Abstract: A multi-level transferable region-based domain adaptive object detection apparatus includes: an image-level feature part that extracts an image-level feature by providing unlabeled target data to a plurality of convolutional layers; an RPN-level feature part that determines region candidates by providing the image-level feature to a region proposal network (RPN) and performing RPN-level domain adaptation and transferable region filtering; and an instance-level feature part that extracts a region of interest (RoI) pooling feature by conducting dynamic instance sampling on the region candidates.

Abstract: A method and system for autonomous parking are disclosed. The system employs Homography guided motion segmentation (HGMS) to determine the availability of a parking slot. A free parking slot is determined based on an occupancy status check and identified structures of parking lines. For example, motion analysis is performed on successive images captured by a camera unit to determine the occupancy status of a parking slot. Information of the free parking slot, for example, the dimensions and orientation, may be determined from identifying the structure of parking lines. This information is used by the system to guide a vehicle from its current location to the detected free parking slot.

Abstract: Techniques measuring post contrast phase include collecting 3D medical imagery of a subject after injection with a contrast agent. A first set of slices is obtained in which each includes a first anatomical feature selected from a portal vein, aorta, inferior vena cava, liver, spleen or renal cortex. A second set of slices is obtained in which each includes a different second anatomical feature. A first image region is obtained from the first set and a different second image region from the second set. A trained convolutional neural network is configured to input the first image region to a first plurality of convolutional hidden layers and the second image region to a second plurality of convolutional hidden layers and output from both to a fully connected hidden layer that outputs a post contrast phase. Output data is presented based on the post contrast phase.

Abstract: A multimodal perception system for an autonomous vehicle includes a first sensor that is one of a video, RADAR, LIDAR, or ultrasound sensor, and a controller. The controller may be configured to, receive a first signal from a first sensor, a second signal from a second sensor, and a third signal from a third sensor, extract a first feature vector from the first signal, extract a second feature vector from the second signal, extract a third feature vector from the third signal, determine an odd-one-out vector from the first, second, and third feature vectors via an odd-one-out network of a machine learning network, based on inconsistent modality prediction, fuse the first, second, and third feature vectors and odd-one-out vector into a fused feature vector, output the fused feature vector, and control the autonomous vehicle based on the fused feature vector.

Abstract: A method of recognizing a specific image includes detecting image features from the specific image and storing in a memory each of detected relevant image features, detecting relevant image features from an input image and selecting from the memory a portion corresponding to each of the detected relevant image features, generating a restoration image using portions selected in the selecting, and determining whether the generated restoration image matches with the input image by a matching process and recognizing that, when it is determined that the restoration image matches with the input image, the input image is the specific image.

Abstract: Disclosed herein are arrangements that facilitate the transfer of knowledge from models for a source data-processing domain to models for a target data-processing domain. A convolutional neural network space for a source domain is factored into a first classification space and a first reconstruction space. The first classification space stores class information and the first reconstruction space stores domain-specific information. A convolutional neural network space for a target domain is factored into a second classification space and a second reconstruction space. The second classification space stores class information and the second reconstruction space stores domain-specific information. Distribution of the first classification space and the second classification space is aligned.

Abstract: A system for determining relevance of a light source to an automobile includes at least one camera adapted to capture images of light sources in proximity to the automobile, a controller in communication with the at least one camera and adapted to receive captured images from the at least one camera, the controller further adapted to estimate an orientation of at least one light source relative to the automobile, classify the at least one light source as one of relevant and irrelevant, and, when the at least one light source is classified as relevant, send information about the at least one light source to a planning module for the automobile.

Abstract: A determination method of non-destructively and easily determining a state of an aggregate of a plurality of cells formed by three-dimensional culture is provided. A determination method according to the disclosed technology includes generating a phase difference image of an aggregate of a plurality of cells from a hologram obtained by imaging the aggregate, deriving a first index value that indicates a randomness of an array of a phase difference amount in a plurality of pixels constituting the phase difference image, and determining a state of the cells constituting the aggregate on the basis of the first index value.

Abstract: Examples described herein include systems and methods, including wireless devices and systems with neuron calculators that may perform one or more functionalities of a wireless transceiver. The neuron calculator calculates output signals that may be implemented, for example, using accumulation units that sum the multiplicative processing results of ordered sets from ordered neurons with connection weights for each connection between an ordered neuron and outputs of the neuron calculator. The ordered sets may be a combination of some input signals, with the number of signals determined by an order of the neuron. Accordingly, a kth-order neuron may include an ordered set comprising product values of k input signals, where the input signals are selected from a set of k-combinations with repetition. As an example in a wireless transceiver, the neuron calculator may perform channel estimation as a channel estimation processing component of the receiver portion of a wireless transceiver.

Abstract: Various embodiments include a fire or smoke alarm comprising: a detection arrangement arranged within an alarm housing; and an alarm-housing cover having, on an inner side, a plurality of housing ribs pointing radially in the direction of an alarm dome. The detection arrangement comprises a level divider with an opening. A maximum possible spacing between two points on a peripheral line of the opening or on a common peripheral line of a plurality of openings is larger than a diameter of the alarm dome. The peripheral line of the opening or the common peripheral line of a plurality of openings in the level divider extends beyond the alarm dome of the alarm-housing cover on all sides.

