87results about How to "Improve object detection accuracy" patented technology

The invention discloses a power transmission line inspection image denoising method and system, and the method comprises the following steps: S1, obtaining an original image of an insulator, adding noise to the original image, and constructing an insulator noise image data set; s2, improvement is carried out based on an SADNet denoising network model, a Mix module, a CSM module and a CCAM module are introduced, and an SADNet-S denoising network model is constructed; s3, training the SADNet-S denoising network model by using the insulator noise image data set to obtain an optimal training weight; and S4, loading the optimal training weight into the SADNet-S denoising network model, and inputting the noise image of the insulator to be detected into the SADNet-S denoising network model to obtain a denoised insulator image. The invention provides an improved SADNet-S denoising network model based on multi-scale feature extraction, dynamic adaptive filtering and an attention mechanism, and by adopting the SADNet-S denoising network model, the strong generalization and robustness of the SADNet-S denoising network model are brought into full play, so that efficient image denoising is realized, and the target detection precision is remarkably improved.

The invention discloses a remote sensing image target detection method based on an accelerated projection recurrent neural network. The method comprises the following steps: acquiring an original remote sensing image and calculating a remote sensing image autocorrelation matrix; constructing a linear constraint optimization mathematical model of filtering output based on the remote sensing image autocorrelation matrix, and obtaining a linear equation mathematical model through conversion; and solving the linear equation mathematical model by adopting an accelerated projection recurrent neural network algorithm, carrying out vector decomposition on a solving result to obtain a filtering coefficient vector, obtaining a remote sensing image after filtering output based on the filtering coefficient vector, and completing remote sensing image target detection. According to the remote sensing image target detection method based on the accelerated projection recurrent neural network, the convergence speed is higher, the calculation time is shorter, the image threshold classification capability is higher and the target detection precision is higher when the optimization problem is solved.

The invention relates to an underwater image detection system and method based on a YOLOv8s model, and the system comprises an underwater image collection and preprocessing subsystem which is used for collecting underwater image data and carrying out the preprocessing; the target detection subsystem is used for carrying out target detection by adopting an improved YOLOv8s model, and the improved YOLOv8s model is used for obtaining a feature map by adopting a mode of combining a denoising mechanism and a dynamic adjustment receptive field mechanism based on the preprocessed underwater image data, carrying out feature enhancement by adopting a dual attention mechanism based on the feature map, and carrying out target detection by adopting an improved YOLOv8s model; performing feature fusion and detection to obtain a target detection result; the performance monitoring and evaluation subsystem is used for monitoring and evaluating the target detection result; and the detection result display and output subsystem is used for outputting and displaying the target detection result. Compared with the prior art, the method has the advantages of improving the depth and precision of feature extraction, improving the underwater image detection performance and the like.

The invention relates to an automobile automatic obstacle avoidance system based on real-time 3D target detection, the system comprises a point cloud data collection module, an image data collection module, a LoGoNet network and an early warning and feedback module, and the LoGoNet network is used for realizing real-time target detection of an obstacle, detecting whether there is an obstacle, and judging the category of the obstacle. The system is a local-to-global multi-modal data fusion network, can carry out real-time 3D target detection automobile automatic obstacle avoidance, solves the inherent limitation of a single mode, carries out local-to-global multi-modal fusion by using the complementary characteristics of an image and a laser radar, provides a more complete three-dimensional environment perception capability through multi-source fusion, and improves the real-time 3D target detection efficiency. And the vehicle is helped to better perceive the surrounding environment.

The invention discloses an unmanned aerial vehicle target detection method and device based on scale adaptive recognition and a medium, and relates to the field of machine learning, and the method comprises the steps: carrying out the data collection based on an unmanned aerial vehicle, and obtaining video data corresponding to a target scene; analyzing based on the video data to obtain image data of a continuous sequence, and labeling the image data to generate a training data set; performing data enhancement on the image data in the training data set; and training the convolutional neural network through the training data set after data enhancement, and performing target detection through the trained convolutional neural network. The image is used as input, and then the feature extraction fusion part is used for feature extraction. A multi-scale convolution strategy is adopted, convolution operations of various different sizes are specifically covered, and feature fusion is carried out on feature maps of different scales to obtain a feature combination.

