Methods and systems for determining a respective mass associated with respective portions of the respective layers of metallic scrap material deposited into a charging-bucket associated with a batchwise-charged electric arc furnace (EAF) are provided, in which the methods and systems determine the respective masses associated with the respective portions of the respective layers of metallic scrap material based on (a) the respective volume of the respective portions of the respective layers of metallic scrap material and (b) the respective assigned densities assigned by a machine learning classification model based on digital images of the respective portions of the respective layers of metallic scrap material.

The described positional awareness techniques employing sensory data gathering and analysis hardware with reference to specific example implementations implement improvements in the use of sensors, techniques and hardware design that can enable specific embodiments to provide positional awareness to machines with improved speed and accuracy. The sensory data are gathered from an operational camera and one or more auxiliary sensors.

In accordance with an embodiment, a neural network is configured to: process a first grid representing at least a first portion of a field of view of a first sensor; process a second grid representing at least a second portion of a field of view of a second sensor; and fuse the processed first grid with the processed second grid into a fused grid, where the fused grid includes information about the occupancy of the first portion of the field of view of the first sensor and the occupancy of the second portion of the field of view of the second sensor.

A method and device for sensor data fusion for a vehicle as well as a computer program and a computer-readable storage medium are disclosed. At least one sensor device (S1) is associated with the vehicle (F), and in the method, fusion object data is provided representative of a fusion object (O.sub.F) detected in an environment of the vehicle (F); sensor object data is provided representative of a sensor object (O.sub.S) detected by the sensor device (S1) in the environment of the vehicle (F); indicator data is provided representative of an uncertainty in the determination of the sensor object data; reference point transformation candidates of the sensor object (O.sub.S) are determined depending on the indicator data; and an innovated fusion object is determined depending on the reference point transformation candidates.

Disclosed is a system for medical procedure tracking, evaluation and assistance, wherein one or more video cameras, one or more acoustic sensors or one or more medical device interfaces acquire video, audio or medical device feeds from a medical treatment setting. A scene evaluation module detects scene related features in the video, audio or medical device feeds. A procedure compliance assessment module compares one or more scene related features detected and reported by the scene evaluation module to a list of expected actions or equipment usages associated with the procedure being performed in the treatment setting. A procedure assistance module provides compliance based procedure related action recommendations or instructions from within the list of expected actions or equipment usages.

Distance measurements are received from one or more distance measurement sensors, which may be coupled to a vehicle. A three-dimensional (3D) point cloud are generated based on the distance measurements. In some cases, 3D point clouds corresponding to distance measurements from different distance measurement sensors may be combined into one 3D point cloud. A voxelized model is generated based on the 3D point cloud. An object may be detected within the voxelized model, and in some cases may be classified by object type. If the distance measurement sensors are coupled to a vehicle, the vehicle may avoid the detected object.

The technology disclosed relates to authenticating users using a plurality of non-deterministic registration biometric inputs. During registration, a plurality of non-deterministic biometric inputs are given as input to a trained machine learning model to generate sets of feature vectors. The non-deterministic biometric inputs can include a plurality of face images and a plurality of voice samples of a user. A characteristic identity vector for the user can be determined by averaging feature vectors. During authentication, a plurality of non-deterministic biometric inputs are given as input to a trained machine learning model to generate a set of authentication feature vectors. The sets of feature vectors are projected onto a surface of a hyper-sphere. The system can authenticate the user when a cosine distance between the authentication feature vector and a characteristic identity vector for the user is less than a pre-determined threshold.

At a first timestep, one or more first objects can be determined in a first fusion image based on determining one or more first radar clusters in first radar data and determining one or more first two-dimensional bounding boxes in first camera data. First detected objects and first undetected objects can be determined by inputting the first objects and the first radar clusters into a data association algorithm, which determines first probabilities and adds the first radar clusters and the first objects to one or more of first detected objects or first undetected objects by determining a cost function. The first detected objects and the first undetected objects can be input to a first Poisson multi-Bernoulli mixture (PMBM) filter to determine second detected objects, second undetected objects and second probabilities. The second detected objects and the second undetected objects can be reduced based on the second probabilities determined by the first PMBM filter and the second detected objects can be output.

A method and system for training an image classification model is disclosed. An aspect is to separate training processes of a feature value extraction model and an image classification model and train the feature value extraction model on a representative feature value suitable for image classification into a specific label value (e.g., “Peak”), thereby improving accuracy and performance of a classification model for a ground-penetrating radar (GPR) image that is captured by a GPR and is not easy for feature value extraction.

A method, a system, a device and a medium for landslide identification based on full Polarimetry Synthetic Aperture Radar (full PoISAR) are provided. The method mainly includes: registering target full PoISAR data with target optical remote sensing data and target digital elevation model data to obtain a first registration result and a second registration result; determining a polarization feature, a decomposition feature, and a terrain feature of a target area according to registration results; determining a texture feature and a hue feature of the target area according to the target full PoISAR data; determining a spectrum feature of the target area according to the target optical remote sensing data; fusing abovementioned multi-dimensional features to obtain a target fusion feature; and inputting the target fusion feature into a landslide mass identification model for identifying a landslide mass, so as to determine a landslide area in the target area.