Abstract: A monitor control unit that is configured to receive, from the electronic pool device, the sensor data, compare the sensor data to a threshold, based on comparing the sensor data to a threshold, determine that the sensor data exceeds the threshold, based on determining that the sensor data exceeds the threshold, provide an instruction to initiate the capture of image data by the camera of the electronic pool device, receive, from the camera of the electronic pool device, the image data, analyze the image data, based on analyzing the image data, identify a monitoring system action to perform, and perform the monitoring system action.

Abstract: An image capturing device that detects a change in lane width for a vehicle without using information on an adjacent lane is mounted in the vehicle and includes a first camera which captures a first image and a control device which recognizes, in the first image, first and second compartment line L1 and L2 that regulate lanes. The control device determines the presence or absence of a change in lane width on the basis of relationships among the widths of the first compartment line L1 at two points PV1, PV2 at which the distances from a vehicle on the first image are different, the widths of the second compartment line L2 at the two points PV1, PV2 on the first image, and the distances between the first compartment line L1 and the second compartment line L2 at the two points PV1, PV2 on the first image.

Abstract: A method, computer program, and computer system is provided for coding video data. Video data is received and entropy-parsed into one or more components. The one or more entropy-parsed components are de-quantized. A joint component secondary transformation (JCST) is performed on the one or more components. The video data is decoded based on one or more residual components corresponding to the joint component secondary transformed components.

Abstract: A synthetic aperture optics (SAO) imaging method minimizes the number of selective excitation patterns used to illuminate the imaging target, based on the objects' physical characteristics corresponding to spatial frequency content from the illuminated target and/or one or more parameters of the optical imaging system used for SAO. With the minimized number of selective excitation patterns, the time required to perform SAO is reduced dramatically, thereby allowing SAO to be used with DNA sequencing applications that require massive parallelization for cost reduction and high throughput. In addition, an SAO apparatus optimized to perform the SAO method is provided. The SAO apparatus includes a plurality of interference pattern generation modules that can be arranged in a half-ring shape.

Abstract: A method for determining relative motion between a time-of-flight camera and an object in a scene sensed by the time-of-flight camera is provided. The method includes receiving at least two sets of raw images of the scene from the time-of-flight camera, each set including at least one raw image. The raw images are based on correlations of a modulated reference signal and measurement signals of the time-of-flight camera. The measurement signals are based on a modulated light signal emitted by the object. The method includes determining, for each set of raw images, a value indicating a respective phase difference between the modulated light and reference signals based on the respective set of raw images, and determining information about relative motion between the time-of-flight camera and object based on the values indicating the phase differences. The method includes outputting the information about relative motion between the time-of-flight camera and the object.

Abstract: A method for dynamically calibrating a vehicular trailer angle detection system includes providing at least a rear camera at a rear portion of the vehicle. A trailer is hitched at the vehicle and the vehicle is driven forward while towing the trailer. The control determines an expected location of a portion of the trailer based on provided vehicle-trailer parameters as the vehicle is driven forward and towing the trailer. An actual location of the portion of the trailer is determined via processing at the control of captured image data as the equipped vehicle is driven forward and towing the trailer. The vehicular trailer angle detection system is calibrated responsive to determination, via processing at the control of captured image data as the equipped vehicle is driven forward and towing the trailer, that the determined actual location of the portion of the trailer is not at the determined expected location.

Abstract: A system for detecting a classifying objects in a vehicle can comprise one or more sensors for detecting the presence of an object, other than a passenger, on the vehicle. The system can classify the object as, for example, a personal object or trash. The system can provide a series of escalating reminders for the passenger to take the object with them when they exit the vehicle. When a personal object is left in the vehicle after the passenger has exited the vehicle, the system can communicate with a computing device of a central control or the passenger using additional communication channels such as, for example, e-mail, text, or the Internet. When trash is left in the vehicle, the vehicle can automatically contact, or return to, a maintenance facility for servicing. This can prevent the use of unclean vehicles for new passengers, among other things.

Abstract: An IR illuminator for providing infrared radiation for a digital camera having a camera lens with a camera field of view, including equidistant mounting substrates arranged adjacent to the digital camera, IR LEDs mounted to each of the mounting substrates, and a cover lens positioned to cover the IR LEDs. The shape of the free form cover lens is such that an emission pattern of radiation is emitted without entering into the camera lens and the emission pattern of IR radiation has an asymmetric field of view. Two IR illuminators adjacent to the camera are tilted at an angle from the camera optical direction. The cover lens may be a Fresnel lens, or include a diffractive layer or a collimator to shift radiation emitted from the LED to an asymmetric distribution.

Abstract: Disclosed herein is a method for adaptive bidirectional optical flow estimation for inter prediction compensation during video encoding. The method aims to reduce complexity and/or cost of bidirectional optical flow (BIO) at a pixel level or a subblock level.

Abstract: Disclosed is a compression method for a deep neural network. The deep neural network comprises a plurality of layers. The method includes the following steps for each of at least one layer of the plurality of layers other than an input layer: reading parameters of that layer from a parameter storage space; reading a first feature map stored by an immediate previous layer from a feature map storage space; generating a second feature map on the basis of the read parameters and the first feature map; compressing the second feature map so as to obtain a third feature map; and storing the third feature map into the feature map storage space. Further, a chip based on the compression method and a medium are also provided.