The invention relates to the technical field of ship navigation, and discloses a ship overwater multi-target detection method comprising the following steps: S1, obtaining a real-time original image of a water area where a ship is located; s2, improving the resolution of the original image by using a super-resolution reconstruction algorithm, and generating a high-definition image; s3, inputting the high-definition image into a pre-trained Faster R-CNN model, and carrying out target detection; s4, outputting a position coordinate, a category label and a confidence score of the target through the Faster R-CNN model; s5, starting a multi-target tracking algorithm, and continuously monitoring the motion trail; s6, calculating MCPA and MTCPA according to the motion trail, and calculating a collision risk through a collision risk assessment algorithm; and S7, when the MCPA and the MTCPA of any target are lower than a safety threshold, sending out an early warning signal to indicate to take a collision avoidance measure. According to the method, the high-definition image is generated through the super-resolution reconstruction algorithm, the Faster R-CNN model is utilized, the water target is rapidly and accurately detected, the detection precision and generalization ability are remarkably improved, and navigation safety is guaranteed.

The invention discloses a remote sensing target detection method based on dynamic adaptive query, and the method comprises the following steps: obtaining a target detection data set, and carrying out the preprocessing of the target detection data set; the method comprises the following steps of: constructing an initial network structure which is formed by combining a ResNet50 convolutional neural network and a Transform self-attention mechanism; meanwhile, dynamic self-adaptive position query is adopted to replace original position query; training the initial network structure by using the preprocessed target detection data set to obtain a trained target detection network model; and identifying a target in the remote sensing image by using the target detection network model. The method not only improves the target detection precision, but also can improve the model convergence speed.

The invention discloses a traffic sign detection method and device based on YOLOv5 and a medium, belongs to the technical field of traffic sign detection, and aims to solve the technical problem of how to improve the small target detection precision, reduce the omission ratio and further improve the detection performance of traffic signs. According to the technical scheme, a prior anchor point frame is optimized by using a genetic algorithm and a K-means algorithm, and the detection accuracy of a small target is enhanced; a Bi-FPN structure is introduced to realize feature fusion of semantic and position information, and the representation capability of the network is improved; by integrating an attention mechanism GAM, the anti-interference performance and the feature extraction capability of the network in a complex environment are enhanced; sIOUloss is adopted as a frame regression loss function, so that the positioning accuracy is improved.

The invention discloses an optical remote sensing image saliency target detection model and detection method, and belongs to the technical field of target detection. The saliency target detection model comprises a PVT backbone network module, an edge information extraction and fusion module BG, a feature enhancement module HAM, two space attention modules, a feature interaction module KTM and a feature fusion module. According to the invention, by introducing an edge detection module (BG) and a feature enhancement module (HAM), the target detection precision under a complex background is effectively improved. Compared with the existing CNN-based method, the method provided by the invention can better process targets with different scales and direction changes, reduces the probability of missing detection and false detection, and enables saliency target detection to be more complete and accurate.

The invention discloses a classroom behavior detection method based on dimension diffusion perception adaptive fusion, and the method comprises the steps: replacing a part of C2f layer of a Backbone network in a YOLOv8 model with parallelization plaque perception attention PPA, constructing a dimension perception fusion diffusion pyramid network DAIDFPN through employing a dimension perception selective fusion module DASI, and replacing a Neck feature fusion network in the YOLOv8 model. Therefore, an improved YOLOv8 model is obtained, and classroom behavior detection is carried out on the classroom image by using the improved YOLOv8 model. Compared with other methods, the classroom behavior detection method based on dimension diffusion perception adaptive fusion does not need to depend on a large number of data annotation data and computing resources, has the advantages of being small in computing overhead, high in real-time performance and high in detection precision, is low in cost in smart classroom deployment and has good practical application value.

