Abstract: Provided is an image recognition method including the steps of: for a deep learning network that carries out object recognition on a random image, carrying out quantization corresponding to the number of a plurality of different bits to generate a plurality of quantization models respectively corresponding to the number of bits; receiving image data as an input for the deep learning network; determining the uncertainty of the input image data; selecting any one of the plurality of quantization models on the basis of the determined uncertainty; and recognizing an object from the image data by using the selected quantization model, and outputting, as the result of the object recognition, a label corresponding to the image data.

Abstract: According to the present disclosure, an apparatus for real-time object detection in an image captured by an unmanned aerial vehicle (UAV) including an image splitter configured to receive an input image and split the input image into a left image and a right image; and an object detector configured to detect an object from each of the left image and the right image provided from the image splitter is provided.

Abstract: According to the present disclosure, an apparatus for real-time object detection in an image captured by an unmanned aerial vehicle (UAV) including an image splitter configured to receive an input image and split the input image into a left image and a right image; and an object detector configured to detect an object from each of the left image and the right image provided from the image splitter is provided.

Abstract: An apparatus for generating data based on generative adversarial networks (GANs) is provided. The apparatus includes a first generator configured to receive input data and generate a first fake image, a first discriminator configured to receive the first fake image generated by the first generator and a first real image and verify whether an image is fake or real, a second generator configured to receive the first fake image and generate a second fake image; and a second discriminator configured to receive the second fake image and a second real image and verify whether an image received by the second discriminator is fake or real. The apparatus improves an object recognition performance as compared with a typical object recognition algorithm by generating an image of a class of which a sufficient database is not secured so as to reduce an object misrecognition caused by an insufficient amount of data.

Abstract: Provided is an apparatus for generating data based on generative adversarial networks (GANs), the apparatus including a first generator configured to receive input data and generate a first fake image and a first discriminator configured to receive the first fake image generated by the first generator and a first real image and verify whether an image is fake or real.

Abstract: An egomotion estimation system may include: a stereo camera suitable for acquiring a stereo image; a map generation unit suitable for generating a depth map and a disparity map using the stereo image; a feature point extraction unit suitable for extracting a feature point from a moving object in the stereo image using the disparity map; a motion vector detection unit suitable for detecting a motion vector of the extracted feature vector point; an error removing unit suitable for removing an error of the detected motion vector; and an egomotion determination unit suitable for calculating and determine an egomotion using the error-removed motion vector.

Abstract: An object detection device may include: a candidate object selection unit suitable for selecting candidate objects from a stereo image transmitted from moving cameras; a global motion estimation unit suitable for estimating global motions representing movement of the moving cameras from the stereo image; and an object determination unit suitable for detecting a moving object from the stereo image based on the candidate objects and the global motions.

Abstract: An egomotion estimation system may include: a stereo camera suitable for acquiring a stereo image; a map generation unit suitable for generating a depth map and a disparity map using the stereo image; a feature point extraction unit suitable for extracting a feature point from a moving object in the stereo image using the disparity map; a motion vector detection unit suitable for detecting a motion vector of the extracted feature vector point; an error removing unit suitable for removing an error of the detected motion vector; and an egomotion determination unit suitable for calculating and determine an egomotion using the error-removed motion vector.

Abstract: An object detection device may include: a candidate object selection unit suitable for selecting candidate objects from a stereo image transmitted from moving cameras; a global motion estimation unit suitable for estimating global motions representing movement of the moving cameras from the stereo image; and an object determination unit suitable for detecting a moving object from the stereo image based on the candidate objects and the global motions.

Abstract: The present inventive concept can be used in a wide range of applications, including: mobile devices, such as mobile phones; an image processing apparatus or processor and computer programs, including a member for converting 2D image signals into 3D image signals or using an algorism for converting 2D image signals into 3D image signals.

Abstract: A method of preparing optically pure (S)-3-hydroxypyrrolidine is disclosed. The present invention provides a method of economically and industrially preparing optically and chemically pure (S)-3-hydroxypyrrolidine, through a process comprising introducing an amine protecting group by using optically pure 4-amino-(S)-2-hydroxybutylic acid as a starting material, reducing a carboxylic acid group into a primary alcohol, removing the amine protecting group to form an amine salt, halogenating the primary alcohol, and amine cyclization; and through a simple purification process, i.e., distillation under reduced pressure. As another method, the present invention provides a method of preparing optically and chemically pure (S)-3-hydroxypyrrolidine, through a process comprising esterifying optically pure 4-amino-(S)-2-hydroxybutylic acid as a starting material, lactam cyclization, and reduction.

Abstract: A method of preparing optically pure (S)-3-hydroxypyrrolidine is disclosed. The present invention provides a method of economically and industrially preparing optically and chemically pure (S)-3-hydroxypyrrolidine, through a process comprising introducing an amine protecting group by using optically pure 4-amino-(S)-2-hydroxybutylic acid as a starting material, reducing a carboxylic acid group into a primary alcohol, removing the amine protecting group to form an amine salt, halogenating the primary alcohol, and amine cyclization; and through a simple purification process, i.e., distillation under reduced pressure. As another method, the present invention provides a method of preparing optically and chemically pure (S)-3-hydroxypyrrolidine, through a process comprising esterifying optically pure 4-amino-(S)-2-hydroxybutylic acid as a starting material, lactam cyclization, and reduction.

Abstract: A method of automatically dividing the domain of a motion picture is disclosed including the steps of: quantizing at least two sequential picture frames, and simplifying the shapes of the quantized picture frames; obtaining time space slope information from the quantized and simplified picture frames; detecting divides of the picture from the time space gradient information, and obtaining the boundaries between the divides, so as to divide the picture into multiple regions; combining neighboring smaller regions using graph theory, to thereby reduce the number of the divided regions; and dividing the regions into a motionless background object and moving objects, using motion information of the combined regions.