Abstract:
A steganography method and an apparatus embedding a hidden message in a video stream of an original cover video to produce a stego video using a generative neural network. The original cover video is a video stream as opposed using an image. A discriminant neural network is used to correct a generated video compared to an original cover video. The generated neural network is trained when the generated video is determined to be real by the discriminant neural network. A second stego video is acquired by adversarial training through a mutually adversarial relationship between a generative neural network and an discriminant neural network. The embedding technique is one of pre-embedding, intra-embedding, or post-embedding.
Abstract:
A method creating a high-speed hyperspectral video by acquiring images from a hyperspectral high speed camera and forming a of a three-dimensional data cube by including spectra for each pixel in addition to a two-dimensional spatial information of an image taken with a general camera. Dividing successive three-dimensional data cubes obtained by photographing images with a spectral scanning type hyperspectral camera. Acquiring the three-dimensional data cubes for each specific time point and creating three-dimensional data cubes for as many as the number of spectra. Then separating a region corresponding to a moving object and a region corresponding to a background from the created data cubes. Acquiring spectral values according to spatial locations of the images and reconstructing a three-dimensional data cube with all spectral values for each specific time point with regard to the region with motion through a generative adversarial network algorithm.
Abstract:
The present invention relates to a device for testing packaging leakage using a difference in pressure and distance. The present invention provides a device for testing packaging leakage including a test vessel having a sealed internal space that accommodates a packaged product and having a plurality of compartments, a distance measurement sensor configured to measure a distance to the packaged product, a pressure measurement sensor configured to measure a pressure in the test vessel, a vacuum pump configured to form vacuum in the internal space of the test vessel, a solenoid valve configured to adjust a vacuum level of the test vessel, and a control box interworked with the distance measurement sensor, the pressure measurement sensor, the vacuum pump, and the solenoid valve.
Abstract:
The present disclosure relates to an integrated monitoring system. The integrated monitoring system includes: a mother ship system which receives operation information, determines a range of an operation area based on the received operation information, and determines the number of unmanned robots movable in the air and underwater for monitoring the operation area based on the determined range of the operation area to form a swarm; a first group of swarm robots, including the determined number of unmanned robots, which collects information on the operation area, and configures a distributed network to perform mutual communication; and a first mobile relay robot which follows a movement path of the first group of swarm robots and is positioned between the mother ship system and the path of the first group of swarm robots to relay data communication between the mother ship system and the first group of swarm robots.
Abstract:
The present application provides a satellite receiver comprising: an antenna unit for receiving a satellite signal; a transmission line unit comprising a bandpass filter for selecting a reception band of the satellite signal, and a variable attenuator for generating artificial noise in the satellite signal which has passed through the filter; a low noise amplifier and converter for carrying out low noise amplification and frequency conversion of the satellite signal in which the artificial noise has been generated; and a modem for receiving, from the low noise amplifier and converter, a signal-to-noise ratio (SNR) of the satellite signal.
Abstract:
The present application relates to a silanized boron nitride composite and a preparation method thereof, and more specifically, to a silanized boron nitride composite, which exhibits excellent mechanical properties and excellent thermal conductivity by realizing excellent dispersibility and improved affinity for epoxy through silane surface treatment, and a preparation method thereof.
Abstract:
Disclosed are an unmanned aerial vehicle, a charging station, and an automatic charging system for an unmanned aerial vehicle including the same. The unmanned aerial vehicle includes: a main body which includes a plurality of rotors, and is capable of flying and vertical taking off and landing by the rotors; a battery which is mounted in the main body for supplying power and is chargeable; a landing gear which includes a first charging terminal and a second charging terminal having different polarities and electrically connected to the battery, and is provided at a lower part of the main body; and a controller configured to control the main body.
Abstract:
The present application relates to a steganography method and a steganography apparatus using the same. According to the steganography method of the present application and the steganography apparatus using the same, they can simplify a data refinement process compared to the supervised learning method as AI learns a large amount of data related to steganography encoding and decoding by itself, can generate a high-quality stego video close to the cover video to improve the imperceptibility of hidden information as the generator and discriminator conduct mutual learning, can hide the message in the images and/or sounds according to the learning method to secure a high-capacity cache, and can secure robustness against third-party detection, monitoring, and removal attacks when learning the detection and avoidance methods of physical and technical detection systems (monitoring equipment, wiretapping equipment and security equipment, etc.). In addition, according to the steganography method of the present application, it can simplify a data refinement process compared to the supervised learning method as AI learns a large amount of data related to steganography decoding by itself, and can recover the hidden message close to the original hidden message to improve perceptibility of hidden information as the generator and the discriminator conduct mutual learning.
Abstract:
The present invention relates to a method for creating a high-speed hyperspectral video by dividing successive three-dimensional data cubes obtained by photographing images with a spectral scanning type hyperspectral camera so as to be capable of having a temporal resolution within the number of spectra.
Abstract:
The present application relates to a method for synthesizing image and an image synthesizing apparatus using the same. The image synthesizing method of the present application and the image synthesizing apparatus using the same can reduce the time required for learning by reducing the distortion phenomenon of the algorithm and reducing the amount of calculation required for image synthesis. In addition, the image synthesizing method of the present application and the image synthesizing apparatus using the same can be utilized in various fields such as national defense, IT, and entertainment based on characteristics such as excellent performance and learning time reduction of deep learning algorithms, and can be utilized in psychological warfare or induction of command system confusion.