The invention discloses a target detection method based on an improved yolov8 algorithm, and relates to the technical field of computer vision and deep learning, and the method comprises the steps: collecting picture data according to a target object needing to be detected, marking a picture data set through Label, dividing a training set, a verification set and a test set in the data set according to the proportion of 7: 1: 2, and obtaining a training set, a verification set and a test set; completing the manufacturing of a data set of the target object; secondly, a target detection model is constructed based on a YOLOv8 algorithm, a backbone layer, a head layer and a loss function part of the YOLOv8 algorithm are improved, a lightweight adaptive weight down-sampling module is added to the backbone layer, a P2 detection head is added to the head layer, and a new loss function is designed in combination with the thoughts of WiseIoU, InnerIoU and MPDIOU; and then, obtaining a final prediction result by using the trained target detection and recognition model. And finally, comparing and analyzing the advantages of the improved algorithm in combination with a final result. In a word, target detection based on the improved yolov8 algorithm can be realized, and meanwhile, the precision of target detection is greatly improved.

The invention relates to a cervical vertebra MRI (Magnetic Resonance Imaging) image degenerative region positioning detection method based on deep learning. The method comprises the steps that firstly, an original cervical vertebra MRI image is acquired and preprocessed; then, a degenerative region positioning model is constructed based on a TOOD network, and the degenerative region positioning model comprises a feature extraction network, a multi-scale self-attention mechanism feature fusion network and a detection head network; then, training the degenerative region positioning model based on the preprocessed original cervical vertebra MRI image; and finally, inputting a cervical vertebra MRI image to be predicted into the trained degenerative region positioning model, and outputting a degenerative region positioning detection result. The deep learning model is used for detecting the cervical intervertebral disc, degeneration grading detection can be directly carried out on the intervertebral disc according to the T2 weighted image of the MRI, and the positioning detection efficiency is effectively improved.

The invention relates to the technical field of image segmentation, and particularly discloses a bridge crack segmentation method based on YOLOv8n-seg, which comprises the following steps: acquiring a bridge crack image, labeling the acquired bridge crack image and making a data set, respectively adding a C2fDCNv2 module and a CBAM attention mechanism into a backbone network and a detection head of a YOLOv8n-seg model to obtain an improved YOLOv8n-seg model, and segmenting the bridge crack by using the improved YOLOv8n-seg model. And under the supervision of a loss function, training the improved YOLOv8n-seg model by using the data set to obtain a bridge crack segmentation model, re-collecting a bridge crack image, and inputting the bridge crack image into the bridge crack segmentation model to obtain a segmentation result which is an image marking all bridge cracks. According to the invention, the detection precision of small targets such as bridge cracks is high, the manual labor is reduced, the cost is low, and the bridge cracks can be efficiently and accurately detected.

The invention discloses a PCB surface defect detection method based on improved YOLOv8, and belongs to the technical field of deep learning and quality detection, and the method comprises the following steps: constructing an improved YOLOv8 model based on an RFCBAMCConv module, an ScConv module and a VoVGSCSPC module; and inputting the PCB into the improved YOLOv8 model to obtain a PCB surface defect detection result.

The invention provides a target detection method and device, equipment and a storage medium, and relates to the technical field of target detection. The method comprises the following steps: mapping each collected image in a sample image set to a Riemannian space to obtain a Riemannian mean value corresponding to each type of road target; and taking the sample image set and each Riemannian mean value as training data, inputting the training data into a convolutional neural network for training, and taking the trained convolutional neural network as a target detection model. In the real-time image processing process, inputting the real-time image into the backbone network after weighted training in the target detection model to obtain target feature information of the real-time image, and obtaining the target feature information of the real-time image based on the target feature information; and the head network outputs the type and position information used for indicating each target in the real-time image after the soft non-maximum suppression processing based on the Riemannian distance. The feature extraction capability of the target features is improved by weighting the convolution kernel in the backbone network and improving soft non-maximum suppression through the Riemannian distance, the target detection precision is improved, and meanwhile, the detection time is not increased.

