device for which a risk release has been previously set.
[0025] According to one disclosure of the present invention, for a safety device detected at a construction site, by asking a worker through an interface whether to release the danger and receiving an input from the worker to set the danger release, and at the same time setting the warning for the safety device not to be displayed, the worker can prevent the warning from continuously sounding for a safety device whose location is already known by the worker and thus has a low collision risk, thereby increasing work efficiency.
[0026] According to one disclosure of the present invention, by configuring to determine whether a detected safety device is a safety device that has been previously released from danger, a state of danger release is maintained without the need to repeatedly select danger release for a safety device that has been released from danger, and convenience of the operator can be improved.
[0027] Figure 1 is a block diagram of a construction equipment safety system according to one disclosure of the present invention.
[0028] FIG. 2 is a drawing for explaining various objects that can be detected at a construction site in one disclosure of the present invention.
[0029] FIGS. 3A to 3C are drawings for explaining an example in which a pop-up message asking whether to release the risk is displayed through an interface unit in one disclosure of the present invention.
[0030] Figure 4 is a flowchart showing the flow of a method according to one disclosure of the present invention.
[0031] FIG. 5 is a flowchart showing the detailed flow of the risk setting step in a method according to one disclosure of the present invention.
[0032] FIG. 6 is a flowchart showing the detailed flow of a step for determining whether a recognized safety device is a safety device that has been released from danger in a method according to one disclosure of the present invention.
[0033] Below, embodiments of the present disclosure are described in detail with reference to the attached drawings so that those skilled in the art can easily implement the present disclosure. The embodiments presented in this disclosure are provided to enable those skilled in the art to utilize or implement the contents of the present disclosure. Accordingly, various modifications to the embodiments of the present disclosure will be apparent to those skilled in the art. That is, the present disclosure may be implemented in various different forms and is not limited to the embodiments described below.
[0034] Throughout the specification of this disclosure, identical or similar drawing numbers refer to identical or similar components. Furthermore, for clarity in the description of this disclosure, drawing numbers for parts unrelated to the description of this disclosure may be omitted in the drawings.
[0035] The term "or" as used herein is intended to mean an inclusive "or" rather than an exclusive "or." That is, unless otherwise specified herein or clear from context, "X employs A or B" should be understood to mean either of the natural inclusive permutations. For example, unless otherwise specified herein or clear from context, "X employs A or B" can be interpreted to mean either X employs A, X employs B, or X employs both A and B.
[0036] The term “at least one of A or B” as used in this disclosure should be interpreted to refer to all of A, B, and combinations of A and B.
[0037] The term "and / or" as used herein should be understood to refer to and include all possible combinations of one or more of the related concepts listed.
[0038] The terms "comprises" and / or "comprising" as used herein should be understood to mean the presence of certain features and / or components. However, it should be understood that the terms "comprises" and / or "comprising" do not exclude the presence or addition of one or more other features, other components, and / or combinations thereof.
[0039] Unless otherwise specified in this disclosure or unless the context makes it clear that the singular form is intended to be referred to, the singular should generally be construed to include “one or more.”
[0040] The term "Nth (N is a natural number)" used in the present disclosure can be understood as an expression used to mutually distinguish components of the present disclosure based on a predetermined standard such as a functional perspective, a structural perspective, or convenience of explanation. For example, components performing different functional roles in the present disclosure can be distinguished as a first component or a second component. However, components that are substantially the same within the technical spirit of the present disclosure but must be distinguished for convenience of explanation may also be distinguished as a first component or a second component.
[0041] The term "connected" as used in this disclosure should be interpreted to include not only cases where components are "directly connected" but also cases where other components are "present" between them and cases where they are "electrically connected" with other components interposed between them.
[0042] Meanwhile, the term "module" or "unit" used in the present disclosure can be understood as a term referring to an independent functional unit that processes computing resources, such as a computer-related entity, firmware, software or a part thereof, hardware or a part thereof, or a combination of software and hardware. At this time, the "module" or "unit" may be a unit composed of a single element, or a unit expressed as a combination or set of multiple elements. For example, as a narrow concept, a "module" or "unit" may refer to a hardware element of a computing device or a set thereof, an application program that performs a specific function of software, a processing process implemented through software execution, or a set of instructions for program execution, etc. In addition, as a broad concept, a "module" or "unit" may refer to the computing device itself that constitutes the system, or an application running on the computing device, etc. However, since the above-described concept is only an example, the concept of “module” or “part” may be defined in various ways within a range understandable to those skilled in the art based on the contents of the present disclosure.
