28results about How to "Improve object detection performance" patented technology

The application provides a point cloud augmentation method and device, a computer readable storage medium and a terminal device. The point cloud augmentation method comprises: obtaining original point cloud data and at least one image, the original point cloud data and the at least one image being collected for the same target; projecting each original point cloud in the original point cloud data into the at least one image to obtain a plurality of projection points in the at least one image, each projection point corresponding to an original point cloud; selecting at least one adjacent pixel as an extended pixel in a vertical direction of each projection point according to a preset interval; and at least mapping each extended pixel to a three-dimensional space to obtain an augmented point cloud. The application can improve the number of point clouds and the effectiveness of the augmented point cloud.

The present application relates to the radar signal processing neighborhood, specifically to a kind of target detection method based on target space-time stability.The method includes: based on the time-domain signal representation of multiple frames sliding, generate subframe by dynamic matching filter, obtain subframe peak point information, including the energy, distance, doppler information of peak point on each subframe RD spectrum;Based on the spatial signal processing of single snap angle, generate multi-subframe peak point RDA spectrum, obtain the azimuth information of peak point on each subframe RD spectrum, utilize the feature information of each subframe peak point, remove false alarm point using false alarm suppression method based on mahalanobis distance;After false alarm suppression, the result is further removed discrete false alarm point using target track based on space-time stationarity, the method proposed in the present application improves the problem of too many false alarms in the RD spectrum after traditional clutter suppression algorithm;It can effectively reduce false alarm rate while retaining weak target signal, improve target detection capability;It is suitable for multiple system radars, and the application range is wide.

The embodiment of the application relates to an algorithm and a device of a Bayesian classifier of a non-uniform background, which are applied to an underwater active sonar system, the algorithm comprising: obtaining underwater data to be measured and auxiliary data through the active sonar system; the number K of the auxiliary data is greater than 0; modeling classification of the unknown covariance matrix structure into a binary hypothesis testing problem; hypotheses of the binary hypothesis testing problem comprise H i Wherein i=0, 1, H0 is a case that the unknown covariance matrix is a complex conjugate symmetric matrix; H1 is a case that the unknown covariance matrix is a real symmetric matrix; a Bayesian model is set, the Bayesian model comprising a complex inverse Wishart random matrix and a real inverse Wishart random matrix; a classifier for distinguishing the two hypotheses is obtained by using a minimum error probability criterion.

This invention discloses a radar target detection method based on graph node dual-channel feature attention fusion, belonging to the field of radar signal detection technology. The method includes the following steps: Step 1: Divide the received frame radar echo data into graph nodes; Step 2: Extract time-domain amplitude and time-frequency features from the echo time-series data corresponding to each graph node; Step 3: Construct a feature preprocessing subnetwork; Step 4: Construct a node feature fusion subnetwork; Step 5: Construct a signal classification graph neural network; Step 6: Connect the feature preprocessing subnetwork, the node feature fusion subnetwork, and the signal classification graph neural network in series to form a radar target detection neural network; Step 7: Input the test set into the trained radar target detection neural network and output a binary classification result indicating whether the corresponding node is a target or clutter signal. This method can improve the radar's target detection capability in clutter environments.

The present application relates to the field of active sonar target detection, and relates to a kind of adaptive target detection method and system suitable for reverberation edge environment.The method of the present application comprises: selecting the data of unit to be detected as main data, and selecting the received data of multiple distance units on both sides of the unit to be detected as overall auxiliary data;Overall auxiliary data is distributed in the three uniform reverberation areas formed by the left reverberation edge and the right reverberation edge of the unit to be detected, and is divided into three auxiliary data subsets accordingly;Modeling target adaptive detection as a binary hypothesis testing problem including no-target hypothesis and target hypothesis;Obtain the joint probability density function of main data and overall auxiliary data under no-target hypothesis and target hypothesis;Based on the modified two-step generalized likelihood ratio test criterion, the joint probability density function and the probability density function of main data and auxiliary data subsets are processed in turn, and the final detection expression is obtained to realize target adaptive detection.

