Abstract: In various examples, sensor data used to train an MLM and/or used by the MLM during deployment, may be captured by sensors having different perspectives (e.g., fields of view). The sensor data may be transformed—to generate transformed sensor data—such as by altering or removing lens distortions, shifting, and/or rotating images corresponding to the sensor data to a field of view of a different physical or virtual sensor. As such, the MLM may be trained and/or deployed using sensor data captured from a same or similar field of view. As a result, the MLM may be trained and/or deployed—across any number of different vehicles with cameras and/or other sensors having different perspectives—using sensor data that is of the same perspective as the reference or ideal sensor.

Abstract: An information processing apparatus includes a processor configured to: extract attribute values for plural attributes from an optical character recognition (OCR) result for an image in accordance with an extraction rule determined in advance, and generate an extraction result in which the extracted attribute values and the respective attributes are correlated with each other; and perform control so as to associate, in accordance with an association rule for associating an attribute value for a sub attribute with a different attribute, the attribute value for the sub attribute with the different attribute included in the extraction result, the sub attribute being an attribute for which an attribute value is extracted from the image and which supplements a content for the different attribute.

Abstract: A method and a graphic user interface for displaying digital media objects and dynamically calculating their quality indicators. A first digital media object is displayed on a first computing device. A first user provides one of predefined inputs corresponding either to a positive or a negative response to the first digital media object. The quality indicator of the first digital media object is increased if the response is positive and decreased if the response is negative. The amount of increase or decrease is calculated based on a coefficient value associated with the first user. Subsequent responses to the first digital media object from other users impact the quality indicator of the first digital media object and, also, impact the coefficient value of the first user. Updated coefficient value of the first user is used to calculate impact of subsequent responses of the first user to other digital media objects.

Abstract: A system and method of landmark detection using deep neural network with multi-frequency self-attention is provided. The system includes an encoder network that receives an image of an object of interest as an input and generates multi-frequency feature maps as output. The system further includes an attention layer that receives the generated multi-frequency feature maps and refines the generated multi-frequency feature maps based on correlations or associations between the received multi-frequency feature maps. The system further includes a decoder network that receives the refined multi-frequency feature maps as a second input from the attention layer and generates a landmark detection result based on the second input. The landmark detection result includes a heatmap image of the object of interest and the heatmap image indicates locations of landmark points on the object of interest in the image.

Abstract: A first parcel digital image associated with a first interaction point is received. The first parcel digital image may be associated with a first parcel being transported to or from the first interaction point. At least a second parcel digital image associated with at least a second interaction point is further be received. The second parcel digital image may be associated with the first parcel being transported to or from the second interaction point. A first parcel damage analysis is automatically generated based at least in part on analyzing the first parcel digital image and the at least second parcel image. The damage analysis can include determining whether the first parcel is damaged above or below a threshold.

Abstract: A data analysis computer system is provided that receives a timeseries dataset and generates implied data from the dataset. The dataset is further vectorized to reduce the dimensionality of the data. Users provide input to identify windows of data that either positively or negatively correlate to instances of a given type of occurrence within the data. The user defined windows are converted to fixed sized windows and a machine learning algorithm constructs a model from the data. The model is used to predict instances of the given type of occurrence in newly received data. Validation of the predications may be performed.

Abstract: Provided in the invention is a method and a device of Correction of a ring artifact in a CT image and a computer program medium. The method of correction comprises: pre-processing original detection data; marking a bad detector according to data in the pre-processed original sinogram; acquiring a replacing detection value corresponding to the bad detector by means of a first averaging processing; and performing a CT image reconstruction using a sinogram data after the first averaging processing. The device comprises: a pre-processing unit configured to pre-process original detection data; a marking unit configured to mark a bad detector according to data in the pre-processed original sinogram; a first averaging processing unit configured to acquire a replacing detection value corresponding to the bad detector by means of a first averaging processing; and an image reconstruction unit.

Abstract: This application discloses an object recognition method and apparatus in the field of artificial intelligence. This application relates to the field of artificial intelligence, and specifically, to the field of computer vision. The method includes: obtaining one or more body regions of a to-be-recognized image; determining a saliency score of each of the one or more body regions; and when a saliency score of a body region A is greater than or equal to a categorization threshold, determining a feature vector of an object in the body region A based on a feature of the object in the body region A, and determining a category of the object in the body region A based on the feature vector of the object in the body region A and a category feature vector in a feature library, where the body region A is any one of the one or more body regions.

Abstract: A method for controlling a vehicle in an environment includes generating, via a cross-attention model, a cross-attention cost volume based on a current image of the environment and a previous image of the environment in a sequence of images. The method also includes generating combined features by combining cost volume features of the cross-attention cost volume with single-frame features associated with the current image. The single-frame features may be generated via a single-frame encoding model. The method further includes generating a depth estimate of the current image based on the combined features. The method still further includes controlling an action of the vehicle based on the depth estimate.

Abstract: Disclosed are a vehicle path restoration system through sequential image analysis which includes: an image capturing unit that acquires sequential images from the front camera installed in the subject vehicle; an image analysis unit for generating multiple lanes that can be recognized from the sequential images of the video file acquired by the image capturing unit and multi-paths calculated using the geometric characteristics of the lanes recognized at the current time and the speed of the subject vehicle, that restores the path of the subject vehicle and restores the path of the front vehicle driving in front of the subject vehicle; a memory for storing path data of the subject vehicle and the front vehicle restored by the image analysis unit; and a display unit that expresses the path data of the subject vehicle and the front vehicle stored in the memory in the form of a top view.

