Abstract: A power supply system includes a RF power source configured to generate an output signal at an output frequency, a signal source configured to generate a perturbation signal, an extremum seeking frequency controller configured to generate a frequency control signal based on the perturbation signal, and a frequency selector configured to select a perturbation frequency of the perturbation signal that is isolated from at least one frequency tone associated with the power supply system. The frequency control signal varies the output frequency of the RF power source. Other example power supply system, methods for controlling a RF generator, and control systems for controlling a RF generator are also disclosed.

Abstract: A RF generator includes a RF power source configured to generate an output signal at an output frequency, and an extremum-seeking frequency controller configured to generate a frequency control signal. The frequency control signal varies the output frequency of the RF power source, and the frequency control signal is formed from a gradient signal. The RF generator further includes a gradient estimator configured to generate the gradient signal. A frequency of the frequency control signal is adjusted based on the gradient signal. The gradient estimator is configured to receive frequency values of the frequency control signal and corresponding output response values, and the gradient signal is generated based on the frequency values and the output response values. Other example RF generators, methods for extremum-seeking frequency control of a RF generator, and control systems for controlling a RF generator are also disclosed.

Abstract: A power generator includes a power source and a control module coupled to the power source. The control module is configured to generate at least one control signal to vary a respective at least one of an output signal from the power source or an impedance between the power source and a load. The output signal includes a signal modulated by a pulse signal, and the control module is further configured to adjust the at least one control signal to vary at least one of an amplitude or a frequency of the output signal or the impedance between the power source and the load to control a shape of the pulse signal. The at least one of the amplitude, the frequency, or the impedance is adjusted in accordance with respective feedforward adjustments that vary in accordance with a respective sensed pulse parameter detected between a matching network and the load.

Abstract: A radio frequency (RF) generator includes a RF power source configured to output an RF power signal, and a controller coupled to the RF power source. The controller is configured to generate a pulse to modulate the RF power signal of the RF power source. The pulse includes one or more state transitions. The controller is further configured to receive a sync signal indicative of one or more operating characteristics or parameters of another RF generator, and adjust at least one of the state transitions of the pulse to synchronize the state transition with a defined phase of the received sync signal. Other example RF generators, RF power delivery systems including one or more RF generators, and control methods for adjusting a state transition of a pulse to synchronize the state transition with a defined phase of a sync signal are also disclosed.

Abstract: A radio frequency (RF) power generation system includes a RF power source that generates a RF output signal delivered to a load. A RF power controller is configured to generate a control signal to vary the RF output signal. The controller adjusts a parameter associated with the RF output signal, and the parameter is controlled in accordance with a trigger signal. The parameter is adjusted in accordance with a cost function, and the cost function is determined by intruding a perturbation into an actuator that affects the cost function. The actuator may control an external RF output signal, and the trigger signal may vary in accordance with the external RF output signal.

Abstract: A dynamic digital signage system based on measured customer behaviors through video analytics.

Abstract: A dynamic digital signage system based on measured customer behaviors through video analytics.

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: Methods and systems for detecting anomalies in transportation related video footage. In an offline training phase, receiving video footage of a traffic location can be received. Also, in an offline training phase, event encodings can be extracted from the video footage and collected or compiled into a training dictionary. One or more input video sequences captured at the traffic location or a similar traffic location can be received in an online detection phase. Then, an event encoding corresponding to the input video sequence can be extracted. The event encoding can be reconstructed with a low rank sparsity prior model applied with respect to the training dictionary. The reconstruction error between actual and reconstructed event encodings can then be computed in order to determine if an event thereof is anomalous by comparing the reconstruction error with a threshold.

Abstract: Methods and systems for automatically detecting multi-object anomalies at a traffic intersection utilizing a joint sparse reconstruction model. A first input video sequence at a first traffic location can be received and at least one normal event involving P moving objects (where P is greater than or equal to 1) can be identified in an offline training phase. The normal event in the first input video sequence can be assigned to at least one normal event class and a training dictionary suitable for joint sparse reconstruction can be built in the offline training phase. A second input video sequence captured at a second traffic location similar to the first traffic location can be received and at least one event involving P moving objects can be identified in an online detection phase.

