SYSTEMS, METHODS, AND APPARATUS FOR PASSIVE COOLING OF UAVS

    公开(公告)号:US20210129995A1

    公开(公告)日:2021-05-06

    申请号:US17247546

    申请日:2020-12-16

    Abstract: An innovative passive cooling solution with sealed UAV enclosure system allows heat from a semiconductor chip to be dissipated to the ambient environment through evaporation/condensation phase-change cooling and air cooling a heat sink such as a fin without any additional power consumption to operate cooling solution. One example of such a solution may include a pipe with a fin and a fluid. The pipe may include a wick structure along an inner surface of the pipe configured to allow the fluid to travel within the wick structure and to allow a vapor form of the fluid to exit the wick structure towards a center of the pipe.

    SYNCHRONIZATION MECHANISM FOR IMAGE CAPTURE AND PROCESSING SYSTEMS

    公开(公告)号:US20210337117A1

    公开(公告)日:2021-10-28

    申请号:US17109009

    申请日:2020-12-01

    Abstract: Techniques and systems are provided for processing image data. For example, an image signal processor can obtain (e.g., from a host processor) a first setting change indicator value indicating a change in parameter settings of the image signal processor. The image signal processor can obtain an image frame from an image sensor, and can determine a second setting change indicator value from the image frame. The second setting change indicator value can be provided to the image sensor from the host processor. The second setting change indicator value indicates a change in parameter settings of the image sensor. The image signal processor can compare the first setting change indicator value to the second setting change indicator value, and can determine whether to process the image frame or to drop the image frame based on comparing the first setting change indicator value to the second setting change indicator value.

    OBJECT CLASSIFICATION USING MACHINE LEARNING AND OBJECT TRACKING

    公开(公告)号:US20190034734A1

    公开(公告)日:2019-01-31

    申请号:US16037912

    申请日:2018-07-17

    Abstract: Techniques and systems are provided for classifying objects in one or more video frames. For example, one or more bounding regions are determined for a current video frame of a scene. The one or bounding regions are determined based on object tracking performed for one or more blobs detected for the current video frame. The one or more bounding regions are associated with the one or more blobs. A blob includes pixels of at least a portion of one or more objects in the current video frame. One or more regions of interest are determined in the current video frame of the scene. The one or more regions of interest are determined using the one or more bounding regions determined for the current video frame. One or more objects within the one or more regions of interest are classified using a trained network applied to the one or more regions of interest.

Patent Agency Ranking