Abstract: A method for detecting security holograms on documents in a video stream is disclosed, including: searching for interest points and calculating descriptors in a frame; filtering of interest points in the previous frame so that only points located inside the quadrangle of the outer borders of the document remain; matching the descriptors of interest points of the current and previous frames; application of an algorithm for estimating the parameters of projective transformation between the frames; projective transformation of the quadrangle of the outer boundaries of the document from the previous frame to obtain the outer boundaries of the document in the current frame; document image normalization; calculating the color saturation and hue; updating the saturation and hue values; further considering the pixels of the normalized document image with brightness values not exceeding a preset threshold; filtration of the obtained image.

Abstract: A non-contacting system for visualizing and analyzing periodic movements in machinery includes at least one video acquisition device that acquires sampling data as a video comprising a plurality of video image frames and a data analysis system including processor and memory, and a computer program operating in the processor to filter movements depicted in the video to a specific frequency to normalize the phase in a plurality of objects in the video representing parts or components of the machinery, to compare the movements of such objects which in some embodiments provides for construction of a modified video to visually exaggerate the apparent movement of the at least one of the plurality of objects.

Abstract: Various systems are provided for non-uniform thickness and/or sampling of slabs of the breast to present DBT acquisitions. A method for generating a patient image as a set of slabs representing an imaged object, the method comprising acquiring a tomosynthesis projection, reconstructing a series of slab images, each slab representing a portion of a breast, and a plurality of slabs of non-uniform thickness and/or non-uniform sampling in a 3D reconstructed domain defined by x-, y-, and z-axes.

Abstract: A computer-implemented method for ascertaining an output signal, which characterizes an object detection of an object of an image. The method includes: ascertaining a plurality of object detections with respect to the image; ascertaining a graph based on the plurality of object detections, object detections of the plurality of object detections being characterized by nodes of the graph and overlaps between two object detections each being characterized by edges of the graph; ascertaining a cluster of the graph based on the nodes and on the edges of the graph with the aid of a density-based clustering method; ascertaining an object detection based on the cluster and providing the object detection in the output signal.

Abstract: A checking mechanism for workshop security applying a method for workshop security comprises a transmission device, a recording device, a storage subassembly and a control subassembly. The transmission device comprises a first end (115) and a second end (116). The recording device records personnel and objects in their possession through a security check process, to establish a correspondence. The storage subassembly stores the information comprising personnel and their objects. The control subassembly is used for controlling the recording device to record and store the information to the storage subassembly. The control subassembly can retrieve the information recorded by the recording device to detect a certain person's correspondence to the certain object.

Abstract: A method for recognizing different object-categories within images based on texture classification of the different categories, which is implemented in an electronic device, includes extracting texture features from block images segmented from original images according to at least one Gabor filter; determining a grayscale level co-occurrence matrix of each block image according to the texture features; calculating texture feature statistics of each block image according to the grayscale level co-occurrence matrix; training and generating an object recognition model using the texture features and the texture feature statistics; and recognizing and classifying at least one object in original image according to the object recognition model.

Abstract: The present disclosure discloses an apparatus and a method for detecting a facial pose, an image processing system, and a storage medium. The apparatus comprises: an obtaining unit to obtain at least three keypoints of at least one face from an input image based on a pre-generated neural network, wherein coordinates of the keypoints obtained via a layer in the neural network for obtaining coordinates are three-dimensional coordinates; and a determining unit to determine, for the at least one face, a pose of the face based on the obtained keypoints, wherein the determined facial pose includes at least an angle. According to the present disclosure, the accuracy of the three-dimensional coordinates of the facial keypoints can be improved, thus the detection precision of a facial pose can be improved.

Abstract: Techniques are disclosed for extracting micro-features at a pixel-level based on characteristics of one or more images. Importantly, the extraction is unsupervised, i.e., performed independent of any training data that defines particular objects, allowing a behavior-recognition system to forgo a training phase and for object classification to proceed without being constrained by specific object definitions. A micro-feature extractor that does not require training data is adaptive and self-trains while performing the extraction. The extracted micro-features are represented as a micro-feature vector that may be input to a micro-classifier which groups objects into object type clusters based on the micro-feature vectors.

Abstract: The technology disclosed performs hand pose estimation on a so-called “joint-by-joint” basis. So, when a plurality of estimates for the 28 hand joints are received from a plurality of expert networks (and from master experts in some high-confidence scenarios), the estimates are analyzed at a joint level and a final location for each joint is calculated based on the plurality of estimates for a particular joint. This is a novel solution discovered by the technology disclosed because nothing in the field of art determines hand pose estimates at such granularity and precision. Regarding granularity and precision, because hand pose estimates are computed on a joint-by-joint basis, this allows the technology disclosed to detect in real time even the minutest and most subtle hand movements, such a bend/yaw/tilt/roll of a segment of a finger or a tilt an occluded finger, as demonstrated supra in the Experimental Results section of this application.

Abstract: Systems and methods described herein relate, among other things, to unmixing more than three stains, while preserving the biological constraints of the biomarkers. Unlimited numbers of markers may be unmixed from a limited-channel image, such as an RGB image, without adding any mathematical complicity to the model. Known co-localization information of different biomarkers within the same tissue section enables defining fixed upper bounds for the number of stains at one pixel. A group sparsity model may be leveraged to explicitly model the fractions of stain contributions from the co-localized biomarkers into one group to yield a least squares solution within the group. A sparse solution may be obtained among the groups to ensure that only a small number of groups with a total number of stains being less than the upper bound are activated.