Abstract: Methods, systems and processor-readable media for adaptive character segmentation in an automatic license plate recognition application. A region of interest can be identified in an image of a license plate acquired via an automatic license plate recognition engine. Characters in the image with respect to the region of interest can be segmented using a histogram projection associated with particular segmentation threshold parameters. The characters in the image can be iteratively validated if a minimum number of valid characters is determined based on the histogram projection and the particular segmentation threshold parameters to produce character images sufficient to identify the license plate.

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: Methods and systems for detecting anomalies in transportation related video footage. In an offline training phase, receiving video footage of a traffic location can be received. Also, in an offline training phase, event encodings can be extracted from the video footage and collected or compiled into a training dictionary. One or more input video sequences captured at the traffic location or a similar traffic location can be received in an online detection phase. Then, an event encoding corresponding to the input video sequence can be extracted. The event encoding can be reconstructed with a low rank sparsity prior model applied with respect to the training dictionary. The reconstruction error between actual and reconstructed event encodings can then be computed in order to determine if an event thereof is anomalous by comparing the reconstruction error with a threshold.

Abstract: Methods, systems and processor-readable media for adaptive character segmentation in an automatic license plate recognition application. A region of interest can be identified in an image of a license plate acquired via an automatic license plate recognition engine. Characters in the image with respect to the region of interest can be segmented using a histogram projection associated with particular segmentation threshold parameters. The characters in the image can be iteratively validated if a minimum number of valid characters is determined based on the histogram projection and the particular segmentation threshold parameters to produce character images sufficient to identify the license plate.

Abstract: Methods and systems for automatically detecting multi-object anomalies at a traffic intersection utilizing a joint sparse reconstruction model. A first input video sequence at a first traffic location can be received and at least one normal event involving P moving objects (where P is greater than or equal to 1) can be identified in an offline training phase. The normal event in the first input video sequence can be assigned to at least one normal event class and a training dictionary suitable for joint sparse reconstruction can be built in the offline training phase. A second input video sequence captured at a second traffic location similar to the first traffic location can be received and at least one event involving P moving objects can be identified in an online detection phase.

Abstract: A cleaning blade assembly within a printing device is positioned to contact a surface to be cleaned. There is a first opening within the cleaning blade assembly and a first pin within the first opening. There is also a second opening within the cleaning blade assembly, and a second pin within the second opening. The first and second pins connect the cleaning blade assembly to the printing device. The first pin has a first cam surface that is rounded and is off-center with respect to the axis of the first pin. The cam surface is parallel to the axis of the first pin and is positioned within the first opening such that rotation of the first pin within the first opening causes the cleaning blade assembly to move in a direction perpendicular to the axis of the first pin.

Abstract: A printing system includes a plurality of printers, at least a first and a second of the plurality of printers printing in a first print modality. A scheduling system schedules printing of a set of pages by the plurality of printers. The set of pages, when assembled, may include pages where a high level of consistency is desired, such as facing pages or pages which are otherwise to be placed in close relationship. The scheduling system includes at least two scheduling modes, a first mode in which a consistency constraint is applied to the set of pages, and a second mode, different from the first mode, in which the consistency constraint is not applied. The printing system is configured for printing the set of pages in accordance with the first mode and in accordance with the second mode.

Abstract: Disclosed is a method and apparatus for sensing residual toner mass after transfer of a xerographic image, to facilitate the identification and characterization of different types of transfer defects. The technique employed utilizes a nominal residual mass signature, measured at the start of a job, in conjunction with subsequent residual mass signature, where the calculated difference between the nominal and subsequent signatures is used to indicate transfer defects and changes in transfer efficiency.

Abstract: A development system for an electrophotographic system including: a magnetic brush roll speed selector for selecting a rotational speed for a magnetic brush roll in a development system of the electrophotographic system; and a controller, responsive to the rotational speed, for adjusting xerographic actuators to maintain DMA within a predefined range.

Abstract: A defect analysis system for a xerographic print engine includes a residual mass sensor that senses the two-dimensional signature structure of residual mass remaining on a photoconductive or other substrate surface after image transfer. Preferably, the sensor is a full width array that spans substantially an entire width of the photoconductive surface. This information is then processed and analyzed to determine a specific type of transfer defect present. This may include the quantified level of defect for each detected type. The defect analysis system may also include a closed-loop control system that can adjust various xerographic process parameters using feedback based on the identification and optionally magnitude of each specific defect type. The identified print quality defect, such as mottle, streaks, point deletions, graininess, etc.