Various embodiments utilize application-based processing parameters to dynamically configure a radar-based detection system based upon an operating context of an associated device. A first application with execution priority on a device dynamically configures the radar-based detection system to emit a radar field suitable for a first operating context associated with the first application. The first application can also dynamically configure processing parameters of the radar-based detection system, such as digital signal processing parameters and machine-learning parameters. In some cases, a second application assumes execution priority over the first application, and dynamically reconfigures the radar-based detection system to emit a radar field suitable to a second operating context associated with the second application. Alternately or additionally, the second application can dynamically reconfigure the processing parameters of the radar-based detection system based upon the second operating context of the second application.

A method of multi-sensor data fusion includes determining a plurality of first data sets using a plurality of sensors, each of the first data sets being associated with a respective one of a plurality of sensor coordinate systems, and each of the sensor coordinate systems being defined in dependence of a respective one of a plurality of mounting positions for the sensors; transforming the first data sets into a plurality of second data sets using a transformation rule, each of the second data sets being associated with a unified coordinate system, the unified coordinate system being defined in dependence of at least one predetermined reference point; and determining at least one fused data set by fusing the second data sets.

A water stress detection method for tomatoes in a seedling stage based on micro-CT and polarization-hyperspectral imaging multi-feature fusion, comprising: using micro-CT to scan microscopic morphological features such as water stress stomata, spongy body, palisade tissue, cilia, vascular bundle, root volume, main root, and root hair density of tomatoes; using a polarization-hyperspectral imaging system to obtain macroscopic morphological features such as crown width, plant height, and leaf inclination of water stress plants, as well as leaf vein distribution, average gray, and leaf margin shaded area under a water-sensitive wavelength of 1450 nm, and macroscopic morphological features such as polarization states, stock vectors, and Mueller matrix variables of 1450 nm feature images at 0, 45, 90, 135, and 180 feature polarization angles. By fusion of internal and external structures, above-ground, underground, and macroscopic and microscopic morphological features of water stress tomatoes, and mutual fusion of water stress feature wavelength images and polarization state features, advantages are complementary, comprehensive and precise extraction and precise quantitative analysis of water stress features of the tomatoes are implemented, and a basis for scientific management of water and fertilizer integration of facilities is provided.

A user terminal according to an embodiment of the present invention includes a capturing device for capturing a face image of a user, and an eye tracking unit for, on the basis of a configured rule, acquiring, from the face image, a vector representing the direction that the face of the user is facing, and a pupil image of the user, and performing eye tracking of the user by inputting, in a configured deep learning model, the face image, the vector and the pupil image.

An electronic device includes: a display; a memory; and at least one processor, wherein the at least one processor is configured to display a first image and one or more objects on the display, acquire a second image in response to a first user input, acquire first information based on the second image and a representing type of at least one object among the one or more objects, transmit the acquired first information to a server, receive information on at least one third image related to the first information from the server, display the information on the at least one third image on the display, receive a second user input for selecting the at least one third image, and change the first image into the at least one third image and display the at least one third image based on the second user input. Other various embodiments are possible.

Mechanisms are provided for implementing a patient complexity classification (PCC) computing system. The PCC computing system receives medical image study data for a patient that comprises one or more medical image data structures and one or more corresponding medical image metadata data structures. A natural language processing engine of the PCC computing system performs natural language processing on the medical image metadata data structure to extract features indicative of at least one of patient or medical image characteristics. A complexity classifier of the PCC computing system evaluates the extracted features to determine a patient complexity indicating a complexity of a medical condition of the patient. Routing logic associated with the PCC computing system routes the one or more medical image data structures and one or more corresponding medical image metadata data structures to one or more downstream patient evaluation computing systems based on the determined patient complexity.

Embodiments of this application disclose an image fusion method performed by a computing device. The method includes the following steps: obtaining source face image data of a current to-be-fused image and resource configuration information of a current to-be-fused resource, performing image recognition processing on the source face image data, to obtain source face feature points corresponding to the source face image data, and generating a source face three-dimensional grid of the source face image data according to the source face feature points, performing grid fusion by using a resource face three-dimensional grid and the source face three-dimensional grid to generate a target face three-dimensional grid, and performing face complexion fusion by using source complexion data of the source face image data and resource complexion data of resource face image data on the target face three-dimensional grid, to generate fused target face image data.

The disclosure relates to a method for evaluating an optical appearance in the surroundings of a vehicle and to a vehicle. The method has the steps of providing a captured image of the surroundings of a vehicle and extracting features from the captured image. Furthermore, the method comprises carrying out a first analysis of the captured image, wherein one or more objects are detected as surfaces and the result of the analysis is provided as a first analysis result. A second analysis of the captured image is also carried out, wherein edges of one or more objects are detected and the result of the analysis is provided as a second analysis result, the first analysis and the second analysis being carried out independently of each other. The method further comprises combining the first analysis result and the second analysis result to form an output image in which the detected edges from the second analysis result are excluded on the surfaces of the detected objects from the first analysis result.

The present disclosure relates to a video rating method, a video rating device, equipment and a storage medium, relating to the field of multimedia. An embodiment of the present disclosure provides a method for automatically rating a video based on features of multiple modals of the video and rating embedding modes. By fusing the features of the multiple modals of the video, the rating of the video is converted into rating embedding in a vector space, and a matching degree between a target feature fusing with the multiple modals and each rating embedding is acquired, the rating of the video is predicted according to the matching degree corresponding to each rating embedding, and the video rating efficiency and accuracy can be improved.

A multi-modal emotion recognition system is disclosed. The system includes a data input unit for receiving video data and voice data of a user, a data pre-processing unit including a voice pre-processing unit for generating voice feature data from the voice data and a video pre-processing unit for generating one or more face feature data from the video data, a preliminary inference unit for generating situation determination data as to whether or not the user's situation changes according to a temporal sequence based on the video data. The system further comprises a main inference unit for generating at least one sub feature map based on the voice feature data or the face feature data, and inferring the user's emotion state based on the sub feature map and the situation determination data.