A method may include obtaining an image representing a region of interest (ROI) of an object. The ROI may include two or more sub-regions. The method may include determining an average value of quantitative indexes associated with elements in the image corresponding to a first region of the ROI. The method may include determining, for each of the two or more sub-regions of the ROI, a threshold based on the average value; identifying target elements in the image based on the thresholds of the two or more sub-regions. The method may include assigning a presentation value to each of at least some of the target elements based on the average value and the quantitative index of the each target element. The method may include generating a presentation of the image based on the presentation values.

A method for determining hardness of a material by implementing 3D imaging is proposed. The imaging provides database of points on the 3D imprint in an orthogonal X-Y-Z coordinate system. An imaginary image of the imprint is formed by finding a plurality of intersection points obtained by intersecting the imprint image in X-Y plane with the X-Z plane movable in the Y-axis direction for obtaining a plurality of points of intersection that lay in the X-Y plane. Statistical processing of the plurality of the points of intersection makes it possible to form imaginary image of the imprint in the X-Y plane and to use the reference dimension of the obtained imaginary image as a parameter for insertion into the hardness calculation formula.

A system for patient cardiac imaging and tissue modeling. The system includes a patient imaging device that can acquire patient cardiac imaging data. A processor is configured to receive the cardiac imaging data. A user interface and display allow a user to interact with the cardiac imaging data. The processor includes fat identification software conducting operations to interact with a trained learning network to identify fat tissue in the cardiac imaging data and to map fat tissue onto a three-dimensional model of the heart. A preferred system uses an ultrasound imaging device as the patient imaging device. Another preferred system uses an MRI or CT image device as the patient imaging device.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for implementing a reservoir computing neural network. In one aspect there is provided a reservoir computing neural network comprising: (i) a brain emulation sub-network, and (ii) a prediction sub-network. The brain emulation sub-network is configured to process the network input in accordance with values of a plurality of brain emulation sub-network parameters to generate an alternative representation of the network input. The prediction sub-network is configured to process the alternative representation of the network input in accordance with values of a plurality of prediction sub-network parameters to generate the network output. The values of the brain emulation sub-network parameters are determined before the reservoir computing neural network is trained and are not adjusting during training of the reservoir computing neural network.

Methods, systems, and devices for equipment reading in a factory or plant environment are described, including: capturing an image of an environment including a measurement device; detecting a target region included in the image, the target region including at least a portion of the measurement device; determining identification information associated with the measurement device based on detecting the target region; and extracting measurement information associated with the measurement device based on detecting the target region. In some aspects, detecting the target region may include: providing the image to a machine learning network; and receiving an output from the machine learning network in response to the machine learning network processing the image based on a detection model, the output including the target region.

An apparatus, including an interface configured to receive images with measured distance information of an environment in which an autonomous agent is designed to operate; and processing circuitry that is configured to: generate distance histogram images over time, wherein the distance histogram images include the measured distance information in corresponding picture elements; perform a distribution-based outlier analysis on the distance histogram images to classify each picture element of each of the received images as either an outlier picture element representing a dynamic object or a non-outlier picture element representing a static portion of the environment; and track a dynamic object over time and cause an action by the autonomous agent if it is determined, based on a result of the distribution-based outlier analysis, a distance between the dynamic object and the autonomous agent is less than a predefined distance.

A reference pose of an object in a coordinate system of a map of an area is determined. The reference pose is based on a three-dimensional (3D) reference model representing the object. A first pose of the object is determined as the object moves with respect to the coordinate system. The first pose is determined based on the reference pose and sensor data collected by the sensor at a first time. A second pose of the object is determined as the object continues to move with respect to the coordinate system. The second pose is determined based on the reference pose, the first pose, and sensor data collected by the sensor at a second time consecutive to the first time.

A controller of a medical image processing device acquires a medical image of a subject. The controller causes a display to display a pre-modification image in which at least the position or range of a lesion to be modified on the medical image is displayed. The controller receives an instruction to designate at least the position or range of the lesion to be modified in a state in which the pre-modification image is displayed on the display. When at least the position or range of the lesion is designated, the controller acquires a predicted disease image in which the lesion is modified according to the designated information on the basis of the medical image. The controller causes the display to display the predicted disease image and the pre-modification image simultaneously or in a switching manner.

A method may include obtaining an image representing a region of interest (ROI) of an object. The ROI may include two or more sub-regions. The method may include determining an average value of quantitative indexes associated with elements in the image corresponding to a first region of the ROI. The method may include determining, for each of the two or more sub-regions of the ROI, a threshold based on the average value; identifying target elements in the image based on the thresholds of the two or more sub-regions. The method may include assigning a presentation value to each of at least some of the target elements based on the average value and the quantitative index of the each target element. The method may include generating a presentation of the image based on the presentation values.

Various implementations disclosed herein include devices, systems, and methods that provide measurements of objects based on a location of a surface of the objects. An exemplary process may include obtaining a three-dimensional (3D) representation of a physical environment that was generated based on depth data and light intensity image data, generating a 3D bounding box corresponding to an object in the physical environment based on the 3D representation, determining a class of the object based on the 3D semantic data, determining a location of a surface of the object based on the class of the object, the location determined by identifying a plane within the 3D bounding box having semantics in the 3D semantic data satisfying surface criteria for the object, and providing a measurement of the object, the measurement of the object determined based on the location of the surface of the object.