Abstract: Techniques are described for identifying correspondences between images to generate a fundamental matrix for the camera positions related to the images. The resultant fundamental matrix enables epipolar geometry to correlate common features among the images. Correspondences are identified by confirming feature matches across images by applying a homography to data representing features across images. Further techniques are described herein for generating a representation of a boundary of a feature of a structure based on a digital image. In one or more embodiments, generating a representation of a boundary of a particular feature in a digital image comprises determining a portion of the image that corresponds to the structure, and determining a portion of the image that corresponds to the particular feature. One more vanishing points are associated with the portion of the image corresponding to the particular feature.

Abstract: Disclosed are techniques for enhancing two-dimensional (2D) image capture of subjects (e.g., a physical structure, such as a residential building) to maximize the feature correspondences available for three-dimensional (3D) model reconstruction. More specifically, disclosed is a computer-vision network configured to provide viewfinder interfaces and analyses to guide the improved capture of an intended subject for specified purposes. Additionally, the computer-vision network can be configured to generate a metric representing a quality of feature correspondences between images of a complete set of images used for reconstructing a 3D model of a physical structure. The computer-vision network can also be configured to generate feedback at or before image capture time to guide improvements to the quality of feature correspondences between a pair of images.

Abstract: Disclosed are techniques for enhancing two-dimensional (2D) image capture of subjects (e.g., a physical structure, such as a residential building) to maximize the feature correspondences available for three-dimensional (3D) model reconstruction. More specifically, disclosed is a computer-vision network configured to provide viewfinder interfaces and analyses to guide the improved capture of an intended subject for specified purposes. Additionally, the computer-vision network can be configured to generate a metric representing a quality of feature correspondences between images of a complete set of images used for reconstructing a 3D model of a physical structure. The computer-vision network can also be configured to generate feedback at or before image capture time to guide improvements to the quality of feature correspondences between a pair of images.

Abstract: Techniques are described for identifying correspondences between images to generate a fundamental matrix for the camera positions related to the images. The resultant fundamental matrix enables epipolar geometry to correlate common features among the images. Correspondences are identified by confirming feature matches across images by applying a homography to data representing features across images. Further techniques are described herein for generating a representation of a boundary of a feature of a structure based on a digital image. In one or more embodiments, generating a representation of a boundary of a particular feature in a digital image comprises determining a portion of the image that corresponds to the structure, and determining a portion of the image that corresponds to the particular feature. One more vanishing points are associated with the portion of the image corresponding to the particular feature.

Abstract: Disclosed are techniques for enhancing two-dimensional (2D) image capture of subjects (e.g., a physical structure, such as a residential building) to maximize the feature correspondences available for three-dimensional (3D) model reconstruction. More specifically, disclosed is a computer-vision network configured to provide viewfinder interfaces and analyses to guide the improved capture of an intended subject for specified purposes. Additionally, the computer-vision network can be configured to generate a metric representing a quality of feature correspondences between images of a complete set of images used for reconstructing a 3D model of a physical structure. The computer-vision network can also be configured to generate feedback at or before image capture time to guide improvements to the quality of feature correspondences between a pair of images.

Abstract: Methods, storage media, and systems for three-dimensional building model generation based on classification of image elements. An example method includes obtaining images depicting a building, with individual images being taken at individual positions about an exterior of the building, and with the images being associated with camera properties reflecting extrinsic and/or intrinsic camera parameters. Semantic labels are determined for the images via a machine learning model, with the labels being associated with elements of the building, and with the semantic labels being associated with two-dimensional positions in the images. Three-dimensional positions associated with the plurality of elements are estimated, with estimating being based on one or more epipolar constraints. A three-dimensional representation of at least a portion of the building is generated, with the portion including a roof of the building.

Abstract: A condensation-recovery device for overpressure gas based on liquefied natural gas (LNG) cold energy, including a tank body and a condensation cavity provided on a bottom thereof. LNG is stored in the condensation cavity to condense boil-off gas (BOG). The condensation cavity includes a vertical hollow tube arranged in the tank body, and an engagement mechanism is provided on a bottom of the vertical hollow tube. The vertical hollow tube is configured such that the gas can experience preliminary contact with the LNG when flowing therein, and the gas will continuously enter the vertical hollow tube under the action of pressure difference. After entering the conical tube, the gas will be distributed along the cavity of the conical tube to spread downward, so as to increase a contact time of the gas and the LNG while avoiding expanding diffusion area of the gas after entering the LNG.

