10 results about "Focus area" patented technology

The invention discloses a capsule endoscopic image super-resolution reconstruction method based on deep learning. The method comprises the steps of designing a data enhancement and label mechanism for pollution shielding; optimizing the ESRGAN model in combination with a lightweight structure and an attention mechanism; generating a structure sensing label; and training the model. The invention provides an image super-resolution reconstruction method fused with medical structure perception in order to solve the problems that a capsule endoscopic image is low in resolution, serious in pollution and shielding, difficult in structural detail recognition and the like in an actual clinical environment. According to the method, a pollution simulation data enhancement mechanism and a structural mask label system are constructed, so that the attention capability of the model on medical key information is effectively improved; a super-division network architecture combining lightweight improvement and attention mechanism optimization is adopted, so that the reconstruction quality is ensured, and meanwhile, the computing resource demand is greatly reduced; and a structure weighting loss function and an edge perception loss strategy are designed, so that the visual performance of the focus area is obviously enhanced.

The invention provides an automatic pathological section labeling method based on a viewpoint tracking technology. The method is applied to a computer device and comprises the following steps: receiving an instruction for acquiring a pathological section; when a subject observes the pathological section, viewpoint track information of the subject is collected in real time through an eye tracker, and voice information of the subject during pathological section observation is collected in real time through a microphone; generating a viewpoint track information image of the subject corresponding to the pathological section in real time based on the viewpoint track information, and generating a corresponding text label in real time based on the voice information; automatically identifying a focusing area in the viewpoint track information image through a density clustering algorithm; generating a pathological section initial labeling box based on the focusing area; adjusting the size of the initial labeling box in real time to generate a final labeling box; and binding the text labels with the corresponding final labeling boxes one by one. According to the method, the viewpoint track information of the subject is captured, the high-quality pathological annotation is automatically generated, and man-machine collaborative annotation is achieved.

The invention provides an image display method and device, equipment and a storage medium to achieve accurate positioning of a guide wire position and reduce the path deviation risk, and the method comprises the steps that preoperative three-dimensional image data of a focus area of a patient is obtained, three-dimensional reconstruction processing is conducted on the three-dimensional image data, and a focus area three-dimensional model is generated; in the guide wire puncture operation process, a multi-axial image of a puncture part of a patient is collected, and the multi-axial image comprises a plurality of axial two-dimensional images; determining a projection transformation relationship between the plurality of axial two-dimensional images and a three-dimensional space; identifying and extracting guide wire features in the two-dimensional image, and determining two-dimensional feature information of the guide wire; according to the projection transformation relation, converting multiple pieces of axial guide wire two-dimensional feature information into three-dimensional space coordinates, and generating guide wire three-dimensional data representing the spatial position of the guide wire; and according to the three-dimensional data of the guide wire, generating a three-dimensional model of the guide wire, and displaying the three-dimensional model of the guide wire on the three-dimensional model of the focus area in an overlapping manner.

A method and a system for enhanced information broadcasting are disclosed. A method according to the present invention may leverage artificial intelligence (AI) to convert spoken words into video clips in real time. The duration of these clips may be designed to be flexible, even in a customizable manner: long enough to capture the essence of the content being presented, yet short enough to maintain the natural flow of the conversation. Thus, the present invention offers tailored video content to meet real time needs of meeting participants by adapting to individual roles, priorities, and even calendar availability. The present invention dynamically segments and adjusts content based on user focus areas, job role and engagement levels, creating more relevant, role-specific visualizations. Additionally, the present invention offers interactivity during meetings in a way that users can request, modify, or view content in alternative formats.