[0043] The term "model" as used herein may be understood as a system implemented using mathematical concepts and language to solve a specific problem, a set of software units for solving a specific problem, or an abstract model of a processing process for solving a specific problem. For example, a neural network "model" may refer to the entire system implemented as a neural network that has problem-solving capabilities through learning. In this case, the neural network can have problem-solving capabilities by optimizing the parameters connecting nodes or neurons through learning. A neural network "model" may include a single neural network or a set of neural networks that are a combination of multiple neural networks.
[0044] Additionally, the artificial intelligence neural network referred to in this disclosure may be a neural network trained through supervised learning. Here, supervised learning is a machine learning method for inferring a function from training data. Among these inferred functions, outputting continuous values is called regression analysis, and predicting and outputting the class of an input vector is called classification. In supervised learning, an artificial neural network is trained with labels for training data. Here, the label may refer to the correct answer (or output value) that the artificial neural network must infer when training data is input to the artificial neural network. The correct answer that the artificial neural network must infer when training data is input may be called a label or labeling data, and setting a label on the training data for the purpose of learning the artificial neural network may be called labeling. In this case, the training data and the corresponding labels constitute a training set, and can be input to the artificial neural network in the form of a training set. Meanwhile, training data represents multiple features, and labeling the training data can mean that the features represented by the training data are labeled. In this case, the training data can represent the features of the input object in vector form. An artificial neural network can infer a function regarding the relationship between the training data and the labeled data using the training data and the labeled data. Then, the parameters of the artificial neural network can be determined (optimized) through the evaluation of the inferred function. Loss functions can be used as an indicator for evaluating the inferred function. The loss function is a score value generated by receiving the correct answer and the prediction as input, and it serves as an indicator to determine how well the neural network predicted the correct answer.A smaller value for this loss function indicates greater prediction accuracy for the artificial neural network. The loss function can be appropriately selected depending on the specific problem or data set. For example, for a convolutional neural network model, loss functions such as cross-entropy loss and mean squared error loss can be used.
[0045] The term "data" used in this disclosure may include "images," signals, and the like. The term "image" used in this disclosure may refer to multidimensional data composed of discrete image elements. In other words, "image" may be understood as a term referring to a digital representation of an object visible to the human eye. For example, "image" may refer to multidimensional data composed of elements corresponding to pixels in a two-dimensional image. "Image" may refer to multidimensional data composed of elements corresponding to voxels in a three-dimensional image.
[0046] The explanation of the above terms is intended to aid understanding of the present disclosure. Therefore, unless explicitly stated as limiting the contents of the present disclosure, it should be noted that the above terms are not intended to limit the technical ideas of the present disclosure.
[0047] Hereinafter, an embodiment of the present invention will be described in detail with reference to the attached drawings.
[0048] FIG. 1 is a block diagram of a construction equipment safety system according to one disclosure of the present invention, and FIG. 2 is a drawing for explaining various objects that can be detected at a construction site according to one disclosure of the present invention.
[0049] First, referring to FIG. 1, a construction equipment safety system (10) according to one disclosure of the present invention may include a detection unit (100), a control unit (200), and an interface unit (300).
[0050] The detection unit (100) is equipped on the construction equipment (1) and is configured to monitor a certain area around the construction equipment (1) and detect objects that may collide with the construction equipment (1) during operation of the construction equipment (1).
[0051] The detection unit (100) may be, for example, a camera equipped to capture real-time images of a predetermined area in front, behind, and on both sides of the construction equipment (1). The video images captured in real-time by the detection unit (100) are transmitted to the control unit (200), which will be described later, and the control unit (200) can recognize objects included in the video images.
