Patents
Literature
Hiro is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Hiro

46results about How to "Reduce classification error" patented technology

Vehicle-borne multi-obstacle classification device and method based on Bayes classifier

The present invention relates to a vehicle-borne multi-obstacle classification device and method based on a Bayes classifier. The classification device comprises a camera and a PC which is connected to the camera. The PC comprises a Kalman filter module for carrying out Kalman filtering on the vehicle front video image collected by a camera and detecting an obstacle target, a characteristic extraction module which is used for carrying out characteristic extraction on the detected obstacle target, and a Bayes classification module which is used for using a Naive Bayes classifier to obtain the classification of the obstacle target according to the characteristics of the obstacle target, wherein the characteristics comprise a symmetry characteristic, a horizontal edge straightness characteristic and a length and width ratio characteristic, and the classification comprises a cyclist / motorcycle rider, a vehicle side face, a vehicle front side and pedestrians. Compared with the prior art, the device and the method have the advantages of high recognition accuracy, strong anti-interference ability, high efficiency, and good real-time performance.
Owner:UNIV OF SHANGHAI FOR SCI & TECH

Time-space condition information based moving object detection method

InactiveCN102903120AImprove robustnessImprove linear separabilityImage analysisLocal consistencyVisual perception
The invention discloses a time-space condition information based moving object detection method. The method comprises the following steps: building a target detection time-space domain model through considering the significance of human visual time-space domains; calculating a conditional probability that a detection image belongs to a time-space domain reference background; carrying out nonlinear transformation on the conditional probability through negative logarithm checking so as to extract time-space conditional information; carrying out weighted summation on the conditional information of image in an adjacent domain through considering the local consistency of image characteristics; and as characteristics, carrying out object detection by using a linear classifier. The conditional probability is rapidly calculated by using a color histogram, and an image block replacing a single pixel is adopted for carrying out modeling and detection, thereby reducing the algorithm complexity and the storage space requirements; and through combining with an image block difference pre-detection mechanism, the object detection speed is increased. The method disclosed by the invention is low in algorithm complexity, less in storage space requirements and high in algorithm instantaneity, and can effectively suppress the background disturbance interference and isolate the noise influence; and by using the method, the real-time detection of moving objects on the existing computers is realized, therefore, the method is applicable to embedded intelligent camera platforms.
Owner:HUNAN VISION SPLEND PHOTOELECTRIC TECH

Dynamic self-adapting wireless sensor network invasion detection intelligence algorithm

The invention relates to a dynamic self-adapting wireless sensor network invasion detection intelligence algorithm and belongs to the wireless sensor network information safety technology field. The algorithm comprises the following steps of using a min-max standardization method to carry out normalization on a network characteristic; through a mean value drift algorithm, clustering training data into a plurality of clusters, and merging into two clusters according to a relative distance among cluster centers; taking normal data as a template and marking the two clusters as normal clusters or abnormal clusters; distributing weights for each characteristic vector of the training data according to a distance between the characteristic vector and a cluster center where the characteristic vector is located; taking the marked and weighted training data as input of a weighted support vector machine so as to construct a decision function; through the decision function, determining whether the test data is normal or abnormal; and during a detection phase, adding detection data which is determined by the decision function into the training data at intervals of updating time so as to reconstruct the decision function. The algorithm and disposition are simple, cost is low, and the algorithm can adapt to different network structures, can detect attack behaviors with different forms and possesses an expansion capability.
Owner:CHONGQING UNIV OF POSTS & TELECOMM

Apple grading method and system based on machine vision

The invention discloses an apple grading method and system based on machine vision, and the method comprises the steps: collecting a set number of sample images, and building a sample image set; collecting a to-be-detected sample image, and carrying out image preprocessing; performing feature extraction on the sample to be detected; respectively extracting a color feature, a fruit shape feature, a fruit diameter feature and a surface defect feature of the to-be-detected sample image; establishing a classification standard, and establishing a classification model of sample characteristics and grades by utilizing a genetic algorithm and a BP neural network; and inputting the extracted color feature, fruit shape feature, fruit diameter feature and surface defect feature of the to-be-detected sample image into the classification model, and outputting the grade classification of the to-be-detected sample. The method has the advantages that clear apple surface images can be obtained, and classification errors are reduced. The BP neural network model optimized based on the genetic algorithm can accurately classify apples, and the classification efficiency of the apples is greatly improved.
Owner:UNIV OF JINAN