The invention provides a shaft AI video intelligent inspection method and system, and the method comprises the steps: obtaining a real-time video of a shaft support ring connection structure in a preset time period, and extracting the axial displacement of a connection bolt from the real-time video; identifying a potential failure risk area of the connecting bolt by extracting a high deviation value and an abnormal trend in the potential failure risk; determining a focus area of the video acquisition equipment according to the potential failure risk area, performing video resolution enhancement processing on a focus area video, and determining displacement data of a bolt in the focus area; if the displacement data of the bolt in the focus area exceeds a preset displacement threshold value, it is judged that the thread gap is abnormally enlarged, and the early-stage connecting bolt loosening state after the strengthening loosening sign is determined according to the displacement data and the thread gap dynamic change value.

The invention discloses a slice analysis method and device and a storage medium, and relates to the field of pathological sections.The method comprises the steps that when a browsing operation on a to-be-analyzed slice is detected, a region of interest of the to-be-analyzed slice is determined; obtaining a rapid analysis result of the region of interest, and outputting the rapid analysis result at a target position of the region of interest; when it is detected that the browsing duration of the region of interest is greater than or equal to a preset duration, obtaining an accurate analysis result of the region of interest from a preset cache region; and outputting the accurate analysis result in the current browsing area. According to the method, the rapid analysis result is directly provided for the user, the accurate analysis result is directly output after the user browses the rapid analysis result, and the problem that the analysis content is not output in time is solved by sequentially outputting the analysis results with different accuracies.

The invention provides a focus adaptation method and device of equipment, the equipment, a medium and a program product, and relates to the technical field of computers.The method comprises the steps that control information of a plurality of first controls is screened out from page control information of remote control equipment; the first control is a control capable of interacting with the operation of the user; if the monitored remote controller event is a moving event, based on the control information of the first controls, determining the offset of moving from the current control to each first control; selecting the first control with the minimum offset as a next second control for obtaining a focus; and drawing a focus frame of the second control based on the boundary information of the second control. By positioning and calculating the position of the focus control, drawing the focus frame and responding to the event of the focus area, focus adaptation which is low in cost, small in difficulty, convenient to operate, stable and reliable is achieved, and meanwhile the focus adaptation method has compatibility for different devices, systems and applications.

The present invention claims protection for a video pedestrian re-identification method based on region augmentation and location information interaction, which belongs to the image retrieval method. It includes the following steps: data slicing and preprocessing; then using the channel attention module to reconstruct the channel weights; then extracting the salient features of the previous frame, and further transitioning the focus area of ​​the subsequent frame from salient to comprehensive; then using the location information interaction (LII) module to promote the interaction of location information across all frames to achieve mutual enhancement between frames; finally, designing a loss function based on the model and training it. It is worth noting that in the test phase, the LII module is removed to improve the inference speed. The present invention proposes a lightweight video pedestrian re-identification model that demonstrates strong performance and generalization capabilities on multiple public benchmarks.

The present invention provides a method, device and electronic device for interacting with complex virtual reality scenes based on eye tracking, including: tracking the user's eye movement data to determine the user's focus area in the virtual reality scene in real time; projecting all objects in the user's focus area onto a circular plane suspended in front of the user while maintaining the relative position relationship from the user's perspective, and intelligently adjusting the positions of the objects projected into the circular plane so that all objects are separated from each other and do not overlap; and selecting and interacting with objects in the circular plane. The present invention utilizes the user's line of sight information to help the user quickly and accurately select target objects in complex virtual scenes. Compared with traditional ray interaction methods, the present invention can significantly shorten the selection time and improve the accuracy of target object selection, especially when there are a large number of overlapping or occluded objects in the scene, and can effectively solve the problem that traditional methods have difficulty in selecting occluded targets.

The application discloses an information generation method and device, and relates to the technical field of deep learning. A specific embodiment of the method comprises: acquiring a change range of a focusing area of a user's line of sight on a smart display device in a preset time period; in response to determining that the change range meets a preset condition, acquiring pupil diameter change data of the user in the preset time period; and based on the pupil diameter change data, determining emotional information of the user on the focusing area. This embodiment effectively improves the accuracy of the emotional information generated for the focusing area.