The invention discloses a severe environment unmanned aerial vehicle aerial photography target detection method based on multispectral iteration enhancement, and belongs to the technical field of computer vision. The method comprises the following steps: firstly, acquiring RGB pictures and infrared pictures in severe environments such as rain and fog, night and the like, and constructing a data set; then, an unmanned aerial vehicle aerial photography target detection model is constructed, and efficient deep fusion of visible light and infrared multispectral features is realized by introducing a novel iterative hierarchical attention and differential enhancement fusion framework; meanwhile, a tail enhancement unit of an HGBlock module in the backbone network is redesigned; then training an unmanned aerial vehicle aerial photography target detection model by using the data set; and finally, using the trained detection model to detect an aerial target of the unmanned aerial vehicle and evaluate the performance of the model. Through a fusion mode of combining interactive alignment, differential enhancement and iterative feedback, the target detection performance and real-time performance of the unmanned aerial vehicle under complex weather and illumination conditions are improved.

This application discloses a few-shot target detection and recognition method based on self-supervised subspace separation, belonging to the field of remote sensing image processing technology. The proposed innovative framework completely isolates the training of base classes and novel classes at three levels. First, a low-rank subspace adapter is proposed for structural separation, achieving network optimization for novel classes without compromising the pre-training performance of base classes. This uses fewer parameters to modulate network components, alleviating the overfitting problem caused by fully fine-tuning under few-shot conditions. Second, an orthogonal subspace extractor is proposed for feature decoupling, adaptively learning the corresponding subspace for each class and extracting decoupled representations, enhancing the separability between classes. Third, a balanced classifier is designed for loss balancing, preventing the final prediction result from being overly biased towards the background or base class. The framework proposed in this invention has significant advantages in few-shot target detection and recognition, showing significant improvements in both base and novel classes.

The application discloses a target detection method based on motion and event information decoupling, aiming at the problem of coupling of appearance information and motion information in an event stream, proposes an event representation method for decoupling motion and appearance, and designs a double-flow detection network and an event motion guided attention module based on decoupled input, uses motion features to enhance appearance features, and thus greatly improves target detection performance.

The application provides an open-vocabulary aerial image target detection method based on collaborative quality perception, constructs a labeled basic category dataset and an unlabeled new category dataset of aerial images, constructs an SQAPN target detection model, the target detection model comprises a backbone network and an RPN network with a spatial alignment perception module, an alignment consistency loss function is introduced in the training process of the target detection model to supervise the training of the spatial alignment perception module, a confidence modulation module is introduced in the inference stage to obtain a comprehensive quality score, the target detection model is trained by using the dataset to obtain a trained target detection model, in the inference stage, the aerial image to be processed is input into the trained target detection model, and a comprehensive quality score and a candidate box are output, candidate box screening is completed through non-maximum suppression (NMS), and finally, the detection result is output. The application can effectively improve the open-vocabulary aerial image target detection precision and robustness.

This invention discloses a lightweight star catalog target detection method and system. The method includes: constructing a student model, which employs a lightweight feature extractor and a Transformer decoder with width and depth pruning; constructing a teacher model, which employs an un-lightweight feature extractor and a Transformer decoder without width and depth pruning; adjusting the parameters of the teacher and student models, calculating the value of the loss function, stopping the iteration when the value of the loss function is minimized, and obtaining trained teacher and student models; and using the trained student model to perform lightweight star catalog target detection. The advantages of this invention are: lightweight, low computational complexity, and the ability to achieve 3D position detection of star catalog targets.

The application discloses a flood discharge detection model training method and device, equipment and a medium, the method comprises the following steps: taking the video image data of the pre-collected reservoir spillway as a first training sample set, and performing sample enhancement on the first training sample set according to a preset sample enhancement strategy to obtain a second training sample set; wherein the sample enhancement strategy comprises one or more combinations of the following: an independent enhancement strategy, a combined enhancement strategy or an inlay enhancement strategy; training a pre-constructed initial flood discharge detection model according to the second training sample set to obtain a final flood discharge detection model; wherein the initial flood discharge detection model is an improved YOLOv8 model obtained by modifying a flood discharge convolution feature extraction module and updating a feature fusion module. The application can improve the calculation efficiency and target detection accuracy of the flood discharge detection model in a small sample data scene.

