Abstract: The hierarchical occlusion inference method according to the exemplary embodiment of the present disclosure includes: deriving a bounding box feature of the object instance by receiving a region of interest color-depth FPN feature and the object region of interest feature derived from a cluttered scene image including at least one object instance, deriving a visible feature of the object instance by fusing the object region of interest feature and the bounding box feature, deriving an amodal feature of the object instance by fusing the object region of interest feature, the bounding box feature, and the visible feature, deriving an occlusion feature of the object instance by fusing the object region of interest feature, the bounding box feature, the visible feature, and the amodal feature, and inferring occlusion of an object instance by de-convoluting the occlusion feature of the object instance.

Abstract: Provided is a system for detecting an object in an underground space. The system for detecting the object in the underground space includes a movable body moving in the underground space, a wide-angle camera mounted on the movable body to photograph an underground facility in the underground space, an object detection terminal configured to receive an image of the underground facility photographed by the wide-angle camera and correct a corresponding distorted image so as to detect the underground facility corresponding to an object set within the corrected image; and a communication network configured to enable network communication between the movable body and the object detection terminal. Thus, the system may have an effect of robustly detecting the object in an image with a large change in size of an object formed on an image according to the distortion and distance such as the wide-angle or omnidirectional camera.

Abstract: The present disclosure relates to a feature vector transfer method including training a high-quality face recognition network for recognizing a human face based on a high-quality image including the human face, extracting a first feature vector associated with the high-quality image from the high-quality face recognition network, transferring the extracted first feature vector onto a low-quality face recognition network for recognizing the human face based on a low-quality image including the human face, and training the low-quality face recognition network using the transferred first feature vector.

Abstract: The hierarchical occlusion inference method according to the exemplary embodiment of the present disclosure includes: deriving a bounding box feature of the object instance by receiving a region of interest color-depth FPN feature and the object region of interest feature derived from a cluttered scene image including at least one object instance, deriving a visible feature of the object instance by fusing the object region of interest feature and the bounding box feature, deriving an amodal feature of the object instance by fusing the object region of interest feature, the bounding box feature, and the visible feature, deriving an occlusion feature of the object instance by fusing the object region of interest feature, the bounding box feature, the visible feature, and the amodal feature, and inferring occlusion of an object instance by de-convoluting the occlusion feature of the object instance.