Abstract: A heat converter according to one embodiment of the present invention comprises: a plurality of unit modules respectively arranged in a first direction and a second direction that intersects the first direction; and a frame, which supports the plurality of unit modules, allows cooling water to flow in through one surface arranged in the first direction, and allows the cooling water to be discharged through the other surface arranged in the first direction, wherein each unit module includes: a cooling water passage chamber having first and second surfaces arranged to be spaced in the first direction, third and fourth surfaces arranged to be spaced in a third direction that intersects the first direction and the second direction, a fifth surface arranged to be spaced in the second direction such that cooing water flows therein, and a sixth surface from which cooling water is discharged; a first thermoelectric module arranged on the first surface; and a second thermoelectric module arranged on the second surface

Abstract: The present disclosure provides a target for aerial survey transformable to hand-fan shape. In this instance, the target includes a central axis, a first identification marker with one end connected to the central axis and having a first length outwards, and a second identification marker with one end connected to the central axis and having a second length outwards, the second identification marker disposed on the first identification marker, wherein the second length is shorter than the first length, the first identification marker includes a plurality of first unit areas having a predetermined angle therebetween with respect to the central axis, and the plurality of first unit areas has an overlap between adjacent first unit areas.

Abstract: According to an embodiment of the present disclosure, there may be provided an operation method of a server for identifying disaster affected areas. In this instance, the operation method of the server may include acquiring at least one first disaster image; deriving an affected area from each of the at least one first disaster image, and acquiring affected area related information through labeling based on the derived affected area; and training a first learning model using the at least one first disaster image and the affected area related information.

Abstract: According to an embodiment of the present disclosure, there may be provided an operation method of a server for estimating the size of damage in disaster affected areas. In this instance, the operation method of the server may include acquiring at least one first disaster image, deriving an affected area from each of the at least one first disaster image, acquiring affected area related information through labeling based on the derived affected area, and training a first learning model using the at least one first disaster image and the affected area related information.

Abstract: Provided is a control method for preventing an accident in a tunnel. In this instance, the control method for preventing an accident in a tunnel includes estimating water amount information flowing into the tunnel based on at least one input information, determining whether it is an emergency situation based on the estimated water amount information, and when the emergency situation is determined, transmitting a warning message to an identification device, and controlling a device for opening and closing an entrance/exit of the tunnel. In this instance, the water amount information flowing into the tunnel is estimated through a deep learning based learning model, and the emergency situation is determined by comparing water level information of the tunnel with a threshold value.

Abstract: The present disclosure provides a target for aerial survey transformable to hand-fan shape. In this instance, the target includes a central axis, a first identification marker with one end connected to the central axis and having a first length outwards, and a second identification marker with one end connected to the central axis and having a second length outwards, the second identification marker disposed on the first identification marker, wherein the second length is shorter than the first length, the first identification marker includes a plurality of first unit areas having a predetermined angle therebetween with respect to the central axis, and the plurality of first unit areas has an overlap between adjacent first unit areas.

Abstract: Provided is a control method for preventing an accident in a tunnel. In this instance, the control method for preventing an accident in a tunnel includes estimating water amount information flowing into the tunnel based on at least one input information, determining whether it is an emergency situation based on the estimated water amount information, and when the emergency situation is determined, transmitting a warning message to an identification device, and controlling a device for opening and closing an entrance/exit of the tunnel. In this instance, the water amount information flowing into the tunnel is estimated through a deep learning based learning model, and the emergency situation is determined by comparing water level information of the tunnel with a threshold value.