A SegNet remote sensing image semantic segmentation method combined with random walk

ActiveCN109409240AImplementing Initial Semantic SegmentationReduce classification errorScene recognitionComputer visionImage gradient
The invention relates to a SegNet remote sensing image semantic segmentation method combined with random walk, which is divided into a SegNet initial segmentation step and a random walk optimization segmentation step. The SegNet initial segmentation step outputs an initial semantic segmentation image and category intensity information through the SegNet. A method for optimize segmentation of random walk includes selecte a random walk seed region, calculating classification saliency indexes of different class according to classified intensity information output by SegNet, and selecting seed regions of different classes by setting a threshold value; secondly, the undirected edge weights are calculated according to the original image gradient and SegNet classification intensity information. In the third step, starting from the seed region and combining with the undirected edge weights, the segmentation image is randomly walked on the whole initial segmentation image, and finally the optimized segmentation result on the whole image is obtained. The invention randomly walks on the whole image, realizes prediction error and control, greatly reduces edge burr and patch classification error, and completes high-precision remote sensing image semantic segmentation.
Owner:BEIHANG UNIV

Image classification method and device

The invention provides an image classification method and a device. The method includes the following steps: extracting classification image characteristics of a to-be-classified image; quantizing each classification image characteristic into a plurality of vision words in a vision dictionary according to a similarity relation of the each classification image characteristic and the vision words in the preset vision dictionary, and determining similarity factors of the each classification image characteristic and the quantized vision words respectively; determining weight of the vision words to set a classified vision word histogram of the to-be-classified image according to the similarity factors of each vision word corresponding to different classification image characteristics in the vision dictionary; inputting the classified vision word histogram into an image classifier which is generated by training of a sample vision word histogram which is preset according to a large amount of sample images, and determining classes of the to-be-classified image according to output results. The image classification method and the device can improve accuracy of image classification and reduce classification errors.
Owner:ALIBABA GRP HLDG LTD

Vegetation structure parameter measurement device based on wireless sensor network

The invention relates to a vegetation structure parameter measurement device based on a wireless sensor network. The device is formed by the wireless sensor network and a data processing and node control system, wherein the wireless sensor network is formed by measurement nodes distributed at the upper part and the lower part of the canopy of a study area and routing nodes, and the data processing and node control system is formed by a convergent node and a control terminal remote server in a connecting way; the measurement nodes obtain vegetation parameter information through acquiring the solar radiation of the upper part and the lower part of the canopy at different solar altitudes in one day, and conducts data transmission and positioning through a wireless ad hoc network; the convergent node can upload the data of the measurement nodes to a control terminal through serial ports and GPRS, and vegetation structure parameters are computed through a data processing system; and the control terminal sends commands to the nodes through the convergent node to modify parameter setting. The invention has the advantages that the volume is small, the power consumption is low, the deployment is convenient and the cost is low, the device is suitable for large-area and long-period vegetation parameter measurement, and the practical value and the application prospect are wide in agriculture, ecology and the wireless sensor network technical field.
Owner:BEIJING NORMAL UNIVERSITY +1

Zero sample image classification method based on relative attribute random forest

The invention provides a zero sample image classification method based on a relative attribute random forest. An attribute ranking score model is built for an image with an unknown class according to the relative relationship between image classes and image attributes, the attribute ranking score models for all images serve as training samples to train a random forest classifier, and finally, according to an attribute ranking score for a tested image and the random forest classifier obtained through training, the label of the tested image is predicted. The method of the invention can realize zero sample image classification and has the advantages of high classification recognition rate, strong model stability and the like.
Owner:中国科学院电子学研究所苏州研究院

Hyperspectral remote sensing image classification method and system based on visual saliency

