Abstract: Provided are a device and a method for detecting a wildfire. The wildfire detecting device may include: an image data acquisition module acquiring image data captured by a shooting device; an image data storage module storing the image data acquired through the image data acquisition module in a storage space; a wildfire detection module performing wildfire detection by using a deformable convolution based deep learning model to which smoke characteristics widely diffused are reflected by dynamically adjusting a filter position by using a learnable offset from the image data; and a wildfire direction and position estimation module estimating a direction and a position of the wildfire with respect to a case where it is determined that the wildfire occurs by the wildfire detection module.

Abstract: Provided are a forest fire detection system and method capable of determining whether events. The forest fire detection system includes an artificial intelligence-based forest fire detection module configured to detect a forest fire from a captured image using an artificial intelligence model; a monitoring camera configured to monitor a predetermined area; a direction estimation module configured to estimate a direction of the forest fire on a map, using a plurality of forest fire detection images provided from the artificial intelligence-based forest fire detection module and data of the monitoring camera; and a same event determination module configured to determine whether events represented by the plurality of forest fire detection images are the same, based on the estimated direction of the forest fire.

Abstract: Provided are a device and a method for detecting a wildfire. The wildfire detecting device may include: an image data acquisition module acquiring image data captured by a shooting device; an image data storage module storing the image data acquired through the image data acquisition module in a storage space; a wildfire detection module performing wildfire detection by using a deformable convolution based deep learning model to which smoke characteristics widely diffused are reflected by dynamically adjusting a filter position by using a learnable offset from the image data; and a wildfire direction and position estimation module estimating a direction and a position of the wildfire with respect to a case where it is determined that the wildfire occurs by the wildfire detection module.

Abstract: Provided are a forest fire detection system and method capable of determining whether events. The forest fire detection system includes an artificial intelligence-based forest fire detection module configured to detect a forest fire from a captured image using an artificial intelligence model; a monitoring camera configured to monitor a predetermined area; a direction estimation module configured to estimate a direction of the forest fire on a map, using a plurality of forest fire detection images provided from the artificial intelligence-based forest fire detection module and data of the monitoring camera; and a same event determination module configured to determine whether events represented by the plurality of forest fire detection images are the same, based on the estimated direction of the forest fire.