4results about How to "Good segmentation result" patented technology

The application provides a noise label dynamic correction semi-supervised segmentation framework fusing confidence learning, which can efficiently utilize a small amount of high-quality labeled data and a large amount of low-quality noise data to realize accurate and robust three-dimensional medical image segmentation. In the early training stage, the framework mainly uses high-quality data for full supervision learning to guide the model to learn reliable features and segmentation priori; in the middle and late training stage, low-quality noise labels are gradually introduced, noise region recognition is realized through three-dimensional multi-view slice confidence learning, and an uncertainty-guided dynamic soft correction strategy is adopted to dynamically weight and fuse the teacher model prediction results and the original noise labels, so that the noise labels are effectively utilized while avoiding the interference of false labeling, and finally the segmentation accuracy and generalization ability of the model are improved.

This invention relates to a hyperspectral camouflage target detection method based on spatial-spectral feature fusion. It combines deep learning and spatial-spectral feature extraction to establish a 3D network model suitable for spectral feature learning and target spatial localization. Anomaly detection and spatial-spectral constraints are incorporated into the model to improve detection accuracy. Simultaneously, a false positive / false negative removal training method based on spatial receptive domain is proposed to further adjust the network and improve its training effect. The RX-3DSSRF algorithm effectively compensates for the problems of missed detections and false alarms in the traditional RXD algorithm, achieving good segmentation results on low-altitude hyperspectral camouflage target detection data. By removing false positive features of the target and false negative features of the background, the final optimized target detection result is obtained.

The application provides an InSAR deformation anomaly extraction method and system based on multi-modal fusion and vector optimization, relates to the technical field of artificial intelligence and geological disasters, and comprises the following steps: acquiring regional multi-source remote sensing data, calculating surface deformation phase data, terrain relief, slope, vegetation index, water index and soil index, and resampling to obtain multi-source remote sensing full-band data; manually interpreting the InSAR surface deformation anomaly range of the region based on expert knowledge to obtain vector data and binary mask data of the InSAR surface deformation anomaly range; constructing a double-branch multi-modal feature fusion network, extracting InSAR surface deformation anomaly information based on the binary mask data and the multi-source remote sensing full-band data; constructing a dynamic vector optimization network, and optimizing the boundary of the InSAR surface deformation anomaly information based on the multi-source remote sensing full-band data to dynamically convert into a vector result. The application realizes seamless connection from remote sensing images to GIS vectors.

The invention discloses an RGB-T semantic segmentation method and system based on multi-attention guidance and hierarchical fusion, and relates to the technical field of image processing. The system is composed of a double-flow encoder, a discriminative local texture perception unit, a semantic-driven cross-modal fusion unit, a semantic enhancement unit and a multi-scale layered refinement decoder, and efficient fusion and analysis of multi-modal features in a complex traffic scene are achieved. According to the discriminative local texture perception method, saliency features are learned through multi-attention guidance and a self-adaptive gating mechanism, accurate modeling of shallow texture information is focused, and the distinguishing ability of a region of interest and a target edge is improved; according to the semantic-driven cross-modal feature fusion method, efficient aggregation of global contexts is realized through high-level semantic guidance and cross-modal feature interaction, and feature complementarity is enhanced, so that the semantic-driven cross-modal feature fusion method has significant advantages in analysis of small targets, long-distance targets and boundary regions. The decoder adopts a progressive fusion mode, an additional edge detection module does not need to be added, and the overall segmentation precision is improved.