[0052] Meanwhile, a construction equipment (1) equipped with a safety system (10) according to one disclosure of the present invention may include a lower drive body (1a) and an upper rotating body (1b) positioned above the lower drive body (1a) and capable of rotating 360 degrees. A driver's cabin (1c) may be provided in the upper rotating body (1b) for a worker (driver) operating the construction equipment (1) to board, and a bucket and bucket arm (1d), which are work tools, may be positioned in front of the driver's cabin (1c). (See FIG. 2)
[0053] At this time, the bucket and bucket arm (1d) are structurally arranged in front of the driver's cab (1c), so the field of vision of the operator performing driving and work inside the driver's cab (1c) may be limited. Therefore, to assist the operator's vision, a monitor may be installed inside the driver's cab (1c) so that the video images captured by the detection unit (100) may be displayed in real time.
[0054] The control unit (200) is configured to receive the detection results from the detection unit (100) and detect objects existing in a certain area around the construction equipment (1).
[0055] The control unit (200) can control the overall operation of the construction equipment safety system (10) of the present invention. Here, the control unit (200) can include all types of devices capable of processing data, such as a processor. Here, the 'processor' can mean a data processing device built into hardware, which has a physically structured circuit to perform a function expressed by a code or command included in a program, for example. As an example of a data processing device built into hardware, it can encompass processing devices such as a microprocessor, a central processing unit (CPU), a processor core, a multiprocessor, an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), a graphics processing unit (GPU), and a neural processing unit, but the scope of the present invention is not limited thereto.
[0056] The processor included in the control unit (200) can execute an artificial intelligence neural network that has completed pre-training for various types of objects. For example, the neural network may be based on a convolutional neural network (CNN) model trained to detect objects from images taken of a certain area around construction equipment. More specifically, the neural network may be any one of YOLO (You Only Look Once), SSD (Single Shot Multibox Detector), Faster R-CNN, and Mask R-CNN.
[0057] The control unit (200) can determine whether an object detected by the neural network is a safety device. Here, the safety device may include at least one of a signal, a safety fence, and a rubber cone that control the operation of the construction equipment.
[0058] In order to enable the control unit (200) to determine whether an object is a safety device, the neural network may be pre-trained by labeling the learning images with the type of object and whether it is a safety device.
[0059] For example, a person wearing a white hard hat (or white vest) would be labeled as a general worker, and a person wearing a red hard hat (or red vest) would be labeled as a signalman worker, but the general worker could be labeled as a non-safety device and the signalman as a safety device. For example, a safety fence and a lava cone could be labeled as a safety fence and a lava cone, respectively, but both could be labeled as safety devices.
[0060] As another example, the neural network may be pre-trained by labeling the types of objects in the learning images, and the control unit (200) may additionally perform a process of determining whether the data predicted as a result of the type of object is a safety device (e.g., a signalman, a general worker, a lava cone, a safety fence, etc.) based on the type of object.
[0061] Meanwhile, object detection algorithms that extract features from video images using pre-trained neural networks and classify objects based on them are well known in the art, so a detailed explanation of the algorithm will be omitted here.
[0062] Referring to FIG. 2, multiple objects can be detected in an area captured by a detection unit (100). Safety fences (SD1, SD2, SD3) can be detected in detection areas (R1, R2, R3). Rubber cones (SD4, SD5) can be detected in detection areas (R8, R9). Workers (O1, O2, O3) other than signalmen can be detected in detection areas (R4, R5, R6). Signalmen (SD6) can be detected in detection area (R7). The control unit (200) can determine that among the objects detected in this manner, safety fences, rubber cones, and signalmen (SD1 to SD6) are safety devices.
[0063] Meanwhile, the construction equipment safety system (10) according to one disclosure of the present invention may further include a storage unit (400).
[0064] The storage unit (400) may include a magnetic storage media or a flash storage media, but the scope of the present invention is not limited thereto. The storage unit (400) may include a built-in memory and / or an external memory, and may include a volatile memory such as a DRAM, an SRAM, or an SDRAM, a non-volatile memory such as an OTPROM (one time programmable ROM), a PROM, an EPROM, an EEPROM, a mask ROM, a flash ROM, a NAND flash memory, or a NOR flash memory, a flash drive such as an SSD, a CF (compact flash) card, an SD card, a Micro-SD card, a Mini-SD card, an Xd card, or a memory stick, or a storage device such as an HDD.
