Abstract: A vehicle license plate recognition method includes: performing the vehicle license plate recognition on the obtained fisheye image to obtain the vehicle plate region; in response to the vehicle license plate region being in the non-reference direction, enlarging the vehicle license plate region based on all pixels of the vehicle license plate region to obtain the deformed image of the vehicle license plate; the resolution of the deformed image of the vehicle license plate being higher than the resolution of the vehicle license plate region; reference direction correction is performed on the deformed image of the vehicle license plate to obtain the to-be-detected image; and recognizing the to-be-detected image to obtain the output character corresponding to the vehicle license plate region.

Abstract: A field of environmental protection and discloses a method for preparing an amorphous silica-alumina encapsulated metal oxide catalyst and application thereof. The catalyst is prepared by filling silica-alumina precursors in tunnels of a monometallic or bimetallic complex and then performing heat treatment. The catalyst has the advantages that acidic sites and oxygen vacancies are highly dispersed, the pore size range is large and the mass transfer efficiency is high, improves the efficiency of a cracking-oxidation tandem reaction, and achieves full purification of carbon/nitrogen pollutants in landfill leachate. The COD removal rate of the landfill leachate reaches 98.3% or above, and the ammonia nitrogen removal rate thereof reaches 98.0% or above. The COD concentration of oxypyrolysis purified effluent is less than 98.7 mg/L and the ammonia nitrogen concentration thereof is less than 24.9 mg/L.

Abstract: A virtual scene transformation method includes: displaying a first virtual scene picture, the first virtual scene picture comprising a first scene model in a virtual scene, and the first virtual scene picture being about the virtual scene observed by a virtual object; while the virtual scene is observed by the virtual object, displaying a scene transformation when the virtual scene meets a scene transformation condition, the scene transformation including a first stage in which the first scene model is gradually deleted, and a second stage in which a second scene model is gradually generated in the virtual scene, the second stage lagging behind the first stage; and displaying a second virtual scene picture when the scene transformation is completed, the second virtual scene picture comprising the second scene model.

Abstract: This application discloses a virtual picture display method performed by a computer device. The method includes: displaying a virtual environment picture, the virtual environment picture comprising a first object and a virtual prop controlled by a first virtual object; receiving an interaction operation for the first virtual object to interact with the first object by using the virtual prop, and the first region comprising a first environment element; in response to the interaction operation and the first object meeting an environment switching condition, displaying an element switching process of switching a first environment element located in a first region of the virtual environment to a second environment element; and in response to completion of the element switching process, displaying the second environment element located in the first region of the virtual environment.

Abstract: A prop control method in a virtual scene is performed by a computer device. The method includes: displaying a first scene picture of the virtual scene, the first scene picture including a first virtual object and a scene element; when a distance between the first virtual object and the scene element in the virtual scene meets a predefined condition, receiving a prop pull operation for the scene element by the first virtual object; and in response to the prop pull operation for the scene element, controlling the first virtual object pull a target virtual prop corresponding to the scene element closer to the first virtual object. By using the foregoing method, when a user controls a virtual object to interact with a virtual prop, the power consumption and data usage of a computer device is reduced.

Abstract: The present invention provides a new energy-driven in-situ plankton collecting device, comprising a solar photovoltaic cell and wind power generation system, a buoyancy support system, a power supply and control system, a plankton suction and collection system, and an anchoring system. The device has the center of gravity on the lower part and vertically floats in water like a tumbler. The plankton suction and collection system is composed of a suction axial-flow pump and a collecting cod end. The bag-shaped plankton collecting cod end has the mesh aperture of less than 0.8 time the average body length of the target plankton, and can be used on both sides. The devices provided by the present invention can be used simultaneously and arranged in an array for collection and utilization of plankton as well as governance and remediation of water area environment, and thus have a favorable application prospect.

Abstract: The present invention provides a new energy-driven in-situ plankton collecting device, comprising a solar photovoltaic cell and wind power generation system, a buoyancy support system, a power supply and control system, a plankton suction and collection system, and an anchoring system. The device has the center of gravity on the lower part and vertically floats in water like a tumbler. The plankton suction and collection system is composed of a suction axial-flow pump and a collecting cod end. The bag-shaped plankton collecting cod end has the mesh aperture of less than 0.8 time the average body length of the target plankton, and can be used on both sides. The devices provided by the present invention can be used simultaneously and arranged in an array for collection and utilization of plankton as well as governance and remediation of water area environment, and thus have a favorable application prospect.

Abstract: Plane detection and tracking algorithms are described that may take point trajectories as input and provide as output a set of inter-image homographies. The inter-image homographies may, for example, be used to generate estimates for 3D camera motion, camera intrinsic parameters, and plane normals using a plane-based self-calibration algorithm. A plane detection and tracking algorithm may obtain a set of point trajectories for a set of images (e.g., a video sequence, or a set of still photographs). A 2D plane may be detected from the trajectories, and trajectories that follow the 2D plane through the images may be identified. The identified trajectories may be used to compute a set of inter-image homographies for the images as output.