The present invention belongs to the field of target detection technology, and specifically is a target detection method applied to smart construction site security, the method comprising the following steps: constructing a YOLOV8 target detection original model; using historical images collected on the construction site to train the YOLOV8 target detection original model to obtain a trained target detection model; inputting the real-time to-be-detected images collected on the construction site into the trained target detection model, detecting target violations on the construction site in real time, and classifying and locating the detected behaviors, while triggering an early warning system and outputting violation images. The present invention also discloses a target detection system applied to smart construction site security. The target detection model provided by the present invention is applied to a smart construction site, and can monitor various behaviors on the construction site in real time, discover potential safety hazards in a timely manner, and issue alarms or take corresponding preventive measures in a timely manner. This method greatly improves the efficiency of construction site safety management.

The invention discloses a visual perception and trajectory restoration method, system and device for chicken motion analysis and anomaly detection in a large cage farm and a storage medium, and relates to the technical field of video monitoring and behavior analysis. Carrying out fine feature extraction by adopting a space and channel attention mechanism; fine features are combined with Kalman filtering and a Hungary algorithm, chicken individual identities are continuously tracked and adjusted through time sequence prediction and space matching, and a target bounding box is output; adjusting the individual identity of the chicken according to tracking, performing smooth repair on interrupted and shielded trajectory segments through spline interpolation and Kalman filtering, and performing reasonable trajectory recovery by adopting biological kinematics constraint; based on the target bounding box, a frequency domain feature analysis mechanism and a deep learning coding technology are introduced, a behavior feature vector is generated, and health early warning is triggered according to the abnormal confidence coefficient; according to the method, the chicken monitoring precision and the anomaly detection reliability are improved.

The invention is suitable for the technical field of visual language models, and provides a distillation learning method of an open vocabulary target detection model, which comprises the following steps: based on a pre-trained candidate frame extraction model, obtaining a pseudo tag of a to-be-detected picture, cutting the to-be-detected picture according to a pseudo tag region, obtaining a pseudo tag region image, and obtaining an open vocabulary target detection model; the pseudo label is a candidate frame which is not overlapped with the label frame of the known class; based on a CLIP visual encoder, obtaining visual features of the pseudo label area image; on the basis of a CLIP text encoder, a text category label generation method is adopted, and text features of the pseudo label area image are obtained; and based on the visual features and the text features, performing knowledge distillation learning on the target detection model by adopting a bisymmetric distillation method, so that the target detection model learns the visual features of the CLIP visual encoder and the text features of the CLIP text encoder. And the generalization ability of the target detection model is improved.

The application provides a multi-modal target detection method based on super-resolution assistance, and the implementation steps are as follows: obtaining a training sample set and a test sample set; building a multi-modal target detection network model based on super-resolution assistance; iteratively training the multi-modal target detection network model based on super-resolution assistance; and obtaining a target detection result. The multi-modal fusion module is provided with a symmetrical double-branch structure, realizes efficient fusion of RGB and IR images at the input end, retains color integrity and complementary information of thermal radiation, significantly improves feature discrimination, and effectively improves detection accuracy; the super-resolution assistance branch serves as an internal branch, directly optimizes feature representation of the backbone network through a reconstruction loss, thereby significantly enhancing the expression capability of the network for small targets and fine features, and meanwhile, the super-resolution assistance branch does not participate in the detection process of the test sample, realizes zero additional calculation overhead in the reasoning stage, and improves the detection efficiency while improving the target detection accuracy.

The embodiments of the present application disclose a target detection method, device, electronic device and storage medium, which relate to the field of smart home technology. The method includes: obtaining an image to be detected; inputting the image to be detected into a pre-trained network model, the network model is used to fuse the multi-scale traditional features and multi-scale depth features of the image to be detected according to the corresponding scale, and output the detection result of the target to be detected in the image to be detected based on the fused multi-scale traditional features and multi-scale depth features; and obtaining the detection result of the target to be detected output by the network model. The embodiments of the present application introduce multi-scale traditional features in the network model to guide attention, which can improve the target detection accuracy of the network model in the image to be detected.

