Watermarking of images via 2nd generation stochastic seed frequency modulation

    公开(公告)号:GB2498617A

    公开(公告)日:2013-07-24

    申请号:GB201220877

    申请日:2012-11-20

    Applicant: XEROX CORP

    Abstract: Computer-implemented methods and systems facilitate watermarking documents and/or images using 2nd generation stochastic halftoning. The watermark is used to spatially vary the grey level at which a frequency modulation (FM)-to-amplitude modulation (AM) transition T1 or T2 occurs. Transition can occur at T1 for water marked areas and at T2 for non-watermarked areas. The encoding algorithm uses as inputs a contone image and a watermark. The visibility of the watermark is controlled by the magnitude of the difference between the AM-to-FM transition threshold values. Alternatively a first halftone threshold array can be used for watermark areas and a second threshold array for non-watermark areas. Another method can use a first principle seed frequency and second principle seed frequency for watermark and non watermark areas. The watermarks can be decoded by determining local dot and hole counts and comparing to first and second stochastic screen signatures.

    Estimating vehicle speed from video stream motion vectors

    公开(公告)号:GB2507395A

    公开(公告)日:2014-04-30

    申请号:GB201315315

    申请日:2013-08-28

    Applicant: XEROX CORP

    Abstract: Video motion vector clusters corresponding to a moving vehicle are identified and tracked across multiple frames of captured video. Movement of the motion vector clusters is translated from pixels per second to real speed (e.g. kilometres or miles per hour) to determine whether the vehicle is speeding. Estimated speed data is added to the video stream data as metadata, and video segments of candidate speeding vehicles are stored or transmitted for subsequent automated or manual review. Automated low-complexity video-based vehicle speed estimation is thereby provided. The system may form part of a multi-layer speed enforcement system, in which deeper layers provide enhanced accuracy on selected candidate (speeding) vehicles.

    Determining parking lot occupancy from digital camera images

    公开(公告)号:GB2502187A

    公开(公告)日:2013-11-20

    申请号:GB201305127

    申请日:2013-03-20

    Applicant: XEROX CORP

    Abstract: Parking lot occupancy is determined from digital images and includes a set-up procedure that receives a layout of a parking lot 201and estimates parking space volume 202 for at least one viewing angle and determines probability that an observed pixel belongs to the parking space volume. One or more images frames of the parking lot are acquired 203 from at least one digital camera and pixels are classified 204 using a vehicle detector to determine a likelihood that a pixel belongs to a vehicle. The probability that a parking space is occupied 205 by a vehicle is computed based on a spatially varying membership probability density function and a likelihood of vehicle pixels within a region of interest. Parking lot vacancy is determined 206 by comparison of the computed probability that a parking space is occupied by a vehicle to a pre-determined threshold. Pixel classification may be performed by a support vector machine classifier that uses rotation invariant local binary patterns or a TextonBoost classifier.

    Video-based detection for short-term parking violation

    公开(公告)号:GB2502687A

    公开(公告)日:2013-12-04

    申请号:GB201305903

    申请日:2013-04-02

    Applicant: XEROX CORP

    Abstract: A method for determining the occurrence of a short-term parking violation includes receiving video data S404 in a sequence of frames provided by an image capture device monitoring a parking area over a duration of time. The presence of a vehicle captured in at least one of the sequence of frames is determined S406. The location of the vehicle is tracked across the sequence of frames S410 and spatio-temporal information describing the location of the vehicle as a function of time is determined S416. In response to the spatio­temporal information indicating that the vehicle becomes stationary, the method determines a duration that the vehicle is stationary using the determined spatio temporal information S418. The presence of the vehicle can be determined by background subtraction, temporal difference, optical flow and an initialisation process. When the duration has exceeded a threshold S420 a notification of parking regulation violation can be notified S422.

    Vehicle reverse detection method and system via video acquisition and processing

    公开(公告)号:GB2496278A

    公开(公告)日:2013-05-08

    申请号:GB201218997

    申请日:2012-10-23

    Applicant: XEROX CORP

    Abstract: A video camera and video processing alert system for detecting a vehicle in reverse. The system operates according to the following guidelines or steps: (i) Acquire video 5 containing features relevant to reverse detection. (ii) Identify 10 feature(s) within the video frame that are relevant to a vehicle in reverse. (iii) Examine 15 identified features to extract the evidence of vehicle backing up / reversing for a current frame. (iv) Apply 20 temporal filtering on the frame-to-frame evidence. (v) Use 25 filtered evidence for decision on triggering the alarm. (vi) Triggering 30 an alarm if indicated by the decision. Preferably the system is used in a drive-through to detect a reversing vehicle. The camera (50, 51; figure 4) may be positioned to enable viewing of back up lights associated with a vehicle. The features identified in step (ii) may be a brake light, a reversing light, a licence plate, a decal, a running light, a reflective object or a bright spot associated with a vehicle.

Patent Agency Ranking