[0065] The storage unit (400) may include the previously described pre-trained neural network. When the release of the safety device is approved, a record thereof may be stored in the storage unit (400).
[0066] The interface unit (300) is configured to receive information about an object detected by the control unit (200) and warn a worker (driver) on board the construction equipment (1) of the risk of collision. The interface unit (300) may be configured on a monitor installed inside the driver's cabin (1c) described above.
[0067] The interface unit (300) may include a display unit as a means for visually providing various information related to work to the driver. The display unit may be formed of any one of a light emitting diode (LED), a liquid crystal display (LCD), a plasma display panel, and an organic light emitting diode (OLED). However, this is merely an example, and the display unit may be formed of elements not mentioned.
[0068] The visual information provided through the display unit may include a video image containing the object detection result.
[0069] The interface unit (300) may include an input unit for receiving user input. The input unit generates key input data input by the driver. To this end, the input unit may be composed of a key pad, a dome switch, a touch pad (static / capacitive), etc. In particular, when the touch pad forms a mutual layer structure with the above-described display unit, it may be called a touch screen.
[0070] If the control unit (200) determines that the detected object is a safety device, it can ask the driver via the interface unit (300) whether to release the safety device.
[0071] More specifically, the control unit (200) can control the interface unit (300) to output a pop-up message to inquire whether the risk has been lifted.
[0072] FIGS. 3A to 3C are drawings for explaining an example in which a pop-up message asking whether to release the risk is displayed through an interface unit in one disclosure of the present invention.
[0073] The pop-up message may be configured differently depending on the type of safety device. For example, when a safety fence is detected, a pop-up message (P1) with the content "The detected object is a safety fence. Do you want to turn off the warning?" may be output through the display unit (see FIG. 3a). For example, when a signal water is detected, a pop-up message (P2) with the content "The detected object is a signal water. Do you want to turn off the warning?" may be output through the display unit (see FIG. 3b). For example, when a lava cone is detected, a pop-up message (P3) with the content "The detected object is a lava cone. Do you want to turn off the warning?" may be output through the display unit (see FIG. 3c). As a possible embodiment, the content of the pop-up message may be set by storing a plurality of message samples in the storage unit (400) and having the driver select from among them.
[0074] The control unit (200) can receive a user input for setting whether to release the danger of a detected object through the interface unit (300). More specifically, referring to FIGS. 3A to 3C, the pop-up messages (P1 to P3) can include a GUI component indicating whether to accept (yes) or reject (no) the danger release.
[0075] The control unit (200) can turn off the collision risk warning for a detected object upon receiving a user input confirming the release of the object's hazard. Referring to the examples illustrated in FIGS. 3A to 3C , the driver can input consent to release the safety device's hazard by clicking the "Yes" button in a pop-up message.
[0076] In this way, by asking whether to disable the safety device through a pop-up message, the driver can intuitively understand the safety device disabling setting, and can disable the safety device by performing a simple instruction while working.
[0077] A collision risk warning may also be output for the safety device prior to inputting a risk release. The collision risk warning may be transmitted, for example, in the form of a warning sound, warning message, etc., through a speaker installed inside the driver's cab (1c). Preferably, the collision risk warning may be transmitted when the distance between the detected object and the construction equipment (1) within the detection area of the detection unit (100) falls below a threshold value.
[0078] The control unit (200) can control the speaker to turn off the collision risk warning for the corresponding safety device at the same time as receiving an input approving the risk release. In this case, the control unit (200) can control the speaker so that the collision risk warning for the corresponding safety device is turned off regardless of the distance from the construction equipment (1). For example, referring to FIG. 3A, if the risk for the safety fences (SD1, SD2, SD3) is released, the collision risk warning is not transmitted even if the distance between the safety fences (SD1, SD2, SD3) and the construction equipment (1) becomes below a threshold value. In contrast, the collision risk warning is transmitted for the worker (O1) as soon as the distance from the construction equipment (1) becomes below a threshold value.
