Abstract: A method for detecting objects and labeling the objects with distances in an image includes steps of: obtaining a thermal image from a thermal camera, an RGB image from an RGB camera, and radar information from an mmWave radar; adjusting the thermal image based on the RGB image to generate an adjusted thermal image, and generating a fused image based on the RGB image and the adjusted thermal image; generating a second fused image based on the fused image and the radar information; detecting objects in the images, and generating, based on the fused image, another fused image including bounding boxes marking the objects; and determining motion parameters of the objects.

Abstract: A method for detecting objects and labeling the objects with distances in an image includes steps of: obtaining a thermal image from a thermal camera, an RGB image from an RGB camera, and radar information from an mmWave radar; adjusting the thermal image based on the RGB image to generate an adjusted thermal image, and generating a fused image based on the RGB image and the adjusted thermal image; generating a second fused image based on the fused image and the radar information; detecting objects in the images, and generating, based on the fused image, another fused image including bounding boxes marking the objects; and determining motion parameters of the objects.

Abstract: A method for generating a data-bearing image is implemented by an encoding system including a halftoning module and an encoding module that stores encoding rules associated with respective codes. In the method, the halftoning module converts a grayscale image into a halftone image having a plurality of image cells each consisting of a plurality of dots, at least one of which is a first-tone dot and each of the rest of which is a second-tone dot. Afterward, the encoding module generates a data-bearing halftone image encoded with at least one of the codes by maintaining or changing the number of the first-tone dots in one of the image cells based on one of the encoding rules associated with the at least one of the codes.

Abstract: A method for generating a data-bearing image is implemented by an encoding system including a halftoning module and an encoding module that stores encoding rules associated with respective codes. In the method, the halftoning module converts a grayscale image into a halftone image having a plurality of image cells each consisting of a plurality of dots, at least one of which is a first-tone dot and each of the rest of which is a second-tone dot. Afterward, the encoding module generates a data-bearing halftone image encoded with at least one of the codes by maintaining or changing the number of the first-tone dots in one of the image cells based on one of the encoding rules associated with the at least one of the codes.

Abstract: An encoding system converts a grayscale image into an original halftone image according to a predetermined threshold matrix, determines carrier cells from the original halftone image according to reference dot patterns having rotationally asymmetric first-tone patterns, converts the carrier cells into encoded cells according to to-be-embedded codes and rotational states of corresponding asymmetric first-tone patterns, and optimizes non-carrier cells and encoded cells using a direct binary search technique to visually approach the grayscale image.

Abstract: An encoding system is for generating a data-bearing halftone image. The encoding system is configured to: convert a grayscale image into a halftone image having a plurality of image cells; select, from the halftone image, at least one of the image cells to be a carrier cell according to a set of reference dot patterns, the carrier cell having a dot pattern identical to one of the reference dot patterns; and generate a data-bearing halftone image by replacing the dot pattern of the carrier cell by a specified one of multiple encoding dot patterns of one of a plurality of the sets of encoding dot patterns each being associated with a code. The data-bearing halftone image is encoded with a code associated with the one of the sets of the encoding dot patterns.

Abstract: An encoding system converts a grayscale image into an original halftone image according to a predetermined threshold matrix, determines carrier cells from the original halftone image according to reference dot patterns having rotationally asymmetric first-tone patterns, converts the carrier cells into encoded cells according to to-be-embedded codes and rotational states of corresponding asymmetric first-tone patterns, and optimizes non-carrier cells and encoded cells using a direct binary search technique to visually approach the grayscale image.

Abstract: An encoding system is for generating a data-bearing halftone image. The encoding system is configured to: convert a grayscale image into a halftone image having a plurality of image cells ; select, from the halftone image, at least one of the image cells to be a carrier cell according to a set of reference dot patterns, the carrier cell having a dot pattern identical to one of the reference dot patterns ; and generate a data-bearing halftone image by replacing the dot pattern of the carrier cell by a specified one of multiple encoding dot patterns of one of a plurality of the sets of encoding dot patterns each being associated with a code. The data-bearing halftone image is encoded with a code associated with the one of the sets of the encoding dot patterns.

Abstract: A method and system to generate a moiré-free to all-orders N-color screen-set by a lattice-based screen design the method including choosing a lattice in frequency space with basis vectors u1 and u2 such that (?{right arrow over (u)}1?,?{right arrow over (u)}2?,?{right arrow over (u)}1±{right arrow over (u)}2?)>f min, where f min is the minimum moiré invisible to the human eye, and choosing a set of N pairs of fundamental frequency vectors on the vertices of this lattice to be the screen vectors.

Abstract: A method and system to generate a moiré-free to all-orders N-color screen-set by a lattice-based screen design the method including choosing a lattice in frequency space with basis vectors u1 and u2 such that (?{right arrow over (u)}1?,?{right arrow over (u)}2?,?{right arrow over (u)}1±{right arrow over (u)}2?)>f min, where f min is the minimum moiré invisible to the human eye, and choosing a set of N pairs of fundamental frequency vectors on the vertices of this lattice to be the screen vectors.

Abstract: A method for designing a screen set for color halftoning includes selecting a screen set that includes at least two screens. The screens are applied to a uniform color image so as to form a set of corresponding colorant halftones. The colorant halftones are superposed to form a color halftone. A spatial frequency spectrum of the color halftone is calculated. Maxima of the spatial frequency spectrum that occur at two effective frequencies are identified, the two effective frequencies being located in two adjacent quadrants of a complex spatial frequency space. A magnitude of each effective frequency is compared with a predetermined frequency magnitude. The screen set is accepted for future application for color halftoning only if both effective frequency magnitudes are greater than the predetermined frequency magnitude. Relating computer program product and data processing system are also disclosed.

Abstract: A method for designing a screen set for color halftoning includes selecting a screen set that includes at least two screens. The screens are applied to a uniform color image so as to form a set of corresponding colorant halftones. The colorant halftones are superposed to form a color halftone. A spatial frequency spectrum of the color halftone is calculated. Maxima of the spatial frequency spectrum that occur at two effective frequencies are identified, the two effective frequencies being located in two adjacent quadrants of a complex spatial frequency space. A magnitude of each effective frequency is compared with a predetermined frequency magnitude. The screen set is accepted for future application for color halftoning only if both effective frequency magnitudes are greater than the predetermined frequency magnitude. Relating computer program product and data processing system are also disclosed.