The invention discloses a hyperspectral remote sensing image classification method and system based on visual saliency. The method mainly solves the problem of low space information utilization rate during hyperspectral remote sensing image feature extraction. The information of the spatial dimension can visually reflect the real shape and category of the ground object. The visual saliency mechanism can simulate the visual characteristics of people through an intelligent algorithm. A salient region (i.e., a region of interest of human) in an image is extracted; by extracting the saliency features, a target different from the surrounding background can be detected without prior information, the main content of the image is highlighted, the complexity of image processing and analysis is reduced. Finally, classification is performed by combining spectral information, classification errors can be effectively reduced, and the classification precision is improved.
Owner:CHINA UNIV OF GEOSCIENCES (WUHAN)

Coarse classification method and device based on clustering analysis, terminal equipment and storage medium

The invention relates to a coarse classification method based on clustering analysis. Device, terminal equipment and storage medium, The method comprises the following steps of: obtaining a sample; obtaining a first classification result which is determined by classifying the to-be-classified sample data according to a preset clustering algorithm in advance, training the first sample data and thesecond sample data obtained by the first classification to obtain a first-stage SVM classifier, and inputting the to-be-classified sample data of the first-stage SVM classifier into the first-stage SVM classifier for classification; Training by applying the first sample data and the second sample data obtained by last classification to obtain a next-level SVM classifier; and inputting the to-be-classified sample data of the next-level SVM classifier into the next-level SVM classifier, and stopping classification until any one of a first classification stopping condition and a second classification stopping condition in classification stopping conditions is met. Classification error accumulation of each stage of SVM classifier is reduced, and the classifier recognition accuracy in the big data classification process is improved.
Owner:北京细推科技有限公司

Classification mechanical arm for plastic bottle production line

The invention discloses a classification mechanical arm for a plastic bottle production line. The classification mechanical arm comprises a classification box; a conveying cavity is formed in the classification box in a left-right penetrating mode; a conveying belt and a separation belt are slidingly arranged in the conveying cavity; the conveying belt is positioned on the front side of the separation belt; conveying devices are connected into the conveying belt and the separation belt; and the conveying devices can drive the conveying belt and the separation belt to slide. The classificationmechanical arm can automatically detect the diameters of bottle bodies of all plastic bottles to improve the detecting efficiency, and can perform classification according to the diameters of the bottle bodies of the plastic bottles; and the sizes of the plastic bottles can be reflected through the diameters of the bottle bodies more accurately, so that the classification errors are effectively reduced.
Owner:SHENZHEN TAOHUI CUP IND CO LTD

Patent classification method based on similarity measurement

The invention discloses a patent classification method based on similarity measurement, and belongs to the technical field of text classification. According to the invention, the problem of low accuracy of patent classification by use of an existing patent classification method is solved. The invention provides a patent classification method based on mixed similarity by considering the characteristics of patent specification abstracts, combining CHI statistics and cosine similarity and combining the similarity of IPC classification numbers. The patent classification method based on the similarity of the claims is provided for the claims. And calculating the similarity of the claims according to the extracted SAO-x multi-dimensional structure, and classifying the patents by adopting a KNN classification algorithm based on the similarity result. Compared with an existing patent classification method, the patent classification method has the advantages that the accuracy of automatic patent classification reaches 70% or above, and classification errors generated by manual classification on the subjective level are reduced. The method can be applied to the technical field of text classification.
Owner:HARBIN ENG UNIV

Beet identification method based on single-time-sequence NDVI

The invention belongs to the technical field of remote sensing image recognition, and discloses a beet recognition method based on single-time-sequence NDVI, and the method comprises the steps: obtaining near-infrared band, red light band and remote sensing image data; screening spectral characteristics of crops, finding out a period with the most obvious beet spectral characteristic value, and carrying out single-time-sequence NDVI inversion analysis; carrying out statistical analysis on altitude and slope information of all beet plots; taking single-time-sequence remote sensing data as basicdata, importing the obtained GPS coordinate information into an image, performing classification by using a supervision classification method, and identifying beet in a research area by using a random forest classifier to form an identification result graph; performing cumulative statistics on the single-time-sequence NDVI image data, and determining a lower limit threshold value and an upper limit threshold value of crop classification; and taking the altitude, the gradient and the preliminary classification threshold of the random forest classifier as screening conditions through a classification tree method. According to the invention, the beet recognition rate is improved to the greatest extent.
Owner:INNER MONGOLIA AGRICULTURAL UNIVERSITY