Abstract: Techniques are described for identifying correspondences between images to generate a fundamental matrix for the camera positions related to the images. The resultant fundamental matrix enables epipolar geometry to correlate common features among the images. Correspondences are identified by confirming feature matches across images by applying a homography to data representing features across images. Further techniques are described herein for generating a representation of a boundary of a feature of a structure based on a digital image. In one or more embodiments, generating a representation of a boundary of a particular feature in a digital image comprises determining a portion of the image that corresponds to the structure, and determining a portion of the image that corresponds to the particular feature. One more vanishing points are associated with the portion of the image corresponding to the particular feature.

Abstract: A self-adjusting hydraulic static penetrating device and method suitable for a seabed slope area is provided. The device includes an upper adjustable injection platform and a lower adjustable supporting platform. The upper adjustable injection platform is fixedly connected with the upper surface of the lower adjustable supporting platform. The upper adjustable injection platform includes a rack, a control cabin, an injection mechanism, a hydraulic station, a balance weight and first jacks. The control cabin, the injection mechanism, the hydraulic station, the balance weight and the first jacks are all arranged on the rack. The four first jacks are installed at the bottom of a steel structure frame, and the first jacks are fixed to the lower adjustable supporting platform. The device is simple in structure and low in cost, and can guarantee, to the maximum extent, that the overall gravity center of the device is always constant or slightly changes.

Abstract: A turning holder enabling an easy operation and a convenient use without the need for repeated mounting and dismounting is provided. The turning holder comprises a base (11), a holder body (12), and a rotary body. A base sleeve (110) is provided on the base (11). A holder sleeve (120) is provided on the holder body (12). The rotary body includes a shaft sleeve (5), a clamping sleeve for rotary shaft (8), a pressure ring (9) and a locking means. The clamping sleeve for rotary shaft (8) is sleeved outside at a groove around an end of the shaft sleeve (5). The holder sleeve (120) is sleeved on the shaft sleeve (5) in a staggered position relative to the clamping sleeve for rotary shaft (8). The base sleeve (110) is sleeved around the clamping sleeve for rotary shaft (8) and fixedly connected therewith. The pressure ring (9) is sleeved around an end of the shaft sleeve (5) and presses the clamping sleeve for rotary shaft (8) from outside.

Abstract: A turning holder enabling an easy operation and a convenient use without the need for repeated mounting and dismounting is provided. The turning holder comprises a base (11), a holder body (12), and a rotary body. A base sleeve (110) is provided on the base (11). A holder sleeve (120) is provided on the holder body (12). The rotary body includes a shaft sleeve (5), a clamping sleeve for rotary shaft (8), a pressure ring (9) and a locking means. The clamping sleeve for rotary shaft (8) is sleeved outside at a groove around an end of the shaft sleeve (5). The holder sleeve (120) is sleeved on the shaft sleeve (5) in a staggered position relative to the clamping sleeve for rotary shaft (8). The base sleeve (110) is sleeved around the clamping sleeve for rotary shaft (8) and fixedly connected therewith. The pressure ring (9) is sleeved around an end of the shaft sleeve (5) and presses the clamping sleeve for rotary shaft (8) from outside.

Abstract: An eccentric handle device which can be adapted for guiding rails of different sizes includes a base body (3), a pressure block (4), a pull rod (5), a pin (6), an eccentric handle (8) and a nut (1). The base body (3) is matched with the pressure block (4). The rod (5) passes through the base body (3) and the pressure block (4) respectively. One end of the rod (5) is movably connected with the eccentric handle (8) via the pin (6), the other end crosses the base body (3), and the rod is matched with the nut (1) by thread. The distance between the pressure block (4) and the base body (3) can be adjusted by rotating the nut (1), thus the device can be applicable to guiding rails of different sizes. The device can be widely used in the field of firearm aimer.