Abstract: Systems and devices to perform content authoring and establish conversation models for automated agents such as chatbots and virtual assistants are disclosed. In an example, operations for content authoring, to produce a conversation model, include: identifying respective intents from conversation segments in an unstructured data source; generating a knowledge graph of the conversation model to organize the identified intents; linking the intents in the knowledge graph to properties of the respective conversations, for properties used to guide a subject conversation with the conversation model; and outputting the conversation model, to be usable with the automated agent to conduct the subject conversation with a human user.

Abstract: Generally discussed herein are devices, systems, and methods for visualization of user intent in accessing a virtual agent. A method can include receiving sentences from the respective interaction sessions, projecting the sentences to a higher-dimensional space to create respective higher-dimensional vectors, projecting the higher-dimensional vectors to a lower-dimensional space to create respective lower-dimensional vectors, the lower-dimensional space including either two dimensions or three dimensions, plotting the lower-dimensional vectors as respective points on a graph, encoding the respective points consistent with the respective intents determined to be associated with the sentences by an intent classifier to create encoded points, and generating a visual representation of the encoded points.

Abstract: An imaging system includes a first optical module including a first image sensor, a second optical module comprising a second image sensor, and an image processor. The first optical module has a first focal length range. The second optical module has a second focal length range. The first focal length range and the second focal length range are different. The image processor is configured to receive image data for a first image from the first optical module and/or image data for a second image from the second optical module and generate data to show the first image and/or the second image within a display.

Abstract: System and method can support an image processing device. The image processing device operates to obtain a first set of characterization values, which represents a first group of pixels that are associated with a denoising pixel in an image. Also, the image processing device can obtain a second set of characterization values, which represents a second group of pixels that are associated with a denoising reference pixel. Furthermore, the image processing device operates to use the first set of characterization values and the second set of characterization values to determine a similarity between the denoising pixel and the denoising reference pixel. Then, the image processing device can calculate a denoised value for the denoising pixel based on the determined similarity between the denoising pixel and the denoising reference pixel.

Abstract: A method for generating panoramic images includes controlling a carrier to rotate an image capturing device around at least a first axis of the carrier, controlling the carrier to stabilize the image capturing device against vibrations or disturbances with respect to a second axis of the carrier or a third axis of the carrier while the image capturing device is rotating around the first axis, causing the image capturing device to capture a plurality of successive images while the image capturing device is rotating around the first axis, and generating a panoramic image by stitching two or more of the plurality of images. The image capturing device is coupled to an unmanned aerial vehicle (UAV) via the carrier, and the carrier is coupled to the UAV via one or more damping members configured to reduce motions transmitted to the carrier by the UAV.

Abstract: A system includes an optical element configured to separate light into a first light beam and a second light beam, a first lens module configured to focus the first light beam, a second lens module configured to focus the second light beam, a first sensor configured to capture a first image from the first light beam focused by the first lens module onto the first sensor, a second sensor configured to capture a second image from the second light beam focused by the second lens module onto the second sensor, and one or more processors configured to generate a combined image based on the first image and the second image. The first image has a first field of view and the second image has a second field of view different from the first field of view.

Abstract: An image processing method includes capturing an initial image of a subject based on a preset initial exposure value, capturing a compensatory image of the subject based on a preset compensatory exposure value greater than the initial exposure value, calculating a synthesized pixel value at a pixel coordinate position based on a pixel value of an initial pixel at the pixel coordinate position in the initial image and a pixel value of a compensatory pixel at the pixel coordinate position in the compensatory image, and generating a captured image based upon the synthesized pixel value.

Abstract: Imaging systems having multiple optical modules are provided to achieve higher zoom ratio and better displaying effect. The FOVs or focal length ranges of the multiple optical modules may be designed to achieve a zoom ratio higher than either of the multiple optical modules and a Picture-in-Picture function. The gravity center of the imaging system may not be significantly varied during the zooming in and zooming out of the multiple optical modules.

Abstract: An imaging system includes an imaging device and a frame assembly. The imaging device includes a first housing containing an optical unit and a second housing separated from the first housing and containing a non-optical unit. The non-optical unit is configured to communicate with the optical unit. The non-optical unit includes a memory device configured to store images captured by the optical unit. The frame assembly supports the optical unit and does not support the non-optical unit. The non-optical unit does not rotate with the optical unit when the frame assembly rotates the optical unit about at least one rotational axis.

Abstract: A system includes an optical element configured to separate light into a first light beam and a second light beam, a first lens module configured to focus the first light beam, a second lens module configured to focus the second light beam, a first sensor having a first sensor size and configured to capture a first image from the first light beam focused by the first lens module onto the first sensor, a second sensor having a second sensor size different from the first sensor size and configured to capture a second image from the second light beam focused by the second lens module onto the second sensor, and one or more processors configured to modify the first image or the second image based on the first sensor size and the second sensor size to generate a modified image and generate a combined image based on the modified image.

