Abstract: A method includes receiving, from an image sensor, an image, identifying, by a first neural network, a plurality of locations-of-interest within the image, and generating, by the first neural network, a first classification label for each location-of-interest of the plurality of locations-of-interest. The method also includes extracting, from the image, a plurality of image chips derived from the plurality of locations-of-interest and generating, by a second neural network, a second classification label for each image chip of the plurality of image chips. The method further includes determining an identification of a set of targets within the image using the plurality of locations-of-interest, the first classification label for each location-of-interest of the plurality of locations-of-interest, the plurality of image chips, and the second classification label for each image chip of the plurality of image chips, and transmitting the identification of the set of targets within the image.

Abstract: A method and device for performing a perception task are disclosed. The method and device incorporate a dense regression model. The dense regression model advantageously incorporates a distortion-free convolution technique that is designed to accommodate and appropriately handle the varying levels of distortion in omnidirectional images across different regions. In addition to distortion-free convolution, the dense regression model further utilizes a transformer that incorporates an spherical self-attention that use distortion-free image embedding to compute an appearance attention and uses spherical distance to compute a positional attention.

Abstract: A method of image processing includes: determining a first feature, wherein the first feature has a dimensionality D1; determining a second feature, wherein the second feature has a dimensionality D2 and is based on an output of a feature extraction network; generating a third feature by processing the first feature, the third feature having a dimensionality D3; generating a guidance by processing the second feature, the guidance having the dimensionality D3; generating a filter output by applying a deep guided filter (DGF) to the third feature using the guidance; generating a map based on the filter output; and outputting a processed image based on the map.

Abstract: The present disclosure relates to systems, methods, and non-transitory computer-readable media that generate joint-based segmentation masks for digital objects portrayed in digital videos. In particular, in one or more embodiments, the disclosed systems utilize a video masking model having a pose tracking neural network and a segmentation neural network to generate the joint-based segmentation masks. To illustrate, in some embodiments, the disclosed systems utilize the pose tracking neural network to identify a set of joints of the digital object across the frames of the digital video. The disclosed systems further utilize the segmentation neural network to generate joint-based segmentation masks for the video frames that portray the object using the identified joints. In some cases, the segmentation neural network includes a multi-layer perceptron mixer layer for mixing visual features propagated via convolutional layers.

Abstract: This disclosure provides systems, methods, and devices for processing and aligning sensor data features for navigation. In a first aspect, a method is provided that includes determining, based on received sensor data, a first set of features for an area surrounding the vehicle. A second set of features for the area surrounding the vehicle may be determined based on an occupancy map for the area surrounding the vehicle. A third set of features may be determined that align the first set of features with the second set of features. The third set of features may align each of at least a subset of the second set of features with at least one corresponding feature from the first set of features. Other aspects and features are also claimed and described.

Abstract: Various disclosed embodiments are directed to resizing, via down-sampling and up-sampling, a high-resolution input image in order to meet machine learning model low-resolution processing requirements, while also producing a high-resolution output image for image inpainting via a machine learning model. Some embodiments use a refinement model to refine the low-resolution inpainting result from the machine learning model such that there will be clear content with high resolution both inside and outside of the mask region in the output. Some embodiments employ new model architecture for the machine learning model that produces the inpainting result—an advanced Cascaded Modulated Generative Adversarial Network (CM-GAN) that includes Fast Fourier Convolution (FCC) layers at the skip connections between the encoder and decoder.

Abstract: A computer-implemented method can include acquiring first training images using a first image acquisition technique, where each first training image depicts a plant-related motive; and acquiring second training images using a second image acquisition technique, where each second training image depicts the motive depicted in a respective one of the first training images. The method can include automatically assigning at least one label to each of the acquired second training images. The method can include spatially aligning the first and second training images which are depicting the same one of the motives into an aligned training image pair. The method can include training a machine-learning model as a function of the aligned training image pairs and the labels, wherein during the training the machine-learning model learns to automatically assign one or more labels to any test image acquired with the first image acquisition technique which depicts a plant-related motive.

Abstract: Provided in the present application are a target area determination method and a medical imaging system, specifically a target area determination method and device, a medical imaging system, and a non-transitory computer-readable storage medium. The target area determination method includes: pre-processing an original image to acquire a pre-processed medical image, acquiring a target point in the medical image, and acquiring a plurality of sectional images of the medical image according to the target point, and acquiring, on the basis of a first model, a target area corresponding to the target point in the plurality of sectional images.

Abstract: Embodiments of the present disclosure disclose an image generation method and device. A specific implementation manner of the method includes: acquiring an image of a target moving object, wherein limb parts of the target moving object are presented in the image; inputting the image to a pre-trained detection model to obtain an output result for indicating position distribution of all limb parts, presented in the image, in a preset limb part set; generating thermodynamic images corresponding to all the limb parts based on the output result; and superimposing the generated thermodynamic images to regional positions, corresponding to all the limb parts, in the image to generate an image superimposed with the thermodynamic images.

Abstract: An image enhancement method and an electronic device are disclosed. The image enhancement method includes the following steps. An original image is divided into multiple image blocks. A statistical data of each of the image blocks is calculated, and at least one index is obtained according to the statistical data of the each of the image blocks. A final tone mapping curve of the each of the image blocks is obtained based on multiple predefined tone mapping curves according to the at least one index of the each of the image blocks. Afterwards, the original image is adjusted according to the final tone mapping curve of the each of the image blocks to obtain an enhanced image.