The application relates to the field of small sample target detection, in particular to a two-stage small sample target detection method based on an optimized CBAM attention mechanism, and comprises the following steps: training a two-stage target detection network Faster-RCNN by using a base class data set to obtain a base class detection model; freezing parameters of a feature extraction backbone network in the base class detection model; optimizing a CBAM attention mechanism module; placing the optimized CBAM attention module in the feature extraction backbone network to construct a detection network, then inputting a new class small sample data set with a small amount of labeled information to fine-tune parameters of a detection head part of the detection network; and inputting a to-be-detected data set into the detection network to obtain a detection result. Compared with the prior art, the application has the advantages of inhibiting the influence of unimportant spatial information, improving the attention degree of important spatial information, enhancing the sensitivity to different scale features, and having strong generalization ability and robustness and the like.

The application discloses a target detection method based on multi-path component reconstruction residual error, comprising the following steps: step 1: based on the double auto-encoder training algorithm of environmental clutter, learning the clutter structure features in the multi-path channel and reconstructing the multi-path echo; step 2: synthesizing the reconstructed multi-path echo obtained in step 1 into a reconstructed image, based on the target pre-detection algorithm of the reconstruction residual error, comparing the difference between the original image and the reconstructed image, and used for distinguishing whether the to-be-detected region contains target echo. The application fully explores the multi-path characteristics of the clutter, and realizes the weak and small target detection under the condition of no target sample through the multi-path echo reconstruction residual error.

The invention provides a BEV target detection method based on a 4D millimeter wave radar point cloud, and belongs to the field of automatic driving perception. According to the method, a detection model composed of a double-branch interactive feature coding network, an RCS-based radar BEV feature encoder and a 3D detection head is designed for the problem of sparse point clouds of millimeter-wave radars. The method mainly comprises the following steps: firstly, preprocessing an original radar point cloud, calculating centralization features and average centralization features, and outputting enhanced point features through feature splicing, local dimension raising and global maximum pooling operation; then the features are sent to a double-branch interactive feature coding network, the features are extracted by using a point-based encoder and a Transform-based encoder, and feature interaction between double branches is realized through an injection module and an extraction module; through a cylinder feature coding network, radar points are mapped and aggregated into BEV features according to RCS information; and finally, multi-scale features are extracted through an SECOND network, and the 3D frame size, category and direction angle of the target are output by a detection head. According to the invention, through double-branch feature interaction and RCS auxiliary coding, the feature expression capability of the sparse point cloud is effectively enhanced, and the target detection performance is improved.

The present application relates to the technical field of SAR image processing and self-supervised learning. A SAR image self-supervised pre-training method based on a mask autoencoder. In view of the problem that existing SAR target detection relies on natural image pre-training weights and there is a significant domain gap, resulting in low detection accuracy in a small sample scene, a multi-source SAR pre-training dataset is constructed, an asymmetric encoding and decoding architecture is adopted, ResNet50 is used as a feature extraction encoder to adapt to the local scattering characteristics of SAR, a lightweight convolutional decoder is constructed, a Gamma distribution speckle noise modeling mechanism is introduced, the input image is divided into non-overlapping image blocks and a random mask matrix is generated, the encoder only encodes the visible area, the decoder maps the latent representation back to the image space to complete the reconstruction, and the learning rate scheduling and gradient clipping mechanisms are combined to complete unsupervised pre-training, and the encoder weight is extracted and migrated to a downstream rotating target detection model to complete small sample fine tuning.

The invention discloses a radar communication integrated radio frequency signal generation device. In the device, a data interface unit is used for receiving data to be transmitted; the data grouping unit is used for grouping data; the pulse control unit maps each data combination of the pulse mapping group into K pulses selected from a pulse set for data transmission according to a one-to-one mapping relationship, maps each data combination of the transmission sequence group into a certain serial transmission sequence of the K pulses, and outputs the serial transmission sequence to the pulse modulation unit; the pulse modulation unit loads the data of the data modulation group to the K serial pulses according to a mapping modulation mode to complete pulse modulation; and the nonlinear unit generates a nonlinear frequency modulation signal with variable carrier frequency and phase and outputs the nonlinear frequency modulation signal to the power amplifier unit. According to the technical scheme disclosed by the invention, the data transmission capability and the target detection capability of the radar communication integrated signal are improved.

