44results about How to "Prevent oversegmentation" patented technology

The invention discloses a point cloud data partitioning method based on hyper voxels. The three-dimensional geometrical relationship and regional connectivity of point cloud data are taken into account, the point cloud data are partitioned by using a clustering method, so that the hyper voxels attached on a target boundary are obtained; the residual value in planar fit with data of the hyper voxels is calculated, the hyper voxels are sorted and sieved according to the residual value to obtain effective seed hyper voxels, region growing is carried out by using a normal distribution histogram and the difference between a geodesic distance and an Euclidean distance, and finally partitioning treatment on the point cloud data is finally realized. The point cloud data with indoor local scenes are input, and accurate partitioning for the point cloud data is realized by using the hyper voxels and a region growing algorithm. Compared with a traditional point cloud partitioning method, under the premise of guaranteeing the partitioning efficiency, the problems of insufficient partitioning and over partitioning caused by direct treatment of the point cloud data are avoided, a partitioning result with accurate boundary information is obtained, and the partitioning method is healthy for sampling density and noise of the point cloud data.

The invention discloses a point cloud partition method and device, and relates to the technical field of three-dimensional reconstruction. The point cloud partition method includes the following steps: (S1) line-by-line scanning is carried out on a measured scene through a depth transducer to obtain depth information of the measured scene, and coordinate transformation is carried out on the depth information of the measured scene to obtain three-dimensional information of the measured scene under a local coordinate system; (S2) ground point clouds are partitioned from the three-dimensional information; (S3) clustering partition is carried out on non-ground point clouds in the self-adaptation threshold value clustering partition mode, wherein the non-ground point clouds are the other point clouds except the ground point clouds in the three-dimensional information. By means of the point cloud partition method and device, clustering partition is carried out on the non-ground point clouds in the self-adaptation threshold value clustering partition mode, and insufficient partition and excessive partition caused by clustering partition on the non-ground point clouds with fixed threshold values are effectively avoided.

The invention provides a method for segmenting adhesion cells in an image, which comprises the following steps of: performing image binaryzation, and performing distance transform on a binary image to obtain a distance value of each point; detecting local extreme points in a distance image, and screening to obtain central points representing cells; performing water area segmentation on the distance image, and determining the subjection relation of subblocks and the cells according to the distance between the center of each subblock and the center of each cell; and finally segmenting intermediate blocks adjacent to a plurality of subblocks accurately. By the method, the problems of over-segmentation and segmentation error which are likely to occur in the conventional watershed segmentationare solved effectively, and the method has the good applicability to the adhesion of the cells.

An intelligent monitoring system for a power cable production process, including an image acquisition component, a sensor component, a wireless transmission module, an intelligent monitoring center and a danger alarm module, the sensor component is used to collect environmental data and temperature data on the surface of power cable production equipment, and The collected data is transmitted to the intelligent monitoring center, and the intelligent monitoring center processes the received data and compares it with the preset safety threshold, and when the data is higher than the preset safety threshold, the danger alarm module gives an alarm, and The image acquisition component is used to acquire images of the positions of the sensor nodes that acquire the data, and the acquired images are processed and displayed. The beneficial effects of the invention are: realizing the effective monitoring of the environment of the power cable production workshop and the operating state of the power cable production equipment, and improving the intelligence of the monitoring of the power cable production process.

The invention relates to the field of medical image processing and aims to provide a fully-automatic three-dimensional liver segmentation method based on a convolution nerve network. The fully-automatic three-dimensional liver segmentation method based on the convolution nerve network comprises the following processes: preparing a training set, and training the convolution nerve network, processing CTA volume data of an abdominal liver by utilizing the trained convolution nerve network to obtain a segmentation result of the liver. The liver is segmented by means of the three-dimensional convolution nerve network; the three-dimensional liver segmentation method is fully automatic and can also prevent under-segmentation and over-segmentation phenomena well; and the accurate liver segmentation result is obtained.

The invention discloses a multi-source path shortest distance-based interactive image segmentation method. The method comprises the steps of S1, calculating a side weight between pixel points in an image according to pixel value features of the image, and converting the image into an undirected weighted graph according to the side weight between the pixel points; S2, marking a plurality of pixel points as mark points of to-be-segmented objects in the to-be-segmented objects of the image, wherein the mark points of the to-be-segmented objects carry identifiers of the to-be-segmented objects; S3, searching for the mark points closest to unmarked pixel points according to the undirected weighted graph for all the unmarked pixel points in the image, thereby converting an image segmentation problem into a multi-source shortest path search problem; and S4, marking the unmarked pixel points with the identifiers of the mark points closest to the unmarked pixel points, obtaining the identifiers of the pixel points in the image, and marking a boundary of the pixel points with different identifiers as a segmentation boundary. According to the method, a more ideal and high-quality image segmentation result can be obtained.

The invention provides a distribution uniformity assessment method based on a watershed algorithm and a minimum spanning tree. The method comprises the steps that an image is subjected to gray processing and median filtering; binarization processing is conducted through an OTSU method; morphological operation is conducted to obtain a feature tag image; segmentation is conducted through the watershed algorithm; an adjoining matrix composed of centroids of segmented regions in the segmented image and distances between the centroids is calculated; the minimum spanning tree is calculated through a Prim algorithm; the distribution uniformity of particles or spots in the image is analyzed based on the minimum spanning tree. According to the method, interference, noise and other ineffective information of the image are filtered out, a tag source is provided for the watershed algorithm, and mistaken segmentation caused by inconsistency of sizes of the particles or the spots and over segmentation caused by the noise are avoided; segmentation based on the watershed algorithm better represents the relation among the particles or the spots and the relation between the particles or the spots and overall distribution; since the Prim algorithm is used for obtaining the minimum spanning tree, the time complexity is low, the efficiency is high, and the assessment of distribution uniformity is more accurate.

The invention discloses an improved method for segmenting cohesive particle objects based on pit point matching, which belongs to the technical field of image processing. The present invention first performs image preprocessing to obtain the contour and concave points of the target to be segmented; then, performs preliminary segmentation based on morphological operations, thereby effectively reducing the number of concave points for matching processing; then, segmentation processing based on local concave point matching , that is, first perform local pit matching processing, and then realize the first segmentation processing based on the matching result; finally, perform the second segmentation processing based on distance transformation processing to solve the technical problem of isolated pit points. The present invention can be used in technical fields such as agricultural planting, segmentation, etc., and its segmentation accuracy is high.