Abstract: A method and an apparatus for adjusting installation flatness of a lens in real time are provided. The method comprises: acquiring an image captured by a camera in real time, where the image comprises at least two groups of testing charts regarding different positions; pre-processing the image to obtain each group of testing charts by separation; calculating and displaying, based on each group of testing charts, a real-time resolution value of a camera photosensitive surface to each group of testing charts in real time; and adjusting the installation angle of the optical axis of the camera lens relative to the camera photosensitive surface in real time based on the real-time resolution value of the camera photosensitive surface to each group of testing charts.

Abstract: A method for generating a high dynamic range image (HDRI) includes acquiring a first illuminance diagram, generating a second illuminance diagram from the first illuminance diagram by modifying a dynamic range of at least a portion of the first illuminance diagram, and generating the HDRI based on the second illumination diagram. The first illuminance diagram is obtained based on a camera response function and an illuminance logarithm obtained based on a plurality of images having different exposure conditions.

Abstract: A wireless transmission protocol for exchanging data between an unmanned aerial vehicle and a ground terminal is provided. The unmanned aerial vehicle is configured to transit image or video media data while mid-flight. The unmanned aerial vehicle and the ground terminal share a single communications channel using a time division multiple data access protocol. The unmanned aerial vehicle and the ground terminal use different communication protocols to send different types of data signals.

Abstract: A heating system for an automotive passenger cabin includes a blower fan generating an air flow; a first heater core downstream of the blower fan; a second heater core downstream of the first heater core; a coolant loop with a first branch and a second branch, wherein the first heater core is disposed in the first branch and the second heater core is disposed in the second branch; a change-over valve arrangement having a first setting establishing fluid communication between the first and second heater cores by connecting the first and second branches in two locations on opposite sides of the first and second heater cores. The change-over valve arrangement has a second setting separating the fluid communication between the first and second heater cores by disconnecting the first and second branches. The second branch or both the first and the second branch are connectable to a PCM heater.

Abstract: A water sampling method includes acquiring, by an unmanned aerial vehicle, a sampling depth at which a water sample is to be taken. The sampling depth is sent by a portable electronic device or is a preset default depth. The method further includes calculating a descending distance based on the sampling depth and a distance between the unmanned aerial vehicle and a water surface, controlling the water sampler to descend for the descending distance, sampling, by the water sampler, a water sample, and sending a sampling result to a ground station or the portable electronic device.

Abstract: Methods and systems for obtaining texture information and environmental information are provided. Texture information and/or environmental information may be obtained from various portions of captured images and may be utilized to improve operability of movable objects, such as unmanned aerial vehicles (UAVs).

Abstract: The present invention provides an apparatus for stabilizing an imaging device and methods of using the same for a wide variety of applications including photography, video, and filming. Also provided are unmanned vehicles including aerial vehicles that contain the apparatus disclosed herein.

Abstract: Systems and methods can support a data processing apparatus. The data processing apparatus can include a data processor that is associated with a data capturing device on a stationary object and/or a movable object. The data processor can receive data in a data flow from one or more data sources, wherein the data flow is configured based on a time sequence. Then, the data processor can receive a control signal, which is associated with a first timestamp, wherein the first timestamp indicates a first time. Furthermore, the data processor can determine a first data segment by applying the first timestamp on the data flow, wherein the first data segment is associated with a time period in the time sequence that includes the first time.

Abstract: A method for generating panoramic aerial images includes controlling a carrier to rotate an image capturing device by a predetermined angle of rotation around a first axis of the carrier. The image capturing device is coupled to an unmanned aerial vehicle (UAV) via the carrier and the carrier is configured to permit the image capturing device to rotate around at least the first axis and a second axis. The method further includes controlling the carrier to stabilize the image capturing device with respect to at least the second axis while the image capturing device is rotating around the first axis, by controlling one or more actuator members of the carrier. The method also includes controlling the image capturing device to capture a plurality of successive images while the image capturing device is rotating around the first axis and generating a panoramic image based on the captured plurality of images.

Abstract: The present invention provides a method and apparatus for generating a high dynamic range image (HDRI). After acquiring a first illuminance diagram, a base layer and detail layers are extracted from the first illuminance diagram, where the base layer contains low frequency information of the first illuminance diagram and the detail layers contain high frequency information of the first illuminance diagram. The dynamic range of the base layer is then compressed while dynamic ranges of the detail layers remain uncompressed. Further, a second illuminance diagram is generated from the first illuminance diagram by fusing the base layer with the compressed dynamic range and the detail layers, the second illuminance diagram is mapped onto a plurality of preset color channels; and the images on the plurality of preset color channels are fused into the HDRI. Therefore, the detail information in the original illuminance diagram can be preserved.