Abstract: Methods and systems for continuously monitoring the gaze direction of a driver of a vehicle over time. Video is received, which is captured by a camera associated with, for example, a mobile device within a vehicle, the camera and/or mobile device mounted facing the driver of the vehicle. Frames can then be extracted from the video. A facial region can then be detected, which corresponds to the face of the driver within the extracted frames. Features descriptors can then be computed from the facial region. A gaze classifier derived from the vehicle, the driver, and the camera can then be applied, wherein the gaze classifier receives the feature descriptors as inputs and outputs at least one label corresponding to one or more predefined finite number of gaze classes to identify the gaze direction of the driver of the vehicle.

Abstract: Described herein is a method of determining parking lot occupancy from digital images, including a set-up procedure that includes receiving a layout of a parking lot and estimating parking space volume for at least one viewing angle and the probability that an observed pixel belongs to the parking space volume. The method further includes acquiring one or more image frames of the parking lot from at least one digital camera; performing pixel classification using a vehicle detector on the acquired image frames to determine a likelihood that a pixel belongs to a vehicle; computing a probability that a parking space is occupied by a vehicle based on a spatially varying membership probability density function and a likelihood of vehicle pixels within a region of interest; and determining parking lot vacancy via a comparison of the computed probability that a parking space is occupied by a vehicle to a pre-determined threshold.

Abstract: Methods and systems for continuously monitoring the gaze direction of a driver of a vehicle over time. Video is received, which is captured by a camera associated with, for example, a mobile device within a vehicle, the camera and/or mobile device mounted facing the driver of the vehicle. Frames can then be extracted from the video. A facial region can then be detected, which corresponds to the face of the driver within the extracted frames. Features descriptors can then be computed from the facial region. A gaze classifier derived from the vehicle, the driver, and the camera can then be applied, wherein the gaze classifier receives the feature descriptors as inputs and outputs at least one label corresponding to one or more predefined finite number of gaze classes to identify the gaze direction of the driver of the vehicle.

Abstract: Systems and methods of controlling the width of one or more image objects in a digital image are provided which determine if one or more image objects include a line or an edge. If the image includes a line, it is processed using a line width control algorithm to modify its width. If the image includes an edge, it is processed using an edge growth control module which processes it differently than a line to modify the edge in the image object.

Abstract: A camera may be positioned to have a direct view of on-coming vehicle traffic from a first perspective. Additionally, a reflective surface, such as a mirror, may be positioned within the viewing area of the same camera to provide the camera with a reflected view of vehicle traffic from a second perspective. The images recorded by the camera may then be received by a computing device. The computing device may separate the images into a direct view region and a reflected view region. After separation, the regions may be analyzed independently and/or combined with other regions, and the analyzed data may be stored. The regions may be analyzed to determine various vehicle characteristics, including, but not limited to, vehicle speed, license plate identification, vehicle occupancy, vehicle count, and vehicle type.

Abstract: Described herein is a method of determining parking lot occupancy from digital images, including a set-up procedure that includes receiving a layout of a parking lot and estimating parking space volume for at least one viewing angle and the probability that an observed pixel belongs to the parking space volume. The method further includes acquiring one or more image frames of the parking lot from at least one digital camera; performing pixel classification using a vehicle detector on the acquired image frames to determine a likelihood that a pixel belongs to a vehicle; computing a probability that a parking space is occupied by a vehicle based on a spatially varying membership probability density function and a likelihood of vehicle pixels within a region of interest; and determining parking lot vacancy via a comparison of the computed probability that a parking space is occupied by a vehicle to a pre-determined threshold.

Abstract: A camera may be positioned to have a direct view of on-coming vehicle traffic from a first perspective. Additionally, a reflective surface, such as a mirror, may be positioned within the viewing area of the same camera to provide the camera with a reflected view of vehicle traffic from a second perspective. The images recorded by the camera may then be received by a computing device. The computing device may separate the images into a direct view region and a reflected view region. After separation, the regions may be analyzed independently and/or combined with other regions, and the analyzed data may be stored. The regions may be analyzed to determine various vehicle characteristics, including, but not limited to, vehicle speed, license plate identification, vehicle occupancy, vehicle count, and vehicle type.

Abstract: A technique for cross-channel correction in real time for digital color printing in which the full resolution value of a selected colorant is combined with low resolution versions of the remaining colorants to provide a basis for correcting the selected colorant based upon the data for the other colorants employed. The pixel values of sub-samples of the remaining colorants are derived from the cell in which the full resolution selected colorant is taken; and, the desired output value is selected from a look-up table established for the known printing process.

Abstract: In accordance with the present disclosure, there is provided a method for performing streak compensation on compressed digital image data. The method comprises generating the compressed digital image data using a compression method employing a discrete cosine transform (DCT) and recovering a zero frequency component (DC coefficient) of the discrete cosine transform (DCT) for each of a plurality of compressed unit blocks of image data wherein each unit block includes N pixel columns. The method further comprises applying spatially varying compensating tone reproduction curves (TRC) to the DC coefficients of each of the plurality of unit blocks on a block-column basis wherein each block-column receives compensation from a given TRC, re-compressing the compensated image data, and subsequently decompressing all of the compensated units to produce decompressed compensated image data.

Abstract: In accordance with the present disclosure, there is provided a method for compensating tones on a compressed digital image data. The method comprises generating the compressed digital image from an input digital image data using a wavelet-based compression method; recovering a low resolution version of the input digital image data from the compressed digital image data by partially decompressing the compressed digital image; applying compensating tone reproduction curves (TRC) to the low resolution version of the input digital image data to generate a compensated low resolution image; re-compressing the image using the compensated low resolution image; and, subsequently decompressing all of the compensated pixel arrays to produce decompressed compensated image data.

