Abstract: A processing method for image tensor data, which can greatly reduce the number of free parameters in the model, limit the weight layer flexibly, and can be applied to any order of image tensor data. In this processing method for image tensor data, TTRBM model of Restricted Boltzmann machine with tensor train format is introduced. The input and output data of this method are both represented by tensors, and the weight of the middle layer is also represented by tensors, and the restricted weight has the structure of tensor train. The number of free parameters in the middle layer is controlled by adjusting the rank of tensor train decomposition. The rank of TT decomposition is adjusted, and different feature representations with the same size are expressed.

Abstract: Methods, apparatus and systems for wireless sleep monitoring are disclosed. In one embodiment, a described sleep monitoring system comprises: at least one sensor in a venue, wherein the at least one sensor comprises a wireless non-contact sensor having no physical contact with the user; a processor communicatively coupled to the at least one sensor; a memory communicatively coupled to the processor; and a set of instructions stored in the memory. The set of instructions, when executed by the processor, causes the processor to perform: obtaining, based on the at least one sensor, a plurality of time series of sensing features (TSSF) associated with a sleep motion of a user in the venue, and monitoring the sleep motion of the user jointly based on the plurality of TSSF.

Abstract: Methods, apparatus and systems for wireless sensing are described. In one embodiment, a described presentation system comprises: a presentation device with a user-interface; a processor communicatively coupled to the presentation device; a memory communicatively coupled to the processor; and a set of instructions stored in the memory. The set of instructions, when executed by the processor, causes the processor to perform: determining a plurality of time series of analytics (TSA) associated with a lifelog of a living object, determining a common time axis for the plurality of TSA, and generating a presentation that presents the plurality of TSA synchronously and jointly in a hybrid manner based on the common time axis. The presentation is presented on the user-interface of the presentation device.

Abstract: A method includes receiving, with a computing device, an image, identifying one or more salient features in the image, and generating a saliency map of the image including the one or more salient features. The method further includes sampling the image based on the saliency map such that the one or more salient features are sampled at a first density of sampling and at least one portion of the image other than the one or more salient features are sampled at a second density of sampling, where the first density of sampling is greater than the second density of sampling, and storing the sampled image in a non-transitory computer readable memory.

Abstract: A device and method for obtaining distance information from views is provided. The method generating epipolar images from a light field captured by a light field acquisition device; an edge detection step for detecting, in the epipolar images, edges of objects in the scene captured by the light field acquisition device; in each epipolar image, detecting valid epipolar lines formed by a set of edges; determining the slopes of the valid epipolar lines. The edge detection step may calculate a second spatial derivative for each pixel of the epipolar images and detect the zero-crossings of the second spatial derivatives, to detect object edges with subpixel precision. The method may be performed by low cost mobile devices to calculate real-time depth-maps from depth-camera recordings.

Abstract: Methods, apparatus and systems for wireless vital signs monitoring are described. In one embodiment, a described system comprises: a transmitter, a receiver, a processor. The transmitter transmits, using N1 transmit antennas, a wireless signal through a wireless multipath channel of a venue, while a first object in the venue is having a first repetitive motion. The receiver receives, using N2 receive antennas, the wireless signal through the wireless multipath channel, and extracts a plurality of time series of channel information (TSCI) of the wireless multipath channel from the wireless signal. N1 and N2 are positive integers. Each of the plurality of TSCI is associated with a transmit antenna of the transmitter and a receive antenna of the receiver. The processor computes a first information of the first repetitive motion based on the plurality of TSCI, and monitors the first repetitive motion of the first object based on the first information.

Abstract: A rugged, ergonomic integrated telecommunications handset includes an electronic controller that interoperates and controls the universal remote control (URC), which connects to multiple radios simultaneously. The controller downloads options which are implemented by the controller. The handset has an ability to vibrate in a silent mode, and has a memory capacity, as well as GPS capacity. Ergonomically, the handset has a pair of side arrays of protruding ribs, which enhance gripping, preventing the handset from falling out of the user's hands, even if the user has gloves on in inclement weather conditions in the field. While compatible with the latest radio system software defined dual net and dual channel radio equipment, the handset is also backward compatible with single radios or with two or more separate radios.

Abstract: Methods, apparatus and systems for outdoor target tracking are described. In one example, a described system comprises: a transmitter, a receiver, and a processor. The transmitter is configured for transmitting a first wireless signal through a wireless multipath channel. The receiver is configured for receiving a second wireless signal through the wireless multipath channel. One of the transmitter and the receiver is a located device at a known location. The other of the transmitter and the receiver is a moving device. The second wireless signal differs from the first wireless signal due to the wireless multipath channel which is impacted by a movement of the moving device. The processor is configured for: obtaining a plurality of time series of channel information of the wireless multipath channel based on the second wireless signal, computing a spatial-temporal information (STI), and tracking the moving device based on the STI.

Abstract: Methods, apparatus and systems for qualified wireless sensing are described. In one embodiment, a described method comprises: transmitting a wireless signal from a Type 1 device to a Type 2 device through a wireless multipath channel of a venue; obtaining a time series of channel information (TSCI) of the wireless multipath channel based on the wireless signal; performing a qualification test based on the TSCI for at least one to-be-qualified device, which is at least one of: the Type 1 device, a module of the Type 1 device, an integrated circuit (IC) of the Type 1 device, the Type 2 device, a module of the Type 2 device, or an IC of the Type 2 device; determining that each of the at least one to-be-qualified device is a qualified device based on a determination that a respective qualification criterion associated with the to-be-qualified device is satisfied, to obtain at least one qualified device; and performing a task based on the TSCI using the at least one qualified device.

