Abstract: Disclosed are a method and apparatus for recognizing a landmark in a panoramic image. The method includes steps of performing projection transformation on the panoramic image so as to generate a projection image; conducting semantic segmentation on the projection image so as to determine a landmark region and a road surface region; correcting distortion in the landmark region so as to produce a corrected landmark region; and recognizing the landmark in the corrected landmark region.

Abstract: Disclosed are a method and apparatus for recognizing a landmark in a panoramic image. The method includes steps of performing projection transformation on the panoramic image so as to generate a projection image; conducting semantic segmentation on the projection image so as to determine a landmark region and a road surface region; correcting distortion in the landmark region so as to produce a corrected landmark region; and recognizing the landmark in the corrected landmark region.

Abstract: A person counting method and a person counting system are provided. The method includes extracting a group of person images to obtain a first image set; dividing the first image set into first and second subsets based on whether a related image exists in a second image set, and reusing a person ID of the related image; estimating posture patterns of images in the first subset, and storing the images in the first subset into an image library based on person IDs and the posture patterns; and selecting a target image whose similarity to an image in the second subset is highest from the image library, reusing a person ID of the target image when the similarity is greater than a threshold, and assigning a new person ID and incrementing a person counter by 1 when the similarity is not greater than the threshold.

Abstract: A person counting method and a person counting system are provided. The method includes extracting a group of person images to obtain a first image set; dividing the first image set into first and second subsets based on whether a related image exists in a second image set, and reusing a person ID of the related image; estimating posture patterns of images in the first subset, and storing the images in the first subset into an image library based on person IDs and the posture patterns; and selecting a target image whose similarity to an image in the second subset is highest from the image library, reusing a person ID of the target image when the similarity is greater than a threshold, and assigning a new person ID and incrementing a person counter by 1 when the similarity is not greater than the threshold.

Abstract: Camera device and method for shooting light having at least two wavelength bands are disclosed. The camera device includes a first camera containing a first lens for receiving light having a first wavelength band; a second camera including a second lens for receiving light having a second wavelength band which is different from the first wavelength band, the second lens being disposed facing the first lens of the first camera; and a parabolic mirror set between the first camera and the second camera, able to let the light having the first wavelength band penetrate therethrough, and at the same time, reflect the light having the second wavelength band. The first camera is a non-fisheye camera. The first lens is a non-fisheye lens. The second camera and the parabolic mirror form a catadioptric camera. The aperture stop of the non-fisheye lens coincides with the focal point of the parabolic mirror.

Abstract: An image processing method include projecting first and second images which are captured by two fisheye lenses onto first and second hemispherical projection models, respectively; determining a set of waiting-for-stitching surface region pairs on the first and second hemispherical projection models; extracting feature points from the two fisheye images and determining feature points matching each other to serving as pixels matching each other; determining a set of surface region pairs including the pixels matching each other on the first and second hemispherical projection models as the set of waiting-for-stitching surface region pairs; generating a customized projection model on the grounds of the set of waiting-for-stitching surface region pairs by letting a spherical distance between vertexes of each pair in the set of waiting-for-stitching surface region pairs be zero; and generating a third image by projecting the first and second images onto the customized projection model.

Abstract: Three dimensional image fusion method and device are disclosed. The method includes steps of obtaining a spherical image and a two dimensional image; projecting the two dimensional image onto a planar surface predetermined in a spherical coordinate system where the spherical image is located, so as to acquire a projected image having a predetermined number of feature points on the spherical surface corresponding to the spherical image; determining multiple mapping points on the spherical surface which correspond to the predetermined number of feature points, letting the predetermined number of feature points superpose on the multiple mapping points, respectively, and carrying out spatial coordinate conversion, so as to attain a converted image; and mapping multiple points except the predetermined number of feature points in the converted image onto the spherical image based on a predetermined mapping relationship, so as to fuse the two dimensional image onto the spherical image.

Abstract: A ski mat is provided in the present application, comprising a baseplate used for paving a ski field and a plurality of supports mounted on the baseplate to support skiing tools, wherein a mounting base capable of mounting the supports on the baseplate is provided on bottoms of the supports, and a plurality of connectors are provided on a bottom of the mounting base; a plurality of mounting holes capable of clamping the connectors are provided on the baseplate at positions corresponding to the connectors; and, the connectors is clamped into the mounting holes so that the supports are mounted on the baseplate. By clamping the connectors arranged on the supports to the baseplate, it is firmer and difficult to result in a separation of the baseplate and the supports, thus it is safer. The present application also provides a spliced baseplate used for the ski mat.

