Abstract: The invention discloses a system for image segmentation for detecting an object. More particularly, the system performs two-stage segmentation on the object in the image to generate an enhanced image. The first stage is the object detection, followed by a second stage including segmentation. The invention segments the object from a background of the image to create an enhanced image.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating a depth image, comprising obtaining data representing a first image generated by a first sensor and a second image generated by a second sensor, wherein each of the first and second images includes a plurality of pixels; determining, for each pixel of the plurality of pixels included in the first image, whether the pixel is a boundary pixel associated with a boundary of an object that is represented in the first image; determining, from a plurality of candidate penalty values and for each pixel in the first image, an optimized penalty value for the pixel; generating an optimized cost function for the first image based on the optimized penalty values for the plurality of pixels; and generating a depth image for the first image based on the optimized cost function.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a machine learning model configured to generate a predicted depth image, comprising receiving data representing training samples that include a plurality of image pairs, each image pair includes a target image and a reference image both capturing a particular scene from different orientations; for each of the plurality of image pairs, generating a compressed cost volume for the image pair; providing the compressed cost volume as an input to the machine learning model; generating, using the machine learning model, output data representing a predicted disparity map for the compressed cost volume; and generating a total loss using the predicted disparity map for the compressed cost volume, the total loss includes a boundary loss, an occlusion loss, and a transfer loss; and updating the plurality of parameters of the machine learning model by minimizing the total losses.

Abstract: Disclosed are an extendable and retractable fairing for a container ship and a control method thereof. The extendable and retractable fairing includes a controller, a support skeleton, a wind velocity detector, a first flexible deflector, second and third flexible deflectors, and accommodation mechanisms. The third flexible deflectors are sequentially arranged between the first and second flexible deflectors; the support skeleton includes guide-track grooves; the second and third flexible deflectors each are slidably provided in a corresponding guide-track groove; the accommodation mechanisms each include an accommodation winding tube and a drive motor; the accommodation winding tube is provided at one side of a deck at the bow; the drive motor is connected to the accommodation winding tube; the wind velocity detector is provided on the first flexible deflector; and the second and third flexible deflectors each are provided in the accommodation winding tube.

Abstract: Disclosed are an extendable and retractable fairing for a container ship and a control method thereof. The extendable and retractable fairing includes a controller, a support skeleton, a wind velocity detector, a first flexible deflector, second and third flexible deflectors, and accommodation mechanisms. The third flexible deflectors are sequentially arranged between the first and second flexible deflectors; the support skeleton includes guide-track grooves; the second and third flexible deflectors each are slidably provided in a corresponding guide-track groove; the accommodation mechanisms each include an accommodation winding tube and a drive motor; the accommodation winding tube is provided at one side of a deck at the bow; the drive motor is connected to the accommodation winding tube; the wind velocity detector is provided on the first flexible deflector; and the second and third flexible deflectors each are provided in the accommodation winding tube.

Abstract: Disclosed is a novel jet-propelled lift-increasing and stability-increasing amphibious aircraft and an application method thereof. An air intake fan connects and communicates with an air intake end of a pressurized air storage tank, an air outlet end of the pressurized air storage tank connects and communicates with a shunting pipeline, the shunting pipeline respectively connects and communicates with a plurality of air chambers, each connection of the plurality of air chambers and the shunting pipeline is provided with an adjusting valve, and the plurality of air chambers are distributed in a plurality of positions of the bottom of the aircraft, and are configured to jet air outwards. A navigation state sensing device is configured to detect navigation data of the aircraft and send the navigation data to an intelligent analysis device. The intelligent analysis device is configured to analyze the navigation data, obtain a control scheme and send to a jet control device.

Abstract: A method of motion control and textured display, comprising, receiving an image, extracting an initial mask of a subject of interest from the image, segmenting the image into the initial mask and a background, determining a color texture of the initial mask, estimating motion of the initial mask to a new mask and merging the new mask and the background into a merged image.

Abstract: The invention provides a suspended catamaran target boat, including a deck, a suspension structure and two buoyancy units, the suspension structure is connected to upper sides of the two buoyancy units, and the deck is mounted on the suspension structure; the suspension structure includes at least two suspension assemblies including an upper base, a lower base and two support rods. The support rods are hinged between the upper base and the lower base, and the upper base, the lower base and the two support rods form a four-bar linkage mechanism, where a shock absorber and a restricting mechanism are installed between the upper base and the lower base. The deck is provided with a main controller, an acceleration sensor and a heel sensor, and the main controller is respectively electrically connected with the acceleration sensor, the heel sensor and each of the restricting mechanisms of the two suspension assemblies.

Abstract: A method of depth-of-field simulation, including receiving a plurality of images, predicting a layer of interest mask of the plurality of images, determining a plurality of mean brightness anchor values of a respective plurality of layers of interest window arrays, setting a plurality of layers of interest set of binary codes, determining a hamming distance between plurality of layers of interest set of binary codes, determining a cost volume based on the hamming distance, resampling a vertical cost based on a vertical ordinal direction the cost volume, resampling a horizontal cost based on a horizontal ordinal direction the cost volume, determining an all-in-focus layer based on the vertical cost and the horizontal cost, determining an out-of-focus layer based on the vertical cost and the horizontal cost and determining a depth of the all-in-focus layer and out-of-focus layer.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating a depth image, comprising obtaining data representing a first image generated by a first sensor and a second image generated by a second sensor, wherein each of the first and second images includes a plurality of pixels; determining, for each pixel of the plurality of pixels included in the first image, whether the pixel is a boundary pixel associated with a boundary of an object that is represented in the first image; determining, from a plurality of candidate penalty values and for each pixel in the first image, an optimized penalty value for the pixel; generating an optimized cost function for the first image based on the optimized penalty values for the plurality of pixels; and generating a depth image for the first image based on the optimized cost function.

Abstract: The present invention discloses system and method for replacing a texture of a background region in a multimedia. The system is an AI-based multi-media processing system for replacing the original texture of the background of the multimedia with a texture template. The system applies a foreground mask to hide and protect the foreground region and multiple textures of the background. The system uses deep learning to segment specific texture from images or video sequences. The system replaces the texture of the original input image with a texture template to form a processed image.

Abstract: The present invention discloses system and method for replacing a texture of a background region in a multimedia. The system is an AI-based multi-media processing system for replacing the original texture of the background of the multimedia with a texture template. The system applies a foreground mask to hide and protect the foreground region and multiple textures of the background. The system uses deep learning to segment specific texture from images or video sequences. The system replaces the texture of the original input image with a texture template to form a processed image.

Abstract: A method of motion control and textured display, comprising, receiving an image, extracting an initial mask of a subject of interest from the image, segmenting the image into the initial mask and a background, determining a color texture of the initial mask, estimating motion of the initial mask to a new mask and merging the new mask and the background into a merged image.

Abstract: A method of depth-of-field simulation, including receiving a plurality of images, predicting a layer of interest mask of the plurality of images, determining a plurality of mean brightness anchor values of a respective plurality of layers of interest window arrays, setting a plurality of layers of interest set of binary codes, determining a hamming distance between plurality of layers of interest set of binary codes, determining a cost volume based on the hamming distance, resampling a vertical cost based on a vertical ordinal direction the cost volume, resampling a horizontal cost based on a horizontal ordinal direction the cost volume, determining an all-in-focus layer based on the vertical cost and the horizontal cost, determining an out-of-focus layer based on the vertical cost and the horizontal cost and determining a depth of the all-in-focus layer and out-of-focus layer.