The application discloses a kind of electrical secondary paper component detection method, equipment and medium based on structure perception mechanism, belong to paper component detection technical field, including acquisition electrical secondary paper, uniform gridding and pretreatment are carried out to electrical secondary paper, obtain the pretreated electrical secondary paper;Electrical secondary paper component detection model is constructed, input is the pretreated electrical secondary paper, output is the class probability, confidence and boundary box parameter of each target;In the training stage of electrical secondary paper component detection model, the geometric center of all symbols on electrical secondary paper is node, and symbol structure relationship graph is constructed according to alignment, adjacency and electrical connection rule, and loss function is constructed.The present application significantly reduces the false detection and missed detection problem, realizes high-precision identification;It has faster detection efficiency, adapts to aging paper, dense layout and other complex scenes, while having smaller model size and higher deployment efficiency, low cost and strong practicability.

This invention relates to the field of machine vision technology, specifically disclosing a multi-target tracking method with reference point prior position embedding and adaptive updating. It constructs a multi-target tracking network for multi-target tracking, within which a prior position generation network based on target queries is designed. This prior position generation network generates target queries with explicit prior position information. This prior position information facilitates effective keypoint sampling, solving the problem of lacking prior position information for target query reference points, thereby improving target detection performance. Furthermore, a tracking reference point prediction network based on tracking query reference points is designed. This tracking reference point prediction network generates new tracking query reference points for tracking queries, effectively reducing the deviation between the tracking reference point position and the target center position, achieving accurate positioning of the tracking reference point, and thus improving target tracking performance.

The invention provides a radar-based adaptive polarization filtering method and system, and relates to the technical field of radar signal processing. The method comprises the following steps: acquiring main channel discrete data and auxiliary channel discrete data; processing the main channel discrete data by a preset weight coefficient to obtain main channel polarization data; according to the auxiliary channel discrete data and the main channel polarization data, obtaining a cancellation weight coefficient of the auxiliary channel; and performing polarization cancellation on the main channel polarization data according to the cancellation weight coefficient of the auxiliary channel and the auxiliary channel discrete data to obtain cancelled main channel signal data. According to the method, weighting coefficients of two channels are calculated through orthogonal polarization channel signals, clutter interference of a main channel is suppressed in the mode that clutters in the main channel are offset through an auxiliary channel, and therefore the signal-to-noise ratio is increased, the receiving quality of useful signals is effectively improved, and then the target detection capacity is enhanced. In addition, the method has the advantages of automatically compensating the amplitude-phase unevenness between the channels and being easy in engineering implementation.

A small target detection method, system, device and medium based on a local attention feature correlation mechanism, the method comprising: data preprocessing, model construction, model training, small target detection; the system, device and medium are used to realize a small target detection method based on a local attention feature correlation mechanism; the application extracts spatial features and semantic features through a residual network, performs feature fusion through a feature pyramid mechanism, reconstructs features based on a local attention feature correlation mechanism, trains a model using a Hungarian matching algorithm, obtains an optimal matching model suitable for a data set, can ensure high accuracy with fewer iteration times, and has the characteristics of low network operation complexity, low training cost, easy model migration, and high model detection performance.

The present application relates to the field of agricultural machinery safety perception and intelligent early warning technology, and particularly relates to a silage harvester living body detection and early warning method fusing thermal infrared and visible light, wherein a thermal infrared camera and a visible light camera are installed on the roof of the harvester, calibration parameters and spatial mapping relationships are obtained in advance, dual-mode images of the front work area are collected in real time, pre-stored parameters are called to perform synchronous matching and spatial registration, the dual-mode image pair is input into an RGBT-YOLO network based on the improvement of YOLOv11, temperature features are extracted through the thermal infrared branch, texture features are extracted through the visible light branch, and the class, position and confidence of the living body target are output after cross-modal fusion and lightweight detection, when a person or an animal enters a preset dangerous area in front of the header and continuously meets the alarm conditions, an audible and visual alarm device is driven to send an early warning signal, and the problems of insufficient consideration of dual-mode image registration, feature-level fusion detection and early warning control closed loop in the working scene of the dangerous area in front of the silage harvester at the present stage are solved.

