Abstract: The present invention discloses a biaxial supporting device for a rotary opposed piston engine, comprising a cylinder body, a fixing component, a thick axle and a thin axle; the interior of the cylinder body has a cavity; the fixing component is fixed on the outer side wall of the cylinder body; the thick axle is provided with a through hole coaxial with the first axle hole, and is rotatably connected with the through hole; the thin axle is in transition fit with the through hole of the thick axle, and is rotatably connected with the fixing component. The present invention has simple structure, can effectively reduce a diameter difference of two axles to ensure the relatively small diameter of the thick axle and the relatively high strength of the thin axle, and can effectively realize biaxial support of the rotary opposed piston engine.

Abstract: A depth image generation method includes obtaining a first depth image, based on a binocular image, obtaining a second depth image, using a depth camera, and obtaining a final depth image by performing image fusion on the obtained first depth image and the obtained second depth image.

Abstract: A simultaneous localization and mapping device is provided. The device includes an image obtaining device configured to capture color images and depth images of a surrounding environment; an initial pose estimating device configured to estimate an initial pose based on the color images and the depth images; a map constructing device configured to construct a three-dimensional map based on the depth images and the color images; and a pose determining device configured to determine a final pose based on the initial pose and the three-dimensional map.

Abstract: Disclosed is a depth map calculation method and apparatus. The depth map calculation method includes calculating a global sparse depth map corresponding to a current frame using frames including the current frame, calculating a local dense depth map corresponding to the current frame using the current frame, extracting a non-static object region from the current frame by masking a static object region, removing the non-static object region from the global sparse depth map, and generating a global dense depth map corresponding to the current frame by merging the non-static object region-removed global sparse depth map and the local dense depth map.

Abstract: An image processing method and apparatus is disclosed. The image processing method includes receiving an input image and estimating a depth of a target based on a position, a size, and a class of the target in the input image.

Abstract: A method and apparatus for outputting three-dimensional (3D) lines. The apparatus acquires a first image and a second image including lines on a road, generates, based on a first feature map acquired from the first image, a line probability map representing a probability that a pixel point of the first feature map belongs to the lines, calculates matching information of the first image and the second image based on the first feature map and a second feature map acquired from the second image, predicts depth values of the lines using the line probability map and the matching information, detects the lines based on the line probability map, generates 3D lines based on the detected lines and the depth values of the lines, and outputs the 3D lines.

Abstract: A depth image generation method includes obtaining a first depth image, based on a binocular image, obtaining a second depth image, using a depth camera, and obtaining a final depth image by performing image fusion on the obtained first depth image and the obtained second depth image.

Abstract: A simultaneous localization and mapping device is provided. The device includes an image obtaining device configured to capture color images and depth images of a surrounding environment; an initial pose estimating device configured to estimate an initial pose based on the color images and the depth images; a map constructing device configured to construct a three-dimensional map based on the depth images and the color images; and a pose determining device configured to determine a final pose based on the initial pose and the three-dimensional map.

Abstract: A method and device that estimate a pose of a device and the device are disclosed. The method may include generating inertial measurement unit (IMU) data of the device, determining a first pose of the device a first time point based on the IMU data, generating a current predicted motion state array based on the IMU data, and estimating an M-th predicted pose of the device at an M-th time point after the first time point based on the current predicted motion state array, where M denotes a natural number greater than 1.

Abstract: Disclosed is a depth map calculation method and apparatus. The depth map calculation method includes calculating a global sparse depth map corresponding to a current frame using frames including the current frame, calculating a local dense depth map corresponding to the current frame using the current frame, extracting a non-static object region from the current frame by masking a static object region, removing the non-static object region from the global sparse depth map, and generating a global dense depth map corresponding to the current frame by merging the non-static object region-removed global sparse depth map and the local dense depth map.

Abstract: A method and apparatus for outputting three-dimensional (3D) lines. The apparatus acquires a first image and a second image including lines on a road, generates, based on a first feature map acquired from the first image, a line probability map representing a probability that a pixel point of the first feature map belongs to the lines, calculates matching information of the first image and the second image based on the first feature map and a second feature map acquired from the second image, predicts depth values of the lines using the line probability map and the matching information, detects the lines based on the line probability map, generates 3D lines based on the detected lines and the depth values of the lines, and outputs the 3D lines.

Abstract: A method and device that estimate a pose of a device and the device are disclosed. The method may include generating inertial measurement unit (IMU) data of the device, determining a first pose of the device a first time point based on the IMU data, generating a current predicted motion state array based on the IMU data, and estimating an M-th predicted pose of the device at an M-th time point after the first time point based on the current predicted motion state array, where M denotes a natural number greater than 1.

Abstract: An image processing method and apparatus is disclosed. The image processing method includes receiving an input image and estimating a depth of a target based on a position, a size, and a class of the target in the input image.