The invention discloses a textile defect detection method which comprises the following steps: step A, image acquisition: performing real-time and / or timed acquisition on a textile part of a textile needle by virtue of a visual sensing system to acquire images; step B, constructing a feature extraction network: based on a YOLOv5 backbone network, introducing a multi-branch discrete cosine attention mechanism module (MDCA) to form a new backbone network SCNet, and drawing an output feature map of the new backbone network SCNet according to the acquired image; and step C, adopting an MUPool pooling method: a new backbone network SCNet outputs a feature map, important node features are acquired and screened through multi-view map convolution, a cascade structure and a rear-end fusion module, and finally a multi-scale feature map is generated, so that the problems of false detection and missing detection caused by oil stains, black oil needles, bright oil needles and dirty yarns can be solved while relatively high detection precision is ensured.

A method for target detection of large-scale aerial remote sensing images belongs to the technical field of target detection. The present invention aims at the problem that large-scale aerial remote sensing images may lose context information due to image segmentation. The method comprises the following steps: determining the name of the original image; configuring a sub-image name for a sub-image; retrieving the corresponding current original remote sensing image from the original remote sensing image set according to the sub-image name; extracting features from the current sub-image to be detected using a local feature extractor to obtain a set of multi-scale sub-image feature maps; downsampling the current original remote sensing image and then extracting features using a global feature extractor to obtain a set of multi-scale original image feature maps; obtaining a fused feature map using a feature pyramid network with a global-local coupling mechanism; respectively obtaining target prediction results and filtered global prediction results; and fusing the fused target prediction results and filtered global prediction results to obtain a detected target. The present invention is used for target detection.

The application discloses a kind of training and target detection method and device of target detection model, belong to the field of automatic driving, the method includes: according to the sample multi-view image in the sample scene where the image acquisition equipment is collected in the sample scene where the automatic driving vehicle is located, determine sample image dense feature;According to the sample point cloud data in the sample scene where the automatic driving vehicle is located that remote sensing detection equipment is collected, determine sample image sparse feature;Sample image dense feature and sample image sparse feature are fused, and sample fusion image feature is obtained;According to sample fusion image feature, target detection model is trained.The application solves the problem that feature is not aligned, enhances the feature fusion effect, and then improves the accuracy of subsequent target detection result.

The application discloses an underwater target detection encoder, a detection system and a method, the encoder comprising an input projection layer, a global semantic modeling unit, a first-stage feature fusion unit and a second-stage feature fusion unit; wherein the input projection layer is used for channel mapping of multi-scale features output by a backbone network, the global semantic modeling unit establishes a dependency relationship between spatial positions in a feature map through a self-attention mechanism; the first-stage feature fusion unit introduces a frequency domain transformation path in a cross-scale feature fusion process, performs frequency screening on features and generates high-frequency perception features; the second-stage feature fusion unit introduces intermediate features in the first stage in a propagation process and performs splicing and reconstruction processing, forming multi-scale feature representation. Based on the encoder, the detection system and the method are constructed, realizing classification and positioning processing of targets in underwater images.

The invention relates to the field of traffic analysis target detection, in particular to an audio and video target stream identification mutual complementation verification system and method.The audio and video target stream identification mutual complementation verification system comprises an internet access acquisition module, a full-traffic analysis module and the like; and a result is dynamically generated to achieve the effect of mutual complementation of target detection. The voiceprint recognition module and the image target detection module are used for double-model reasoning and integration, so that the accuracy of the target is improved, the target detection precision is improved, and the false alarm rate can be reduced through deep learning. User-defined training audio and video models are introduced in a traffic analysis scene, and a target concerned by a user is accurately identified. Compared with single-model basic target identification and post-event result set processing identification, the method has the advantages that the concerned target can be corrected more accurately in real time, the identification efficiency is improved through multi-model reasoning, the strain capacity of an actual scene is improved, and the labor cost is reduced.

