Abstract: An abnormality diagnosis apparatus, located within a factory monitoring system, may include at least one processor; and memory having programmed thereon instructions that, when executed, are configured to cause the at least one processor to: receive image data about an inspection object from an image sensor; and diagnose an abnormality in the inspection object using the received image data and a pre-trained artificial intelligence-based diagnosis model.

Abstract: An image encoding method according to the present disclosure may include deriving coefficients of a spherical harmonic function for a plurality of vertices on a three-dimensional space; generating a plurality of layer images based on the coefficients; and encoding the plurality of layer images. In this case, each of the plurality of layer images may include a coefficient value in order corresponding to the spherical harmonic function.

Abstract: Disclosed herein are an apparatus and method for removing redundant data between multi-view videos. The method includes generating a pruning mask of an additional view image by mapping a basic view image to the additional view image, among multi-view images, and revalidating the pruning mask using color information of the basic view image and the additional view image. Revalidating the pruning mask may include defining a color relationship between the basic view image and the additional view image by extracting predetermined sample values from corresponding pixels between the basic view image and the additional view image, which are included in the pruning candidate group of the pruning mask, and detecting pixels that do not match the defined color relationship, among the pixels in the pruning mask, as outliers.

Abstract: Disclosed herein is a method for encoding an immersive image. The method includes detecting a non-diffuse surface in a first texture image of a first view, generating an additional texture image from the first texture image based on the detected non-diffuse surface, performing pruning on the additional texture image based on a second texture image of a second view, generating a texture atlas based on the pruned additional texture image, and encoding the texture atlas.

Abstract: An image encoding method according to the present disclosure may include generating an atlas based on a plurality of viewpoint images; encoding the atlas; and encoding metadata for the atlas. In this case, the metadata may include data of a patch packed in the atlas, and the patch data may include type information of an entity corresponding to a patch.

Abstract: An oscillating mirror for lidar has a mirror coupled with a rotor. The rotor is arranged to rotate about a pivot using one or more bearings. A mirror is coupled with the rotor and arranged to reflect light emitted from a laser. A first magnet is coupled with the rotor. A second magnet is coupled with a base. The second magnet is arranged to limit an angular rotation of the rotor by a pole of the second magnet facing a similar pole of the first magnet.

Abstract: A method of processing an immersive video includes classifying view images into a basic image and an additional image, performing pruning with respect to view images by referring to a result of classification, generating atlases based on a result of pruning, generating a merged atlas by merging the atlases into one atlas, and generating configuration information of the merged atlas.

Abstract: An image encoding method according to the present disclosure may include generating an atlas based on at least one two-dimensional or three-dimensional image; and encoding the atlas and metadata for the atlas. In this case, the metadata may include information about a patch packed in the atlas, and the patch information may include information about a three-dimensional point projected on a two-dimensional patch.

Abstract: Provided is a device for evaluating 360-degree bidirectional folding durability of a flexible material in which during a folding test of a film-type flexible material, a single folding device can implement both the infolding and outfolding of the flexible material relative to the unfolded state of the flexible material. To this end, the device includes: a fixing unit configured to fix a first side of the flexible material to be evaluated; a moving unit configured to fix a second side of the flexible material and disposed to be spaced apart from the fixing unit; a motion guide unit to which the fixing unit is fixed; and a motion unit connecting the motion guide unit with the moving unit.

Abstract: A video encoding method according to the present disclosure includes classifying a plurality of view images into basic images and additional images, performing pruning on at least one of the plurality of view images on the basis of the classification result, generating an atlas based on the pruning results, and encoding the atlas and metadata for the atlas.

Abstract: Systems and methods provide for training a language model on the relationships present in a structural database. Information within a structural data is processed and converted into plain text such that the relationships within the database, such as hierarchical relationships, relations, etc. are maintained and represented in a plain text format. This information may be used as training data for a language model to provide pre-training for one or more domains. The language model may then be leveraged with natural language searching in order to identify results within a search domain response to an input query.

Abstract: Disclosed herein is a method for encoding/decoding an immersive image, and the method for encoding an immersive image may include extracting an invalid region from an already encoded atlas and encoding a current atlas by referring to the invalid region.

Abstract: A method of producing an immersive video comprises decoding an atlas, parsing a flag for the atlas, and producing a viewport image using the atlas. The flag may indicate whether the viewport image is capable of being completely produced through the atlas, and, according to a value of the flag, when the viewport image is produced, it may be determined whether an additional atlas is used in addition to the atlas.

Abstract: An image encoding method according to the present disclosure may include classifying a plurality of view images into a basic image and an additional image; performing pruning for at least one of the plurality of view images based on a result of the classification; generating an atlas based on a result of performing the pruning; and encoding the atlas and metadata for the atlas. In this case, the metadata may include spherical harmonic function information on a point in a three-dimensional space.

Abstract: An immersive image encoding method according to the present disclosure includes classifying a plurality of view images into a basic image and an additional image; performing pruning for at least one of the plurality of view images based on the classification result; generating a depth atlas based on a result of performing the pruning; and correcting an occupancy state of pixels in the depth atlas.

Abstract: A method of switching an atlas according to a watching position according to the present disclosure includes acquiring information on a view image required to reproduce a viewport image; acquiring information of a first atlas mapped to the view image; and receiving a bitstream of the first atlas and a bitstream of a second atlas different from the first atlas. In this case, when it is determined that atlas switching is necessary, reception of any one of a bitstream of the first atlas and a bitstream of the second atlas may be stopped and a bitstream of a third atlas may be newly received.

Abstract: A method of processing an immersive video according to the present disclosure includes performing pruning for an input image, generating an atlas based on patches generated by the pruning and generating a cropped atlas by removing a background region of the atlas.

Abstract: Disclosed herein are an apparatus and method for removing redundant data between multi-view videos. The method includes generating a pruning mask of an additional view image by mapping a basic view image to the additional view image, among multi-view images, and revalidating the pruning mask using color information of the basic view image and the additional view image. Revalidating the pruning mask may include defining a color relationship between the basic view image and the additional view image by extracting predetermined sample values from corresponding pixels between the basic view image and the additional view image, which are included in the pruning candidate group of the pruning mask, and detecting pixels that do not match the defined color relationship, among the pixels in the pruning mask, as outliers.

Abstract: Disclosed herein is an immersive video processing method. The immersive video processing method includes: determining a priority order of pruning for input videos; extracting patches from the input videos based on the priority order of pruning; generating at least one atlas based on the extracted patches; and encoding metadata. Herein, the metadata may include information on a priority order of pruning among input videos.