Abstract: A ski mat is provided in the present application, comprising a baseplate used for paving a ski field and a plurality of supports mounted on the baseplate to support skiing tools, wherein a mounting base capable of mounting the supports on the baseplate is provided on bottoms of the supports, and a plurality of connectors are provided on a bottom of the mounting base; a plurality of mounting holes capable of clamping the connectors are provided on the baseplate at positions corresponding to the connectors; and, the connectors is clamped into the mounting holes so that the supports are mounted on the baseplate. By clamping the connectors arranged on the supports to the baseplate, it is firmer and difficult to result in a separation of the baseplate and the supports, thus it is safer. The present application also provides a spliced baseplate used for the ski mat.

Abstract: Camera device and method for shooting light having at least two wavelength bands are disclosed. The camera device includes a first camera containing a first lens for receiving light having a first wavelength band; a second camera including a second lens for receiving light having a second wavelength band which is different from the first wavelength band, the second lens being disposed facing the first lens of the first camera; and a parabolic mirror set between the first camera and the second camera, able to let the light having the first wavelength band penetrate therethrough, and at the same time, reflect the light having the second wavelength band. The first camera is a non-fisheye camera. The first lens is a non-fisheye lens. The second camera and the parabolic mirror form a catadioptric camera. The aperture stop of the non-fisheye lens coincides with the focal point of the parabolic mirror.

Abstract: Three dimensional image fusion method and device are disclosed. The method includes steps of obtaining a spherical image and a two dimensional image; projecting the two dimensional image onto a planar surface predetermined in a spherical coordinate system where the spherical image is located, so as to acquire a projected image having a predetermined number of feature points on the spherical surface corresponding to the spherical image; determining multiple mapping points on the spherical surface which correspond to the predetermined number of feature points, letting the predetermined number of feature points superpose on the multiple mapping points, respectively, and carrying out spatial coordinate conversion, so as to attain a converted image; and mapping multiple points except the predetermined number of feature points in the converted image onto the spherical image based on a predetermined mapping relationship, so as to fuse the two dimensional image onto the spherical image.

Abstract: Image processing method and device are disclosed. The method comprises a step of projecting a first image and a second image onto a first hemispherical projection model and a second hemispherical projection model, respectively; a step of determining a set of waiting-for-stitching surface region pairs on the first hemispherical projection model and the second hemispherical projection model; a step of generating a customized projection model based on the set of waiting-for-stitching surface region pairs; and a step of projecting the first image and the second image onto the customized projection model so as to create a third image. The first image and the second image are fisheye images captured in opposite imaging directions from the same position.

Abstract: Disclosed are a scene video switch system and a scene video switch method. The system comprises an input unit configured to input an image currently captured by a video capture unit to serve as a current image; a detection unit configured to detect all of interesting elements and latent elements in the current image so as to determine a maximum possible existing area of the interesting elements; a state switch unit configured to carry out, by using a predetermined finite state machine, switching between scene states of the maximum possible existing area according to predetermined different scene states and switching conditions; and a display unit configured to extract, based on a current scene state switched by the state switch unit, an area of concern coinciding with the current scene state from the maximum possible existing area to serve as a scene video for display.

Abstract: A screen area capturing an image including the screen area; obtaining candidate boundaries of the screen area; converting the candidate boundaries into straight lines; carrying out binary image processing with regard to the captured image; obtaining boundary pixels of a maximum target area, and letting the boundary pixels serve as an outline of the maximum target area; selecting straight lines on the outline from the converted straight lines; dividing the selected straight lines into four classes; and obtaining final straight lines by carrying out straight line fitting with regard to straight lines in the respective classes so as to obtain four boundaries of the screen area.

Abstract: Disclosed are a scene video switch system and a scene video switch method. The system comprises an input unit configured to input an image currently captured by a video capture unit to serve as a current image; a detection unit configured to detect all of interesting elements and latent elements in the current image so as to determine a maximum possible existing area of the interesting elements; a state switch unit configured to carry out, by using a predetermined finite state machine, switching between scene states of the maximum possible existing area according to predetermined different scene states and switching conditions; and a display unit configured to extract, based on a current scene state switched by the state switch unit, an area of concern coinciding with the current scene state from the maximum possible existing area to serve as a scene video for display.

Abstract: Disclosed are a method and a system for detecting a screen area. The method comprises a step of capturing an image including the screen area; a step of obtaining candidate boundaries of the screen area; a step of converting the candidate boundaries into straight lines; a step of carrying out binary image processing with regard to the captured image; a step of obtaining boundary pixels of a maximum target area, and letting the boundary pixels serve as an outline of the maximum target area; a step of selecting straight lines on the outline from the converted straight lines; a step of dividing the selected straight lines into four classes; and a step of obtaining final straight lines by carrying out straight line fitting with regard to straight lines in the respective classes so as to obtain four boundaries of the screen area.