Abstract: This disclosure provides methods, apparatus and systems to generate vector halftone data for rendering an image on an image output device. According to one aspect, a method generates vector halftone data as a function of contone pixel data for a given colorant at its nominal resolution and contone pixel data for the other colorants at a relatively lower resolution.

Abstract: As provided herein, there are supplied teachings to systems and methods for resizing a digital uniform rosette halftone image composed of multiple colorant separations, by using uniform rosette halftone tile parameters and iterative determination of energy metrics. One approach entails receiving into a digital imaging system, a digital uniform rosette halftone image and a desired resizing factor for that digital uniform rosette halftone image. Subsequently the system will define uniform rosette screen parameters to define uniform rosette Holladay halftone tiles within the color uniform rosette digital halftone image. From the defined uniform rosette cells, a number of uniform rosette halftone tile seams are determined for manipulation. The orientation of the number of uniform rosette halftone tile seams is dictated by the received desired resizing factor.

Abstract: A method, computer readable medium, and computing device for resizing images. A digital image arranged in a rectangular array of pixels is received for resizing in either a horizontal direction or a vertical direction. An energy value is computed for each of the pixels, and pixels are connected to form extended 8-connectivity seams, with each seam having a cumulative energy value. The digital image is segmented into segments corresponding to lines of text and/or images. A seam is selected to best maintain proportionality of white space in the segments when the seam is either replicated or deleted. The selected seam then replicated or deleted. At least the seam selection and replication or deletion is repeated until the resized image is the desired size. The resized image is then outputted to a display screen, storage device, and/or printer.

Abstract: As provided herein, there are supplied teachings to systems and methods for resizing a digital uniform rosette halftone image composed of multiple colorant separations, by using uniform rosette halftone tile parameters. One approach entails receiving into a digital imaging system, a digital uniform rosette halftone image and a desired resizing factor for that digital uniform rosette halftone image. Subsequently the system will define uniform rosette cells within the color uniform rosette digital halftone image. From the defined uniform rosette cells, a number of uniform rosette halftone tile seams are determined for manipulation. The orientation of the number of uniform rosette halftone tile seams is dictated by the received desired resizing factor. An energy map of the digital uniform rosette halftone image is determined according to an energy metric derived from the multiple colorant separations.

Abstract: As provided herein, there are supplied teachings to systems and methods for resizing a halftone image using halftone tile parameters. One approach entails receiving into a digital imaging system, a digital halftone image and a desired resizing factor for that digital halftone image. The system will then define cells within the digital halftone image and determine from those cells, a number of halftone tile seams to suitable for manipulation. The orientation of these halftone tile seams is dictated by the received desired resizing factor. The seam energy of these halftone tile seams is then determined according to an energy metric so as to provide indication of a number of low energy determined halftone tile seams. The number of low energy seams identified is sufficient to achieve the desired resizing factor. A resizing of the halftone image is then performing by iteratively deleting the low energy determined halftone tile seams within the halftone image.

Abstract: An image processing apparatus, program product, and method determine an achievable gamut achievable by the imaging engine or engines for all spatial locations of an output image, or all utilized print engines. A reference gamut is calculated which is any gamut containing the achievable gamut. A gamut mapping is used to map gamuts from the mean gamut to the achievable gamut, and a set of transformations is calculated for each of a set of input colors to a set of target colors selected from colors in the achievable gamut. Values for a received digital image are transformed for each image pixel or clusters of pixels based on the calculated set of transformations. Output images are generated based on the transformed values.

Abstract: As provided herein, there are supplied teachings to systems and methods for resizing a halftone image using halftone tile parameters. One approach entails receiving into a digital imaging system, a digital halftone image and a desired resizing factor for the digital halftone image. Subsequently the system will define cells within the digital halftone image and determine from those cells, a number of halftone tile seams to suitable for manipulation. The orientation of these halftone tile seams is dictated by the received desired resizing factor. The energy of the number of halftone tile seams is determined according to an energy metric so as to provide indication of at least one low energy determined halftone tile seam. A resizing of the halftone image is then performing by manipulating at least one low energy halftone tile seam in the halftone image. The resized halftone image may then be printed on a printer.

Abstract: Systems and methods of controlling the width of one or more image objects in a digital image are provided which determine if one or more image objects include a line or an edge. If the image includes a line, it is processed using a line width control algorithm to modify its width. If the image includes an edge, it is processed using an edge growth control module which processes it differently than a line to modify the edge in the image object.

Abstract: This disclosure provides methods, apparatus and systems to generate vector halftone data for rendering an image on an image output device. According to one aspect, a method generates vector halftone data as a function of contone pixel data for a given colorant at its nominal resolution and contone pixel data for the other colorants at a relatively lower resolution.

Abstract: An image processing apparatus, program product, and method determine an achievable gamut achievable by the imaging engine or engines for all spatial locations of an output image, or all utilized print engines. A reference gamut is calculated which is any gamut containing the achievable gamut. A gamut mapping is used to map gamuts from the mean gamut to the achievable gamut, and a set of transformations is calculated for each of a set of input colors to a set of target colors selected from colors in the achievable gamut. Values for a received digital image are transformed for each image pixel or clusters of pixels based on the calculated set of transformations. Output images are generated based on the transformed values.