[0079] This configuration prevents the constant sounding of warnings for safety devices whose locations the driver already knows and poses a low collision risk, thereby improving work efficiency. Furthermore, the driver can configure the system to receive collision risk warnings for safety devices, allowing the risk level to be adjusted based on driver preference, skill level, and worksite conditions (weather, complexity, etc.), increasing system flexibility.
[0080] In addition to the examples illustrated in Figures 3a through 3c, other embodiments that inquire about and approve the release of a hazard may also fall within the scope of the present invention. For example, instead of displaying a component indicating "yes" or "no" and receiving user input through it, the driver may directly click on a detection area to release the hazard for a safety device detected in that area.
[0081] Meanwhile, the control unit (200) can determine whether the detected object is a safety device for which a risk release has been previously set, if the detected object is a safety device.
[0082] If the control unit (200) determines that the detected object is a safety device for which a risk release has been previously set, it can immediately turn off the collision risk warning without inquiring whether the risk for the safety device has been released.
[0083] For example, whether a safety device has previously been set to be released can be determined by whether the detected safety device is the same type of object as the safety device for which the risk has previously been set to be released.
[0084] For example, whether a safety device has previously been set to be released can be determined by considering whether the detected safety device is the same type of object as the safety device for which the risk has previously been released, and whether the difference between the detection time of the previously released safety device and the detection time of the currently detected safety device is smaller than the preset difference value.
[0085] Specifically, if a safety device is detected and there is no previous risk release record for a similar object, a timestamp (t1_1) may be initially set for the safety device. The timestamp referred to in the present invention may be set for the time of detection. Thereafter, when the driver releases the risk for the safety device, the risk release for the safety device may be recorded in the storage unit (400) along with the timestamp (t1_1).
[0086] When a safety device with a risk release record is re-detected, the time of re-detection (t1_2) is compared with the existing time stamp (t1_1), and if the time difference is less than a preset difference value, the re-detected safety device is determined to be the same safety device as the existing set safety device, and the collision risk warning can be turned off immediately without asking a pop-up message whether the safety device should be released. At this time, the time stamp (t1_1) can be initialized. Here, initializing the time stamp (t1_1) may mean resetting the time stamp to the time (t1_2) at which the safety device was later detected. The risk release record for the re-detected safety device can be recorded in the storage unit (400) together with the reset time stamp (t1_2).
[0087] Meanwhile, if the time difference exceeds the preset difference, the re-detected safety device is determined to be different from the previously set safety device, and a pop-up message can be displayed to inquire again about whether the safety device should be released. At the same time, a timestamp (t2_1) can be initially set for the time the safety device was detected. Thereafter, the operator can be inquired about whether the detected safety device should be released through the interface unit (300).
[0088] Among the safety devices, a signal guard may momentarily disappear from the camera's view and then reappear. Alternatively, a stationary safety fence or lava cone may disappear and reappear in the same location as the upper rotating body (1b) rotates. In this case, the control unit (200) detects the object and displays a pop-up message to re-inquire whether the hazard has been removed. However, if the time until the safety device reappears is very short, continuously inquiring about whether the hazard has been removed can reduce work efficiency.
[0089] According to the present invention, convenience for workers can be improved by releasing a collision risk warning without asking whether the risk has been released for a safety device of the same type.
[0090] Additionally, if a safety device of the same type is detected again after a certain period of time, there is an advantage in being able to re-attract the driver's attention by asking again whether the danger has been lifted.
[0091] FIG. 4 is a flowchart showing the flow of a method according to one disclosure of the present invention, FIG. 5 is a flowchart showing the detailed flow of a risk setting step in a method according to one disclosure of the present invention, and FIG. 6 is a flowchart showing the detailed flow of a step of determining whether a recognized safety device is a safety device whose risk has been released in a method according to one disclosure of the present invention.
[0092] Referring to FIGS. 4 to 6, a method according to one disclosure of the present invention is a method for setting the risk level of an object detected in a certain area around construction equipment at a construction site, which can be performed by the construction equipment safety system (10) described above.
[0093] First, the detection unit (100) detects a certain area around the construction equipment (10) in real time (S100), and the control unit (200) receives the detection result and can detect an object existing in the certain area (S200).