Abstract: Unpowered switching module. A switching module can include a first input terminal, a second input terminal, and an output terminal. The output terminal can be configured to output a radio-frequency (RF) component of an input signal received on the first input terminal or the second input terminal in response to the input signal including a positive direct-current (DC) voltage.

Abstract: A system and method for controlling characteristics of collected image data are disclosed. The system and method include performing pre-processing of an image using GPUs, configuring an optic based on the pre-processing, the configuring being designed to account for features of the pre-processed image, acquiring an image using the configured optic, processing the acquired image using GPUs, and determining if the processed acquired image accounts for feature of the pre-processed image, and the determination is affirmative, outputting the image, wherein if the determination is negative repeating the configuring of the optic and re-acquiring the image.

Abstract: The disclosure relates to a method and an imaging device for generating a motion-compensated image of a target object. The disclosure further relates to a corresponding computer program and a computer-readable storage medium. In the method, a reference image is generated from projection images of a target object. Furthermore, a motion field which characterizes a motion of the target object shown is determined iteratively. In each case, after a predetermined number of iterative acts, the existing reference image is replaced by a provisional motion-compensated image, which is then used for the further iteration. The initial reference image is generated without using a synchronization or gating-signal that characterizes a motion of the target object.

Abstract: In an approach for detecting queuing information, a processor analyzes a video monitoring a queue area. A processor detects a queue barrier in the queue area using an instance segmentation technique based on the video. A processor identifies a queue in the queue area using a heuristic technique. A processor recognizes a number of people in the queue. A processor provides an estimation of a wait time for the queue.

Abstract: An activity recognition system may comprise a local device and a server. The local device may be configured to: obtain a video; determine whether at least one human is present in one or more frames of the video; in response to determining the at least one human present in the video, determine if the at least one human in each of the frames corresponds to the same person; in response to determining that the at least one human in each of the frames corresponds to the same person, determine if the person is a stranger; and in response to determining that the person is not a stranger, transmit at least a portion of the video to the server. The server may be configured to: predict an activity class associated with the person; and trigger an alarm based on the activity class.

Abstract: Methods, apparatus and systems for wireless vital monitoring are described. In one example, a described system comprises: a transmitter configured for transmitting a first wireless signal through a wireless channel of a venue; a receiver configured for receiving a second wireless signal through the wireless channel; and a processor. The second wireless signal comprises a reflection of the first wireless signal by at least one living being having at least one repetitive motion in the venue. The processor is configured for: obtaining a time series of channel information (TSCI) of the wireless channel based on the second wireless signal; generating, for each living being of the at least one living being, a vital signal representing all repetitive motions of the living being based on the TSCI; extracting, from the vital signal of each living being, a heartbeat signal; and monitoring, for each living being in the venue, a heart rate variability based on the heartbeat signal.

Abstract: The embodiments herein relate to a method performed by a first node (101) for enabling testing of at least a part (105, 108) of the first node (101) in a deployed network. The first node (101) determines that at least a part (105, 108) of the first node (101) should be tested, and determines a direction in which to transmit or receive a test signal (200) to or from a second node (103). The first node (101) transmits the test signal (200) OTA in the determined direction to the second node (103) if a transmitter of the first node (101) should be tested. The first node (101) receives the test signal (200) OTA in the determined direction from the second node (103) if a receiver of the first node (101) should be tested.

Abstract: An object detection method, a neural network training method, an apparatus, and an electronic device include: obtaining, through prediction, multiple fused feature graphs from images to be processed, through a deep convolution neural network for target region frame detection, obtaining multiple first feature graphs from a first subnet having at least one lower sampling layer, obtaining multiple second feature graphs from a second subnet having at least one upper sampling layer, and obtaining fused graph by fusing multiple first feature graphs and multiple second feature graphs respectively; and obtaining target region frame data according to the multiple fused feature graphs. Because the fused feature graphs better represent semantic features on high levels and detail features on low levels in images, target region frame data of big and small objects in images can be effectively extracted according to the fused feature graphs, thereby improving accuracy and robustness of object detection.

Abstract: Provided are an image processing apparatus, an image processing method, and an imaging apparatus. An image processing apparatus includes a demosaic processing unit configured to apply demosaic processing to a mosaic image having a first number of colors to generate a multispectral image having a second number of colors equal to or more than three but less than the first number of colors.

Abstract: A medical data processing method, performed by a computer (2), for determining error analysis data describing the registration accuracy of a first elastic registration between first and second image data (A, B) describing images of an anatomical structure of a patient, comprising the steps of: —acquiring the first image data (A) describing a first image of the anatomical structure, —acquiring the second image data (B) describing a second image of the anatomical structure, —determining first registration data describing a first elastic registration of the first image data (A) to the second image data (B) by mapping the first image data (A) to the second image data (B) using a registration algorithm, —determining second registration data describing a second elastic registration of the second image data (B) to the first image data (A) by mapping the second image data (B) to the first image data (A) using the registration algorithm, —determining error analysis data describing the registration accuracy of the firs

Abstract: A system for processing images captured by a movable object includes one or more processors individually or collectively configured to process a first image set captured by a first imaging component to obtain texture information in response to a second image set captured by a second imaging component having a quality below a predetermined threshold, and obtain environmental information for the movable object based on the texture information. The first imaging component has a first field of view and the second imaging component has a second field of view narrower than the first field of view.