Abstract: Provided is an electronic apparatus and method for providing an image of surroundings of a vehicle. The electronic apparatus for providing an image of surroundings of the vehicle includes a first image sensor creating a first image by capturing surroundings of the vehicle; a second image sensor creating a second image by capturing surroundings of the vehicle; and a processor configured to obtain feature information of each of the first image and the second image and use a portion of the first image and a portion of the second image to create a composite image that represents the surroundings of the vehicle, based on the obtained feature information.

Abstract: A deblocking method for deblocking a boundary between a first block of samples, block P, and a second block of samples, block Q. The method includes determining whether at least one of the P block or the Q block is a combined intra-inter prediction block; and, as a result of determining that at least one of the P block or the Q block is a combined intra-inter prediction block, deblocking the boundary between the P block and the Q block.

Abstract: Techniques pertaining to the transmission of digital data via a conventional transmission medium (e.g., a coaxial cable for TV) specifically for analog composite video signals are disclosed. To retrofit in an existing system not designed for transmitting digital signals or data, the techniques are provided to convert the data into an analog signal that is transmitted over a coaxial cable, where the analog signal, when received, is decomposed to recover the data. According to one aspect of the present invention, videos in high quality (e.g. high definition or HD format) from HD cameras are used in the conventional surveillance system, where the transmission medium for the analogy videos is already installed.

Abstract: A vehicle remote support system includes a communication system that operates over a plurality of parallel wireless network connections to provide low-latency video from vehicle to a remote support server that provides remote support to the vehicle dependent on real-time video. The vehicle includes a source that encodes multiple versions of the original video segments (e.g., one per wireless network connection) and transmits the multiple versions of the segments to a sink at the remote support server over the respective wireless connections. This redundant multi-path communication system rationally allocates network resources to the managed video streams and balances bandwidth against latency in order to avoid network congestion and safety issues associated with single-path transmissions. In other embodiments, a similar communication system that transmits video or other real-time messages between a source and a sink may be utilized in cloud robotics applications.

Abstract: An image capture device includes a plurality of stacked ceramic circuit boards, an image sensor, signal conditioning electronics, and a connector. Each ceramic circuit board is parallel and directly coupled to at least one other circuit board. The image sensor is mounted to a first ceramic circuit board. The signal conditioning electronics are mounted to one or more of the stacked ceramic circuit boards and are coupled to receive electrical signals generated by the image sensor. The image capture device is enclosed by a shaft and the stacked ceramic circuit boards are stacked along a length of the shaft. The connector is mounted to a second ceramic circuit board that is on an opposite side of the plurality of stacked ceramic circuit boards from the first ceramic circuit board. The connector is mounted to a side of the second ceramic circuit board facing away from the first ceramic circuit board.

Abstract: Disclosed herein are a video decoding method and apparatus and a video encoding method and apparatus. Encoding and decoding of a target block are performed using intra-prediction. The intra-prediction is intra-prediction that uses bidirectional intra-prediction and a remaining mode. In bidirectional intra-prediction, a prediction value for a target pixel in the target block is determined based on reference pixels in two directions of bidirectional intra-prediction. In intra-prediction using a remaining mode, the remaining mode indicates remaining intra-prediction modes other than MPMs present in an MPM list.

Abstract: The present application provides methods, systems, devices and computer-readable mediums for deblocking filter. A method of the present application comprises: determining a filtering boundary, and then determining a filter pixel group based on the filtering boundary; determining a filter strength of the filter pixel group, comprising: parsing separately a pixel value difference states of pixel points on both sides of the filtering boundary in the filter pixel group to obtain two one-sided flatness FL and FR; calculating a comprehensive flatness FS of the filter pixel group, wherein FS=FL+FR; calculating the filter strength according to FS; filtering calculation of pixel points included in the filter pixel group according to the filter strength.

Abstract: In some embodiments, a method determines a first set of reference pixels for a current block to be coded. The current block is split into a plurality of sub-partitions. The method processes a first sub-partition in the plurality of sub-partitions using the first set of reference pixels and a second sub-partition in the plurality of sub-partitions using the first set of reference pixels in parallel. Then the method processes a third sub-partition in the plurality of sub-partitions based on a second set of reference pixels determined from the processing of the first sub-partition and processing a fourth sub-partition in the plurality of sub-partitions based on a third set of reference pixels determined from the processing of the second sub-partition.

Abstract: Systems and methods are described for managing overhead bin space in an aircraft or other vehicle. An available space or the used space with an overhead bin can be measured using a set of sensors. Using information from the set of sensors, a dongle can determine a shape and volume of the used or unused space within the overhead bin. With this information, the available space can then be reported including the number of roller bags that would fit in the overhead bin or whether there are objects that are not roller bags within the overhead bin.

Abstract: A method includes receiving a current block to be coded and splitting the current block into a plurality of sub-partitions. A first set of reference pixels is determined. The method processes a first sub-partition in the plurality of sub-partitions using the first set of reference pixels and a second sub-partition in the plurality of sub-partitions using the first set of reference pixels in parallel. Then, the method processes a third sub-partition in the plurality of sub-partitions based on a second set of reference pixels determined from the processing of the first sub-partition and processing a fourth sub-partition in the plurality of sub-partitions based on a third set of reference pixels determined from the processing of the second sub-partition.