Abstract: An image processing apparatus including a first generation unit configured to generate a plurality of images having an M-bit depth per pixel by inputting an input image having a bit depth of N bits, and clipping M-bit segments from mutually different positions within the N bits; a second generation unit including a neural network for an M-bit-depth image and configured to generate, by inputting the plurality of images generated by the first generation unit into the neural network, a plurality of output images corresponding to each of the plurality of images being input; and a third generation unit configured to generate an image having the N-bit depth from the plurality of output images generated by the second generation unit.

Abstract: A computing system for self-training of a magnetic resonance imaging (MRI) tissue property artificial neural network (ANN) includes a processor and an ANN training application including instructions that, when executed by the one or more processors, are configured to cause the processor to generate tissue property maps; generate MRI fingerprint images; generate reconstructed MRI k-space data; and compare the reconstructed MRI k-space data to acquired MRI k-space data. A computer-implemented method includes generating tissue property maps; generating MRI fingerprint images; generating reconstructed MRI k-space data; and comparing the reconstructed MRI k-space data to acquired MRI k-space data. A non-transitory computer-readable storage medium storing executable instructions that, when executed by a processor, cause a computer to generate tissue property maps; generate MRI fingerprint images; generate reconstructed MRI k-space data; and compare the reconstructed MRI k-space data to acquired MRI k-space data.

Abstract: In one embodiment, a method includes accessing a batch B of a plurality of images, wherein each image in the batch is part of a training set of images used to train a vision transformer comprising a plurality of attention heads. The method further includes determining, for each attention head A, a similarity between (1) the output of the attention head evaluated using each image in the batch and the (2) output of each attention head evaluated using each image in the batch. The method further includes determining, based on the determined similarities, an importance score for each attention head; and pruning, based on the importance scores, one or more attention heads from the vision transformer.

Abstract: A detection pattern unit includes an inner pattern group, and an outer pattern group that includes two sets of positioning detection patterns, each set including two lines of patterns. For each set, a pitch dimension between adjacent two patterns in one line of the set is the same as a pitch dimension between adjacent two patterns in the other lines of the set. The outer pattern group further includes, for each of two different directions, two connecting lines each extending along the direction and each interconnecting two of the positioning detection patterns respectively from the two lines of a corresponding one of the sets of positioning detection patterns.

Abstract: A method performed by a mobile device for handling identification of equipment. The mobile device records an image, in a recording direction at a first location, of the equipment. Upon recording the image, the mobile device further obtains one or more radiation indications for determining a direction of radiation from the equipment; and provides the obtained one or more radiation indications associated with the recorded image, to an internal identifying process at the mobile device and/or a network node for identifying the equipment.

Abstract: An imaging system is presented for imaging a region of interest. The system includes an imaging arrangement having diffraction limited resolution. The imaging arrangement includes a spatial light encoder scattering medium) which applies spatial encoding patterns to coherent light and provides encoded illuminations of the region of interest located behind the encoder to create encoded diffraction limited images on a detector array. A position controller is provided which sequentially provides relative displacements between the coherent light path and the region of interest, resulting in a plurality of M laterally displaced encoded illuminations in a region of interest plane, displaced by ?x (and/or ?x) between them such that they are characterized by substantially constant appearances of the encoded structure of the coherent light field. This enables super-resolution reconstruction of an image of the region of interest from corresponding M image data pieces without prior knowledge about the encoding patterns.

Abstract: A speed estimation system includes: a detection module configured to: detect an object on a surface in an image captured using a camera; and generate a bounding box around the object; a Jacobian module configured to generate a Jacobian for the object based on the bounding box; and a speed module configured to determine a speed that the object is traveling on the surface based on the Jacobian.

Abstract: Systems and methods of performing video analysis related to a video of an electronic terminal. In one exemplary embodiment, a method is performed by an electronic device that includes processing circuitry. The method may include causing a display to play a video that shows an electronic terminal, automatically detecting a captured event related to the electronic terminal in the video, capturing first time stamp information corresponding to a time point in the video that the captured event occurs in the video, and predicting a future event associated with the captured event related to the electronic terminal in the video. The method may also include capturing and outputting second time stamp information corresponding to a time point in the video that the predicted future event is detected to have occurred in the video.

Abstract: An automated method for segmentation includes steps of receiving at a computing device an input image representing at least one surface and performing by the computing device image segmentation on the input image based on a graph surface segmentation model with deep learning. The deep learning may be used to parameterize the graph surface segmentation model.

Abstract: An imaging device includes a setting unit configured to set a target brightness level of a high-brightness region in an imaging scene; an exposure control unit configured to perform photometry to control exposure; and a gradation correction unit configured to perform predetermined gradation correction on an image obtained by imaging, wherein a mode for controlling the exposure includes a first photometry mode, in which photometry is performed using the high-brightness region as a photometry region and exposure is controlled on a basis of a target brightness level set by the setting unit, and a second photometry mode different from the first photometry mode, and the gradation correction unit suppresses the predetermined gradation correction more in a case in which the image is obtained by imaging using the first photometry mode than in a case in which the image is obtained by imaging using the second photometry mode.