This invention relates to a dual-driven target detection method combining saliency attention and unsupervised image augmentation. The aim is to improve the accuracy and stability of target detection models in complex and degraded environments by introducing salient region information and a target detection feedback mechanism. This method falls under the fields of computer vision and deep learning. It constructs an unsupervised image augmentation network to enhance the input image and guides the network to focus on optimizing target-related regions in the image through a dual saliency attention mechanism. Simultaneously, the target detection model is embedded in the overall training process, and the detection loss provides inverse constraints and optimizations to the image augmentation process. By combining unsupervised image augmentation and target detection tasks, this invention achieves adaptive optimization of the augmentation results for the detection task, avoiding the problem of traditional augmentation methods focusing only on visual quality while neglecting downstream tasks. It does not rely on paired high-quality reference images, exhibits good generalization ability and robustness, and is suitable for target detection applications in complex underwater visual environments.

This invention relates to an adaptive perception and feature recovery method for aircraft wiring harness assembly target detection in complex assembly environments, encompassing computer vision and aircraft manufacturing assembly technologies. It addresses the issue of poor target detection performance caused by feature degradation in complex assembly environments, where existing target detection algorithms cannot guarantee real-time performance. The invention constructs a perception-recovery coupled target detection network structure by introducing an environmental interference perception auxiliary task into the target detection network and combining spatial attention and channel statistical modeling mechanisms. The target detection network includes an environmental interference perception auxiliary classification branch unit, a spatial attention unit, sub-channel units, a backbone network, a neck unit, and a detection head unit; thereby achieving dynamic perception and effective compensation for degraded features in complex assembly environments during the detection process. This invention is primarily used for environmental interference category prediction and wiring harness assembly target detection.

The application provides a target detection method and device, electronic equipment and machine readable storage medium. The method comprises: voxelizing input point cloud data, and performing voxel feature extraction to obtain voxel features of the input point cloud data; according to the voxel features, classifying non-empty voxels corresponding to the input point cloud data into foreground and background, and determining the offset of each foreground voxel relative to a target center point; according to the offset of each foreground voxel relative to the target center point, clustering the foreground voxels to obtain a clustered target cluster; and according to the target cluster, generating a target detection frame by using a cluster-based target detection structure. The method can improve target detection efficiency and improve target detection performance.

The invention discloses a narrow pulse interference suppression method based on energy stability judgment and spectrum correlation, and the method comprises the steps: dividing radar intermediate frequency modulo data into a plurality of data intervals according to an amplitude continuous over-threshold criterion, and carrying out the narrow pulse suppression of the data intervals meeting the narrow pulse amplitude and width judgment criterion, a data interval which only meets amplitude and does not meet width judgment is divided into echo signal subintervals and interference signal subintervals, correlation coefficients of signal frequency spectrums of the echo signal subintervals and local signal frequency spectrums are calculated, each interference signal subinterval is traversed, correlation coefficients of the frequency spectrums and the sum of the signal frequency spectrums of the echo signal subintervals and the local signal frequency spectrums are calculated, and the frequency spectrums of the interference signal subintervals are calculated. And performing narrow pulse interference detection and suppression on the interference signal subintervals according to a correlation coefficient judgment criterion, and repeating the process until all data intervals are processed. According to the invention, detection and suppression of narrow pulse interference in a high signal-to-noise ratio echo background are realized, and the target detection performance of the radar in an interference environment is improved.

The application discloses a kind of underwater acoustic signal's space-time stabilization method, system and storage medium, output space-time signal energy spectrum enters wideband stabilization module, judge its output as reverberation background part input to reverberation stabilization module, judge its output as noise background part input to narrowband stabilization module, output after processing is stabilized after space-time energy chart, finally through energy detection obtains the azimuth, distance and intensity information of target.Data verification is carried out by sea trial, the application can realize space-time signal stabilization in underwater long-distance target detection, solve the interference problem of reverberation, high-power white noise and colored noise, realize the effective detection of long-distance target echo.

The application is suitable for the field of radar technology, and provides a compensation method and device for echo power, a radar and a storage medium. The compensation method comprises the following steps: when a radar detects a target, determining a current echo power of a compensation device according to a distance between the radar and the compensation device, wherein the compensation device is located in a sensing range of the radar; subtracting the current echo power of the compensation device from a reference echo power of the compensation device to obtain a change value of the echo power of the compensation device in this time detection; and if the change value of the echo power of the compensation device in this time detection exceeds a preset range, compensating a current echo power of the radar according to the change value of the echo power of the compensation device in this time detection. Through the application, the interference of factors such as temperature drift, rain and snow attenuation, device aging and the like on the echo power of the radar can be reduced, and the target detection performance of the radar is improved.