9results about How to "Guaranteed detection rate" patented technology

The invention provides an ultrasonic breast tumor recognition method and device based on prior anatomical knowledge and a medium, and the method specifically comprises the steps: firstly segmenting an original breast ultrasonic image through a segmentation algorithm model, and carrying out the morphological processing of a segmentation result, thereby obtaining a breast region image; then performing channel synthesis on the original ultrasonic image and the breast region image to obtain a fused image, and finally performing breast tumor detection on the fused image by using the optimized target detection algorithm model. The interference of a non-tumor area can be greatly reduced through a prior knowledge mask image and original image fusion preprocessing mode, and the false positive rate of tumor recognition is reduced. Meanwhile, a target detection algorithm is improved by using large-scale convolution and programming gradient information, tumors of different scales and peripheral information can be better obtained, and the tumor detection effect is improved.

The invention discloses a CNN+Transformer remote sensing image target detection method, which is applied to the target detection field. The existing target detection algorithm based on convolutional neural network has the problem of low detection accuracy. The invention first constructs a CNN and Transformer parallel target detection network, improves the effect of multi-scale target detection task by using global information and local information interaction, fuses multi-scale information by using top-down and bottom-up paths in the network, and finally completes feature selection by using coordinate attention CA mechanism, assigns adaptive weight to each channel, and realizes accurate detection and positioning of multi-scale targets in remote sensing images. The method of the invention combines the respective advantages of CNN and Transformer, accurately locates the target area, can highly guarantee the detection rate after training, and realizes accurate detection of remote sensing image targets.

The application relates to a generation method and device of a marked video, computer equipment and a storage medium. The method comprises the following steps: acquiring an object identifier, determining an original subtitle file of a target video requested by the object identifier; mapping the object identifier into an identifier sequence, and determining the subtitle offset types corresponding to each identifier in the identifier sequence; determining the identifiers corresponding to each piece of to-be-offset subtitle in the original subtitle file; acquiring offset subtitles obtained by performing corresponding subtitle offset on the to-be-offset subtitles according to the subtitle offset types to which the identifiers corresponding to the to-be-offset subtitles belong; determining a marked subtitle file according to the multiple offset subtitles; and the marked subtitle file is used for jointly constituting a marked video corresponding to the object identifier together with the target video. The method can realize strong robustness of video watermark embedding in the video field.

The invention discloses a method for detecting and locating a high-speed motion filter rod burst bead. First, a high-speed motion filter rod burst bead image is collected, the image is preprocessed, an edge detection method is used to obtain a preliminary pixel point area of ​​a target, a clustering algorithm is used to obtain a foreground class and a background class area, and an intersection operation is performed with the previously obtained target area to determine the accurate pixel point area of ​​the target, and then the image is annotated, a sample training set, a verification set and a test set are reasonably generated, a deep convolutional neural network including an SPP structure and an SE module is built, the fusion of feature maps of different sizes is completed, and an adaptive weight is given to each channel to achieve accurate detection and positioning of the target. The method of the invention combines edge detection and image clustering to accurately locate the target area, remove interference and facilitate annotation, and adjusts the method for obtaining the target area and the network structure according to different sample types. After the sample is trained, a high detection rate can be guaranteed to achieve accurate positioning of the target.

The application discloses a kind of visual detection methods for motor shaft, including real-time acquisition relevant parameter of motor shaft, construct the CPS data model of motor shaft, real-time association with digital twin model is carried out to physical detection unit, manufacturing process state and data transformation time sequence are digitalized mapping;Based on the real-time state vector that fusion output is based on multi-source data and digital twin model, carry out adaptive imaging parameter regulation and control and multi-station collaborative imaging planning based on deep reinforcement learning;Based on real-time state vector and imaging parameter, image pre-processing is carried out, and using distortion correction algorithm based on physical model compensates dynamic deformation;Combine multi-station image, using multi-scale feature fusion algorithm detects the tiny defect of motor shaft;Hierarchical attention classification network is constructed, and hierarchical classification is carried out, and the graph neural network of multimodal fusion is simultaneously established to diagnose output for the cause of defect, the application improves the adaptability and precision of motor shaft fast detection imaging.

The application discloses a kind of detection methods of engine valve lock block missing loading, it is related to engine assembly detection technical field, including using the inherent gap between two valve lock pieces when normal assembly as fixed leakage passage, by machine tool drive semi-automatic plugging down, plugging rubber ring and valve spring seat are adhered to form detection cavity.By test leakage machine to detection cavity inflation, according to the leakage cross-sectional area and height of normal assembly deduce maximum legal loss boundary, set as leakage upper limit.Inflation pressure monitoring after stabilization, when actual leakage exceeds leakage upper limit, it is judged that there is missing loading defect and NG signal is output, and other cylinders are tested for leakage in turn, and data is synchronously interacted to system.The present application overcomes the limitation of traditional differential pressure leakage relying on completely closed cavity, directly identifies missing loading defect by capturing the pressure drop difference caused by component loss, and realizes automatic quality interception.

The application provides a primer probe combination for detecting HPV16 and HPV18 by using microdroplet digital PCR and an application thereof, and belongs to the technical field of human papilloma virus detection products. The primer probe combination for detecting HPV16 and HPV18 by using microdroplet digital PCR comprises a multi-target primer probe combination for detecting HPV16, and a multi-target primer probe combination for detecting HPV18, wherein the nucleotide sequences of the primer probe combination for detecting HPV16 are shown in SEQ ID NO. 1 to SEQ ID NO. 27, and the nucleotide sequences of the primer probe combination for detecting HPV18 are shown in SEQ ID NO. 28 to SEQ ID NO. 54. The primer probe combination provided by the application has high sensitivity and low detection limit, can accurately detect HPV16 and HPV18 with high specificity and low cost, accurately capture trace amounts of ctDNA in early cervical cancer patient samples, significantly improve the early diagnosis rate, and effectively avoid the missed detection risk of single detection.

The application relates to a marked video generation method and device, computer equipment and a storage medium. The method comprises the following steps: obtaining an object identifier and mapping the object identifier into an identifier sequence; determining the subtitle offset type corresponding to each identifier in the identifier sequence, and determining the clip information corresponding to each identifier; for each identifier, obtaining the subtitle offset segment pointed by the clip information corresponding to the identifier and belonging to the subtitle offset type corresponding to the corresponding identifier; the subtitle offset segment pointed by the clip information is obtained by performing subtitle offset on the original video segment with the same clip information in the original video; and based on the subtitle offset segment, a marked video corresponding to the original video and corresponding to the object identifier is generated. The method can realize strong robustness of video watermark embedding in the video field.

The application relates to a generation method and device of a marked video, computer equipment and a storage medium. The method comprises the following steps: acquiring an object identifier, determining an original subtitle file of a target video requested by the object identifier; mapping the object identifier into an identifier sequence, and determining the subtitle offset types corresponding to each identifier in the identifier sequence; determining the identifiers corresponding to each piece of to-be-offset subtitle in the original subtitle file; acquiring offset subtitles obtained by performing corresponding subtitle offset on the to-be-offset subtitles according to the subtitle offset types to which the identifiers corresponding to the to-be-offset subtitles belong; determining a marked subtitle file according to the multiple offset subtitles; and the marked subtitle file is used for jointly constituting a marked video corresponding to the object identifier together with the target video. The method can realize strong robustness of video watermark embedding in the video field.