Abstract: A composition model is developed based on the image segmentation and the vanishing point of the scene. By integrating both photometric and geometric cues, better segmentation is provided. These cues are directly used to detect the dominant vanishing point in an image without extracting any line segments. Based on the composition model, a novel image retrieval system is developed which can retrieve images with similar compositions as the query image from a collection of images and provide feedback to photographers.

Abstract: Robust techniques for self-calibration of a moving camera observing a planar scene. Plane-based self-calibration techniques may take as input the homographies between images estimated from point correspondences and provide an estimate of the focal lengths of all the cameras. A plane-based self-calibration technique may be based on the enumeration of the inherently bounded space of the focal lengths. Each sample of the search space defines a plane in the 3D space and in turn produces a tentative Euclidean reconstruction of all the cameras that is then scored. The sample with the best score is chosen and the final focal lengths and camera motions are computed. Variations on this technique handle both constant focal length cases and varying focal length cases.

Abstract: Robust techniques for self-calibration of a moving camera observing a planar scene. Plane-based self-calibration techniques may take as input the homographies between images estimated from point correspondences and provide an estimate of the focal lengths of all the cameras. A plane-based self-calibration technique may be based on the enumeration of the inherently bounded space of the focal lengths. Each sample of the search space defines a plane in the 3D space and in turn produces a tentative Euclidean reconstruction of all the cameras that is then scored. The sample with the best score is chosen and the final focal lengths and camera motions are computed. Variations on this technique handle both constant focal length cases and varying focal length cases.

Abstract: Plane detection and tracking algorithms are described that may take point trajectories as input and provide as output a set of inter-image homographies. The inter-image homographies may, for example, be used to generate estimates for 3D camera motion, camera intrinsic parameters, and plane normals using a plane-based self-calibration algorithm. A plane detection and tracking algorithm may obtain a set of point trajectories for a set of images (e.g., a video sequence, or a set of still photographs). A 2D plane may be detected from the trajectories, and trajectories that follow the 2D plane through the images may be identified. The identified trajectories may be used to compute a set of inter-image homographies for the images as output.

Abstract: Robust techniques for self-calibration of a moving camera observing a planar scene. Plane-based self-calibration techniques may take as input the homographies between images estimated from point correspondences and provide an estimate of the focal lengths of all the cameras. A plane-based self-calibration technique may be based on the enumeration of the inherently bounded space of the focal lengths. Each sample of the search space defines a plane in the 3D space and in turn produces a tentative Euclidean reconstruction of all the cameras that is then scored. The sample with the best score is chosen and the final focal lengths and camera motions are computed. Variations on this technique handle both constant focal length cases and varying focal length cases.

Abstract: A composition model is developed based on the image segmentation and the vanishing point of the scene. By integrating both photometric and geometric cues, better segmentation is provided. These cues are directly used to detect the dominant vanishing point in an image without extracting any line segments. Based on the composition model, a novel image retrieval system is developed which can retrieve images with similar compositions as the query image from a collection of images and provide feedback to photographers.

Abstract: Plane detection and tracking algorithms are described that may take point trajectories as input and provide as output a set of inter-image homographies. The inter-image homographies may, for example, be used to generate estimates for 3D camera motion, camera intrinsic parameters, and plane normals using a plane-based self-calibration algorithm. A plane detection and tracking algorithm may obtain a set of point trajectories for a set of images (e.g., a video sequence, or a set of still photographs). A 2D plane may be detected from the trajectories, and trajectories that follow the 2D plane through the images may be identified. The identified trajectories may be used to compute a set of inter-image homographies for the images as output.

Abstract: Plane detection and tracking algorithms are described that may take point trajectories as input and provide as output a set of inter-image homographies. The inter-image homographies may, for example, be used to generate estimates for 3D camera motion, camera intrinsic parameters, and plane normals using a plane-based self-calibration algorithm. A plane detection and tracking algorithm may obtain a set of point trajectories for a set of images (e.g., a video sequence, or a set of still photographs). A 2D plane may be detected from the trajectories, and trajectories that follow the 2D plane through the images may be identified. The identified trajectories may be used to compute a set of inter-image homographies for the images as output.

Abstract: Robust techniques for self-calibration of a moving camera observing a planar scene. Plane-based self-calibration techniques may take as input the homographies between images estimated from point correspondences and provide an estimate of the focal lengths of all the cameras. A plane-based self-calibration technique may be based on the enumeration of the inherently bounded space of the focal lengths. Each sample of the search space defines a plane in the 3D space and in turn produces a tentative Euclidean reconstruction of all the cameras that is then scored. The sample with the best score is chosen and the final focal lengths and camera motions are computed. Variations on this technique handle both constant focal length cases and varying focal length cases.