[0094] Object detection can be accomplished by an artificial intelligence neural network that has completed pre-training to detect objects existing in the above-described area. This has been previously discussed in the construction equipment safety system (10) according to one disclosure of the present invention, so any further explanation of this will be omitted here.
[0095] Thereafter, the control unit (200) can determine whether the detected object is a safety device installed at a construction site to ensure safe operation of construction equipment (1), and set the risk level for the safety device. (S300)
[0096] Specifically, in the step of setting the risk level for the safety device (S300), it can be determined whether the detected object is a safety device (S310). If the detected object is not a safety device, the risk for the object is not eliminated and a collision risk warning can be displayed (S360). At this time, preferably, before displaying the collision risk warning, a step of determining whether the distance between the construction equipment (1) and the detected object is less than or equal to a threshold value can be first performed.
[0097] If the detected object is a safety device, it can be determined whether the safety device has previously been set to be released from danger. (S320)
[0098] In order to determine whether a safety device has previously been set to be released, it can be determined whether a record of release of a safety device of the same type as the detected safety device exists. (S321) The record of release of a safety device may be recorded in the storage unit (400).
[0099] If a risk release record exists, the time (t1_2) at which the safety device is detected can be compared with the time stamp (t1_1) preset for the safety device in which the risk release is recorded. (S322) At this time, it is determined whether the time difference between t1_1 and t1_2 is smaller than the preset difference value as a result of the comparison (S324). If the time difference is smaller than the difference value, the safety device detected later is determined to be the same safety device as the safety device for which the risk release was previously set, and the collision risk warning can be turned off immediately without asking whether the risk release is possible through a pop-up message for the safety device in question. (S330)
[0100] Preferably, the timestamp (t1_1) of the safety device in which the risk release is recorded may be initialized before turning off the collision risk warning. (S325) Here, the initialization of the timestamp (t1_1) may mean resetting the timestamp to the time (t1_2) at which the safety device was later detected. When the collision risk warning is turned off, the timestamp (t1_2) of the risk release and reset for the corresponding safety device may be recorded in the storage unit (400).
[0101] Meanwhile, the above preset difference value may be 60 seconds.
[0102] Returning to step S324, if the time difference between t1_1 and t1_2 is greater than the preset difference value, the safety device detected later is determined to be not the same safety device as the safety device for which the risk release was previously set, and a time stamp (t2_1) can be initially set for the time at which the safety device was detected. (S326) Afterwards, a step of asking the worker whether the risk of the detected safety device is released can be performed through the interface unit (300) equipped in the construction equipment. (S340)
[0103] Returning to step S321, if there is no record of risk release for the detected safety device, a time stamp (t1_1) can be initially set for the time at which the safety device was detected (S323). Afterwards, a step of asking the worker whether or not to release the risk for the detected safety device can be performed through the interface unit (300) equipped in the construction equipment (S340).
[0104] Inquiries regarding risk release can be made using a pop-up message, as described with reference to Figures 3a to 3c. Details overlap with those described above and are therefore omitted here.
[0105] In response to a risk release inquiry, if a user input approving the risk release of the detected safety device is received through the interface unit (200), the collision risk warning for the safety device may be turned off (S350, S330). At this time, along with the turning off of the collision risk warning, the risk release for the safety device and the initially set time stamp (t1_1) may be recorded in the storage unit (400).
[0106] In response to a request for risk release, if a user input refusing to release the detected safety device is received through the interface unit (200), a collision risk warning for the object (safety device) may be displayed (S350, S360). At this time, preferably, before displaying the collision risk warning, a step of determining whether the distance between the construction equipment (1) and the detected object is less than or equal to a threshold value may be first performed.
[0107] As described above, according to one disclosure of the present invention, for a safety device detected at a construction site, by asking a worker through an interface unit whether to release the danger and receiving an input from the worker to set the danger release, while simultaneously setting the display of a warning for the safety device, the worker can prevent the warning from continuously sounding for a safety device whose location is already known by the worker and thus has a low collision risk, thereby increasing work efficiency.
