The disclosure relates to a method for making sensor data more robust to adversarial perturbations, wherein sensor data are obtained from at least two sensors, wherein the sensor data obtained from the at least two sensors are replaced in each case piecewise by means of quilting, wherein the piecewise replacement is carried out in such a way that the respectively replaced sensor data from different sensors are plausible relative to one another, and wherein the sensor data replaced piecewise are output.

Apparatus and methods for controlling access to a restricted area by an access control device includes obtaining a first image using a first sensor mounted at a first location. A second image is obtained using a second sensor mounted at a location different from a location of the first sensor. The second image is processed, using the second sensor, to obtain information regarding the detected objects in the second image. The information regarding the detected objects is sent from the second sensor to the first sensor. The first sensor compares the received information with a number of objects detected using the first image. A tailgating event is identified, in response to determining that the number of objects detected using the first image does not match the information regarding the number of objects detected using the second image. A tailgating notification is outputted, by the first sensor, indicating a tailgating event.

A method and system for evaluating performance of operation resources using Artificial Intelligence (AI) is disclosed. In some embodiments, the method includes receiving, each of a plurality of performance parameters associated with a set of operation resources. The method further includes determining a set of features for each of the plurality of performance parameters. The method further includes creating one or more feature vectors corresponding to each of the plurality of performance parameters. The one or more feature vectors are created based on a first pre-trained machine learning model. The method further includes assessing the one or more feature vectors, based on the first pre-trained machine learning model and classifying the set of operation resources into one of a set of performance categories based on the assessing of the one or more feature vectors. The method further includes evaluating performance of at least one of the set of operation resources.

A vehicle generates a city-scale map. The vehicle includes one or more Lidar sensors configured to obtain point clouds at different positions, orientations, and times, one or more processors, and a memory storing instructions that, when executed by the one or more processors, cause the system to perform registering, in pairs, a subset of the point clouds based on respective surface normals of each of the point clouds; determining loop closures based on the registered subset of point clouds; determining a position and an orientation of each of the subset of the point clouds based on constraints associated with the determined loop closures; and generating a map based on the determined position and the orientation of each of the subset of the point clouds.

A method, computer program product, and computing system for proactive encounter scanning is executed on a computing device and includes obtaining encounter information of a patient encounter. The encounter information is proactively processed to determine if the encounter information is indicative of one or more medical conditions and to generate one or more result set. The one or more result sets are provided to the user.

The present exemplary embodiments provide a hybrid sensor, a Lidar sensor, and a moving object which generate composite data by mapping distance information on an obstacle obtained through the Lidar sensor to image information on an obstacle obtained through an image sensor and predict distance information of composite data based on intensity information of a pixel, to generate precise composite data.

A bad weather judgment apparatus and a bad weather judgment method thereof are disclosed. The apparatus includes a target recognizer configured to recognize targets in detection areas of a plurality of heterogeneous sensors based on sensor recognition information received from the heterogeneous sensors, a counter configured to count the number of cases based on detection states of the heterogeneous sensors about a same target among the targets, and a bad weather judger configured to determine whether the same target is present in bad weather judgment zones of the detection areas of the heterogeneous sensors, control the counter to increment or decrement the number of the cases based on detection states of the heterogeneous sensors about whether the same target is present in the bad weather judgment zones, and judge current weather to be bad weather when the number of the cases is greater than a threshold value.

The present application discloses an imaging system for detecting human-object interaction and a method for detecting human-object interaction thereof. The imaging system includes an event sensor, an image sensor, and a controller. The event sensor is configured obtain an event data set of the targeted scene according to variations of light intensity sensed by pixels of the event sensor when an event occurs in the targeted scene. The image sensor is configured capture a visual image of the targeted scene. The controller is configured to detect human according to the event data set, trigger the image sensor to capture the visual image when the human is detected, and detect the human-object interaction in the targeted scene according to the visual image and a series of event data sets obtained by the event sensor during the event.

Aspects include receiving a request to perform an image classification task in a target domain. The image classification task includes identifying a feature in images in the target domain. Classification information related to the feature is transferred from a source domain to the target domain. The transferring includes receiving a plurality of pairs of task-irrelevant images that each includes a task-irrelevant image in the source domain and in the target domain. The task-irrelevant image in the source domain has a fixed correspondence to the task-irrelevant image in the target domain. A target neural network is trained to perform the image classification task in the target domain. The training is based on the plurality of pairs of task-irrelevant images. The image classification task is performed in the target domain and includes applying the target neural network to an image in the target domain and outputting an identified feature.

Provided is a learning-based data processing system which generates a learning model by learning a learning data set, recognizes observational data according to the learning model, and provides a recognition result. The learning-based data processing system may include a data recognition device configured to generate a cascaded learning model by cascading a first learning model generated based on a first learning data set and a second learning model generated based on a second learning data set.