10 results about "Image computing" patented technology

The invention discloses a high-resolution image calculation and display integrated method and system based on a photoelectric calculation hybrid architecture, and belongs to the technical field of image data processing, and the method comprises the steps: carrying out the combined modeling of the time domain gray scale response characteristics of a display panel and a space pixel structure, and constructing a display end prior template; an optical modulation mask is generated based on a template, physical modulation and coding sampling are carried out on an incident light field, a photoelectric mapping relation is utilized to establish a cross-domain correlation tensor as regularization constraint to reconstruct to-be-displayed image data adaptive to panel characteristics, and a display end prior template is combined to carry out consistency residual calculation to generate driving compensation correction. And finally synthesizing an optimized display driving sequence. A display end prior template is combined with optical coding to construct a cross-domain association tensor, and driving data is reconstructed by regularization constraint, so that compensation and optimization of space-time coupling characteristics of a display panel can be realized.

The application discloses a PCBA foreign matter detection method based on a multi-resolution subspace projection, acquires a to-be-detected board and a standard reference board image, determines an adaptive down-sampling multiple based on a minimum foreign matter physical area, performs image registration with the aid of a mask to eliminate geometric deformation, extracts a multi-resolution feature map through a pre-trained deep convolutional neural network, calculates feature differences, and uses a dynamic threshold to screen a preliminary candidate point set, constructs a local principal component subspace of a local neighborhood of a reference image, performs first-stage screening by calculating the orthogonal projection error of a test feature vector in the space, maps remaining candidate points to a multi-scale feature space and splices them, constructs a global multi-scale principal component subspace, performs second-stage screening through a global projection error, and outputs a final result selection, and through the implementation of the application, the problems of a high-definition image computing power bottleneck and a high false alarm in comparison are solved, the application has zero-sample generalization capability, and sample-free training can accurately detect tiny foreign matters.

Techniques are disclosed for imaging computing components of a scalable footprint data center in a prefab factory. A host device in a host region data center can execute a region replicator. The region replicator can obtain configuration information for the plurality of computing devices for the scalable footprint data center. The configuration information can include connection information for a management controller of a computing device of the plurality of computing devices. The region replicator can configure, using the configuration information, the management controller to execute an imaging process on the computing device. The imaging process can be configured to perform an imaging operation for a storage device of the computing device. The region replicator can receive an indication that the imaging operation is complete.

An electronic component bounding system for bounding an electronic component on a circuit board includes an image capturing device and a computing device. The image capturing device is configured to capture the electronic component to obtain a first image. The computing device is electrically connected to the image capturing device. The computing device stores a reference bounding box. The computing device sequentially performs a color space conversion and a binarization process on the first image to generate a second image. The second image has a color block distribution. The computing device obtains a position of the electronic component based on the color block distribution. The computing device sets a detection bounding box in the first image based on the position of the electronic component in the second image. The computing device determines a degree of coincidence between the detection bounding box and the reference bounding box and an offset corresponding to the degree of coincidence. When the offset is greater than a threshold, the computing device corrects the detection bounding box based on the offset.

The invention relates to the technical field of distributed computing and resource scheduling, and provides a remote sensing image computing task scheduling method and system in a resource limited scene, and the method comprises the steps: injecting a submitted remote sensing image computing task into a task queue of a uniform resource pool; monitoring the state of each node in the resource pool and the computing cluster, obtaining a to-be-scheduled task from the task queue, screening out all candidate nodes meeting a hard condition from the cluster nodes through a filtering strategy according to the resource demand of the task, and scoring each candidate node based on a multi-dimensional scoring strategy; calculating a multi-dimensional weighted comprehensive score of each candidate node, and selecting the candidate node with the highest comprehensive score as a target node; and binding the task to the target node, and receiving and executing the task by the Agent on the node. According to the method, dynamic allocation and load balancing of resources are realized while the task execution efficiency is ensured, so that the overall utilization rate of a computing cluster and the intelligent level of scheduling are improved.

The application discloses a dMRI data reconstruction method, device, medium and program product, relates to the technical field of neural image computing, and comprises the following steps: acquiring undersampled scanning data, wherein the scanning data comprises a zero diffusion image, a structural image, and a plurality of first diffusion weighted images collected under a plurality of different first sampling conditions; performing signal decomposition on each first diffusion weighted image through the zero diffusion image to obtain a plurality of diffusion signal components; determining a condition guided signal from the plurality of diffusion signal components according to a preset target sampling condition, wherein the condition guided signal is used for guiding a generative model to generate diffusion characteristics under the target sampling condition; taking the zero diffusion image, the structural image and the condition guided signal as multi-channel input data, inputting the multi-channel input data and the target sampling condition into a pre-trained generative model, and outputting dMRI data under the target sampling condition. The application realizes high-quality, fast and stable reconstruction of dMRI data.

The application belongs to the technical field of brain image computing and medical auxiliary research, and particularly discloses a long-term individual AD risk prediction model and a prediction method based on multi-scale deep learning, which comprises an MRI data acquisition and processing module, an MRI feature extraction module and a risk prediction module. The application adopts the long-term individual AD risk prediction model and the prediction method based on multi-scale deep learning, provides a novel multi-scale model, the model predicts the risk of MCI transforming into AD at the individual level, based on the baseline diagnostic data of the subjects, can obtain the transformation risk once every 6 months within 60 months, thereby effectively tracking the transformation risk of MCI and estimating the transformation time.

The application discloses a surface water empty pixel reconstruction method based on optimal similarity, and is characterized in that the method comprises the following steps: obtaining remote sensing image data sets in a to-be-measured region, and performing empty pixel screening to obtain a first target database with empty pixels and a first reference database without empty pixels; obtaining a three-value image, a two-value image and a one-value image in the to-be-measured region, and performing screening on the first target database and the first reference database to obtain a corresponding second target database and a second reference database; performing image operation on the images in the second reference database to obtain optimal similar images of the images in the second reference database; reconstructing the empty pixels in the second target database based on the optimal similar images to obtain reconstructed images; and supplementing the reconstructed images to the second reference database to complete the reconstruction of the surface water empty pixels. The application can reasonably allocate water resources, maintain the ecological balance of water resources, and realize the reasonable utilization of water resources.

Techniques are disclosed for imaging computing components of a scalable footprint data center in a prefab factory. A host device in a host region data center can execute a region replicator. The region replicator can obtain configuration information for the plurality of computing devices for the scalable footprint data center. The configuration information can include connection information for a management controller of a computing device of the plurality of computing devices. The region replicator can configure, using the configuration information, the management controller to execute an imaging process on the computing device. The imaging process can be configured to perform an imaging operation for a storage device of the computing device. The region replicator can receive an indication that the imaging operation is complete.

1. The name of the design product: backpack workstation. 2. The use of the design product: the design product is used for portable workstations in the fields of front-end high-performance computing, machine learning, AI image computing, machine reasoning, electronic communication, device service, etc. 3. The design points of the design product: in shape. 4. The picture or photo that best indicates the design points: design 1 usage state diagram. 5. Design 1 is designated as the basic design.