[0108] According to one disclosure of the present invention, by configuring to determine whether a detected safety device is a safety device that has been previously released from danger, a state of danger release is maintained without the need to repeatedly select danger release for a safety device that has been released from danger, and convenience of the operator can be improved.
[0109] The foregoing description of the present invention is for illustrative purposes only, and those skilled in the art will readily appreciate that the present invention can be readily modified into other specific forms without altering the technical spirit or essential characteristics of the present invention. Therefore, the embodiments described above should be understood as illustrative in all respects and not restrictive. For example, each component described as a single entity may be implemented in a distributed manner, and similarly, components described as distributed may be implemented in a combined manner.
[0110] The scope of the present invention is indicated by the claims described below rather than the detailed description above, and all changes or modifications derived from the meaning and scope of the claims and their equivalent concepts should be interpreted as being included in the scope of the present invention.
Claims
1. A detection unit installed in construction equipment and detecting a certain area around the construction equipment; A control unit that receives the detection results from the detection unit and detects an object existing in the specified area; An interface unit that receives information about an object detected by the control unit and warns a worker on board the construction equipment of a risk of collision; The above control unit, A method characterized in that it determines whether the detected object is a safety device installed at a construction site to ensure safe operation of the construction equipment, and if the detected object is the safety device, it inquires the worker through the interface unit whether to remove the danger from the safety device. Construction equipment safety systems.
2. In paragraph 1, The above safety device is, Including at least one of a signal man, a safety fence, and a rubber cone that controls the operation of the above construction equipment. Construction equipment safety systems.
3. In paragraph 1, The above control unit, A processor comprising an artificial intelligence neural network that has completed pre-training to detect objects existing in the above-mentioned predetermined area. Construction equipment safety systems.
4. In paragraph 1, The above control unit, The interface unit is controlled to output a pop-up message to inquire whether the risk has been lifted, and the pop-up message is characterized in that it is different depending on the type of the safety device. Construction equipment safety systems.
5. In paragraph 1, The above control unit, Characterized in that a user input for setting whether to release the danger of the detected safety device is received through the interface unit, Construction equipment safety systems.
6. In paragraph 1, The above control unit, When receiving a user input approving the release of the detected safety device, the collision risk warning for the safety device is turned off. Construction equipment safety systems.
7. In paragraph 1, The above control unit, If the detected object is the safety device, it is characterized in that it determines whether it is a safety device for which a risk release has been previously set. Construction equipment safety systems.
8. In paragraph 7, The above control unit, If the detected object is determined to be a safety device with a risk release setting, the collision risk warning is immediately turned off without asking whether the safety device has been released. Construction equipment safety systems.
9. A method for setting the risk level of objects detected in a certain area around construction equipment at a construction site. A step of detecting an object existing in the above-mentioned predetermined area; and A step of determining whether the detected object is a safety device installed at the construction site to ensure that the construction equipment operates safely, and setting a risk level for the safety device; The steps to set the above risk level are: Characterized in that it inquires the worker through the interface unit equipped in the above construction equipment whether the safety device is safe or not. method.
10. In paragraph 9, The step of detecting the above object is: Executing an artificial intelligence neural network that has completed pre-training to detect objects existing in the above-mentioned area, method.
11. In paragraph 9, The steps to set the above risk level are: When receiving a user input approving the release of the risk of the safety device detected through the interface unit, the collision risk warning for the safety device is turned off. method.
12. In paragraph 9, The steps to set the above risk level are: If the detected object is the safety device, it is characterized in that it determines whether it is a safety device for which a risk release has been previously set. method.
13. In paragraph 12, The steps to set the above risk level are: If the detected object is determined to be a safety device with a risk release setting, the collision risk warning is immediately turned off without asking whether the safety device has been released. method.
Citation Information
Patent Citations
Periphery monitoring system for work vehicle and work vehicle
JP2014064144A
Construction machine
KR1020170103288A
Safety Management System Using a Lidar for Heavy Machine
KR102065975B1
Bit interleaver for 256-symbol mapping and low density parity check codeword with 16200 length, 3 / 15 rate, and method using the same
KR102429454B1
Smart Eco-Friendly Container Having Freshness Check Structure
KR102588942B1