Abstract: Disclosed is a convolution operator system comprising a Convolution Neural Network (CNN) reconfigurable engine including a plurality of Mini Parallel Rolling Engines (MPREs) for performing a convolution operation concurrently on an image. An input router receives image data. A controller allocates image data to computing blocks through a set of data flow control blocks. Each computing block produces a convolution output corresponding to each row of the image. The controller allocates a plurality of group having one or more computing blocks to generate a set of convolution output. Further, a pipeline adder aggregates the set of convolution output to produce an aggregated convolution output. An output router transmits either the convolution output or the aggregated convolution output for performing subsequent convolution operation to generate a convolution result for the image data.

Abstract: Fluorescence microscopy method comprising: illuminating a scattering sample with a coherent excitation light beam having a wavefront with an initial configuration for exciting fluorescent emitters in the scattering sample; acquiring an initial image; selecting target pixels in an area of the initial image; optimising the initial configuration of the wavefront for each target pixel for decreasing the speckle grain size and obtaining a final image; subtracting the initial image from the final image for each target pixel, obtaining an image; fitting the image with a Gaussian function with free center coordinates for each target pixel; generating an image containing a Gaussian distribution centered at the coordinates and intensity, and with a waist equal to an average size S of speckle grain of the scattering sample, for each target pixel; and generating a final image of the sample by summing the images of the target pixels.

Abstract: Systems, methods, apparatuses, and computer program products for recognizing human emotion in images or video. A method for recognizing perceived human emotion may include receiving a raw input. The raw input may be processed to generate input data corresponding to at least one context. Features from the raw input data may be extracted to obtain a plurality of feature vectors and inputs. The plurality of feature vectors and the inputs may be transmitted to a respective neural network. At least some of the plurality of feature vectors may be fused to obtain a feature encoding. Additional feature encodings may be computed from the plurality of feature vectors via the respective neural network. A multi-label emotion classification of a primary agent may be performed in the raw input based on the feature encoding and the additional feature encodings.

Abstract: Front end systems and related devices, integrated circuits, modules, and methods are disclosed. One such packaged module includes a multi-mode power amplifier circuit in an interior of a radio frequency shielding structure and an antenna external to the radio frequency shielding structure. The multi-mode power amplifier circuit includes a stacked output stage including a transistor stack of two or more transistors. The multi-mode power amplifier circuit also includes a bias circuit configured to control a bias of at least one transistor of the transistor stack based on a mode of the multi-mode power amplifier circuit. The radio frequency shielding structure can extend above a package substrate. The antenna can be on the package substrate. Other embodiments of front end systems are disclosed, along with related devices, integrated circuits, modules, methods, and components thereof.

Abstract: Systems and methods herein describe accessing an image, generating a resized image, generating an image feature vector by applying an image classification neural network to the resized image, generating analysis of the image by processing the image feature vector using a machine-learning classifier trained to analyze the image feature vector, and based on the analysis, determining an event that is attributed to the image.

Abstract: Systems, devices and methods provide, implement, and use vision-based methods of sequence inference for a device affixed to a vehicle.

Abstract: This invention classifies an action that appears in a video clip by receiving a video clip for analysis, applying a convolutional neural network mechanism (CNN) to the frames in the clip to generate a 4D embedding tensor for each frame in the clip, applying a multi-resolution convolutional neural network mechanism (CNN) to each of the frames in the clip to generate a sequence of reduced resolution blocks, computing a kinematic attention weight that estimates the amount of motion in the block, applying the attention weights to the embedding tensors for each frame in a clip, to generate a weighted embedding tensor, or context, that represents all the frames in the clip, at the resolution, combining the contexts across all resolutions to generate a multi-resolution context, performing a 3D pooling to obtain a 1D feature vector and classifying a primary action of the video clip based on the feature vector.

Abstract: An image sensor is positioned such that a field-of-view of the image sensor encompasses at least a portion of a rack storing items. The image sensor generates angled-view images of the items stored on the rack. A tracking subsystem determines that a person is within a threshold distance of the rack and receives image frames of the angled-view images. A pixel position of a wrist of the person is determined in at least a subset of the received image frames, thereby determining a set of pixel positions of the wrist. An aggregated wrist position is determined based on the set of pixel positions. If the aggregated wrist position is determined to correspond to a position on a shelf of the rack, a trigger signal is provided indicating a shelf-interaction event has occurred.

Abstract: Embodiments of the disclosure provide a disparity map acquisition method and apparatus, a device, a control system and a storage medium. The method includes: respectively performing feature extraction on left-view images and right-view images of a captured object layer by layer through M cascaded feature extraction layers, to obtain a left-view feature map set and a right-view feature map set of each layer, M being a positive integer greater than or equal to 2; constructing an initial disparity map based on the left-view feature map set and the right-view feature map set extracted by an Mth feature extraction layer; and iteratively refining, starting from an (M?1)th layer, the disparity map through the left-view feature map set and the right-view feature map set extracted by each feature extraction layer in sequence until a final disparity map is obtained based on an iteratively refined disparity map of a first layer.

Abstract: This application discloses a method and apparatus for object detection in an image, a vehicle, and a robot. The method for object detection in an image is performed by a computing device. The method includes determining an image feature of an image; determining a correlation of pixels in the image based on the image feature; updating the image feature of the image based on the correlation to obtain an updated image feature; and determining an object detection result in the image according to the updated image feature.