5results about How to "Implement object detection" patented technology

The invention designs a zero sample image target detection method based on deep learning, and belongs to the field of image target detection based on a large model. The visual language model designed by the invention comprises a RO-Yolo-Backbone, an HWD-RepVL-PAN, an MCJ-Text Control Head and a regression bounding box target detection module, the feature extraction capability is enhanced by sharing convolution kernel parameters and optimizing a receptive field range, down-sampling texture loss is reduced by utilizing wavelet transform, intra-class differences are weakened and inter-class differences are enhanced by introducing a multi-distance formula, and the robustness of the target detection model is improved. The objective of the invention is to effectively improve the zero sample image target detection capability in the big data era.

This application discloses a method, apparatus, device, and medium for transferring a perception model, which facilitates the transfer from the source domain to the target domain in point cloud perception tasks, enables the reuse of point cloud data from the original perception model, and improves the generalization ability of the perception model for different application scenarios. The method for transferring a perception model provided in this application includes: transferring the point cloud data of the original perception model to the target perception model according to the application scenario information of the target perception model obtained, thereby obtaining a truth database of the target perception model, wherein the truth database includes point cloud and label information of the perceived target; and training the model based on the truth database of the target perception model to obtain the target perception model.

The application discloses a kind of robust DOA estimation methods based on sparse bayesian learning, belong to array signal processing field, the method of this application first introduces position error parameter, and determines the prior distribution of grid error and element position error, secondly with the aid of sparse bayesian learning model, establish joint probability density distribution function, finally with the aid of maximum expectation algorithm to each unknown parameter is iterated, obtains spatial spectrum diagram, estimates the direction of incident signal.This application method can better azimuth estimation accuracy and azimuth resolution, still have good performance under the condition of less snapshot, low signal-to-noise ratio, and the application method has good robustness to the array system that exists element position error, has greater engineering application value.

Embodiments of the present application disclose image detection methods, model training methods and devices, equipment, storage media and products. The image detection method comprises: obtaining a to-be-detected image and a query text, on the one hand, performing open-vocabulary object detection on the to-be-detected image based on the query text to obtain a set of object position indication information, and on the other hand, extracting global features of the to-be-detected image; then, according to the obtained global features and the set of object position indication information, local features of the to-be-detected image are extracted, and according to the global features, the local features and the query text, a target detection result of the query text in the to-be-detected image is obtained. It can be seen that by decoupling low-level positioning (obtaining the set of object position indication information) and high-level understanding (extracting global features), and performing open-vocabulary object detection on the to-be-detected image in the low-level positioning process, the object position indication information in the set of object position indication information can not be limited to fixed categories, thereby realizing target detection of the image.

The invention provides a radar target high-dimensional signal detection and estimation method, and relates to the technical field of radar detection, and the method comprises the steps: determining the type of a to-be-estimated high-dimensional signal parameter of a radar target according to a preset precise distance evolution model; detecting the three-dimensional detection spectrum of the to-be-estimated high-dimensional signal parameter according to a pre-calculated first threshold, and determining a region unit containing a radar target in the three-dimensional detection spectrum; and according to a preset second threshold, screening the connected regions of the region unit where the local maximum value of the detection data is located to obtain reference detection data, and calculating the reference detection data to obtain an accurate estimation value of the to-be-estimated high-dimensional signal parameter. According to the scheme, target detection in a high-dimensional signal parameter space can be realized, and a more accurate high-dimensional signal parameter estimation value of a radar target can be obtained.