This application discloses a target detection method, apparatus, device, and storage medium. The method includes: acquiring and processing a video to be detected containing a dynamic background to construct a differential image dataset; dividing the differential image dataset to obtain a target image dataset and a background image dataset; passing the target image dataset through a trained first detection model to obtain a first detection result, and passing the background image dataset through a trained second detection model to obtain a second detection result; filtering and performing frame interpolation on the second detection result to obtain a second target detection result; and obtaining the detection result of the target relative to the background information based on the first and second target detection results. This scheme can filter out false detections and supplement lost frame results after detecting different types of targets, so as to accurately determine the detection result of the target relative to the background information, thereby improving the accuracy of target detection.

The present invention discloses a remote sensing SAR target detection method based on the combination of network pruning and parameter quantization, which mainly solves the defects of high model complexity and slow reasoning speed of existing remote sensing SAR target detection methods. Its implementation scheme is: obtain the divided training set and test set from the public remote sensing SAR target detection data set, and perform data expansion on the training set; perform data enhancement on the expanded training set; adjust the existing lightweight network to build a benchmark model; train the benchmark model and calculate its performance index; evaluate the importance of each feature extraction module in the adjusted network, prune unimportant modules, and then perform filter pruning; design a quantization search space, search for a mixed precision quantization scheme of the pruned model, obtain the final model, and use the model for SAR target detection. The present invention saves training costs while improving detection accuracy, and can be used in target recognition scenarios with limited computing resources and high real-time requirements.

The invention discloses a drop-out fuse state monitoring method based on multi-size features and deep learning, and the method comprises the steps: S1, forming a data set for obtained drop-out fuse pictures, and dividing the data set into a training set and a test set; s2, adding an improved receptive field block and a coordinate attention module to a YOLOx backbone network, adding an adaptive spatial feature fusion module to PANet, carrying out secondary fusion on features of different scales, then introducing a loss function of weighting loss and positioning loss fusion, and finally carrying out lightweight improvement, constructing a state monitoring model, and carrying out state monitoring. Performing training verification on the constructed state monitoring model through the training set and the test set; s3, identifying a drop-out fuse picture acquired in real time by adopting the trained and verified state monitoring model; according to the image data collected by the application, the construction of a special database is realized, the YOLOx is improved and lightweight operation is carried out, and the complexity of the model is reduced, so that the method is suitable for an embedded platform of an electric unmanned aerial vehicle, and the detection effect of the drop-out fuse is improved.

The invention relates to the technical field of computer vision, and provides a YOLO model garbage detection method, system, device, product and medium, and the method comprises the steps: obtaining a detection data set, and carrying out the reclassification of the detection data set, and obtaining a classification set; selecting a backbone network, constructing a feature extraction convolution module, and embedding the feature extraction convolution module into the backbone network; selecting a neck network, constructing an SAC-Net module, embedding the SAC-Net module into the neck network, and connecting the neck network with the backbone network; constructing a bounding box loss module comprising an EIOU loss function, constructing a detection head through the bounding box loss module, and connecting the detection head with the neck network; constructing an initial classification model comprising a backbone network, a neck network and a detection head; and configuring the initial classification model according to the classification set, and training the initial classification model to obtain a target classification model. According to the invention, the classification accuracy of the classification model is effectively improved.

The invention discloses a modeling method of a single-stage target detection model for a high-resolution remote sensing image, and the method specifically comprises the following steps: 1, carrying out the original image preprocessing of a pre-collected high-resolution satellite remote sensing image data set, segmenting each high-resolution satellite remote sensing image into a plurality of sub-images with predetermined sizes, acquiring position information of the sub-images and category and position information of targets in the sub-images, and naming the sub-images; 2, generating annotation files according to the sizes of the sub-images, the position information of the sub-images and the types and the position information of targets in the sub-images, uniformly processing the annotation files into a VOC format, and dividing the sub-images into a training set, a verification set and a test set according to a certain proportion; step 3, establishing a target detection model; and step 4, inputting the training set obtained in the step 2 into the target detection model for training, inputting the verification set into the trained target detection model for verification, and inputting the test set into the verified target detection model for testing.