Torch smoke dust monitoring method based on visual perception

The invention discloses a torch smoke dust monitoring method based on visual perception, and belongs to the crossing field of image processing and environment perception. According to the VMFM provided by the invention, firstly, whether flame exists in an image is identified by utilizing a wide tuning color channel, then the position of the flame is determined by combining rapid significance detection and a K-means method, finally, a potential torch smoke area is searched by taking the flame area as a center, and finally, whether torch smoke exists or not is detected. Experimental results on aplurality of video sequences acquired from a petrochemical plant show that the method is superior to existing related methods in monitoring performance and calculation efficiency. According to the torch smoke dust monitoring method based on vision, torch smoke dust can be found in time, and sufficient combustion of torch gas is guaranteed.
Owner:BEIJING UNIV OF TECH

Cell classification method, a device and electronic equipment based on gene expression characteristics

The invention provides a cell classification method, a device and electronic equipment based on gene expression characteristics, and relates to the technical field of cell classification. The method comprises the steps of calculating first differential expression genes of a first tissue sample and a second tissue sample, selecting first genes with high expression in the first tissue sample and thesecond tissue sample based on the first differential expression genes, and respectively forming a first tissue characteristic gene set and a second tissue characteristic gene set; calculating a firstaverage expression value and a second average expression value of the first tissue characteristic gene set and the second tissue characteristic gene set in each cell of the cell population, and dividing the cells in the cell population into a first cell population and a second cell population by adopting a clustering algorithm. Thereby, the limitation of a cell classification method in the existing single cell sequencing data analysis can be reduced, the cell classification accuracy can be improved, and the classification error can be reduced.
Owner:ACADEMY OF MILITARY MEDICAL SCI

Adversarial network data generation method and abnormal event detection method

The invention discloses an adversarial network data generation method and an abnormal event detection method. The method is mainly designed for a multi-dimensional data set abnormal event detection scene in the field of current artificial intelligence and data mining. The generative adversarial network objective function and the corresponding optimization mode are desgined by using the exponentialinformation measure, thereby guiding the generative adversarial network to generate data. Furthermore, the conventional event data and the abnormal event data in the multi-dimensional data set are classified based on the exponential information measure generative adversarial network, so that the classification error is reduced, and the abnormal event detection performance is improved.
Owner:TSINGHUA UNIV

Design method of elastic network constraint self-interpretation sparse representation classifier

The invention relates to a design method of an elastic network constraint self-interpretation sparse representation classifier. The method comprises the following steps: training samples are read, the training samples are linearly transformed to a high-dimensional kernel space, each type of the training samples are learnt in the high-dimensional space, a contribution (i.e., a weight) made by each individual in the type of the training sample to constructing a sub-space of the type of the training samples is found, and a dictionary is constructed by a product of the type of the training samples and a weight matrix; and elastic network coefficient coding of test samples in the kernel space is obtained through training the obtained sparse representation dictionaries, and finally, the test samples are fitted by use of each type of the dictionaries and the elastic network sparse coding corresponding to the dictionaries, fitting errors are calculated, and the type of minimum fitting errors are the type of the test samples. According to the invention, the method is integrated with the advantages of ridge regression and lasso regression, sparse coding features of the samples are enabled to sparse, the fitting errors are also quite small, classification errors are effectively reduced, and the identification performance of a classifier is improved.
Owner:CHINA UNIV OF PETROLEUM (EAST CHINA)

Video classification method based on recurrent neural network

The invention discloses a video classification method based on a recurrent neural network. On the basis of existing GRU video classification, in the GRU training process, Taylor series are innovatively used for explaining a gating cycle unit, and parameter training of the GRU is assisted by introducing remainder items in the Taylor series in the GRU training process. In the Taylor series, the error is related to the order of the series, and the larger the order is, the smaller the error is, so that the video classification error is reduced by constructing the high-order Taylor series for assisting the GRU training. Meanwhile, the relation between the gating circulation unit and the Taylor series is established, and further, the generalization ability of the GRU is explained through the relation.
Owner:成都澳海川科技有限公司

Image enhancement processing method and device, computer equipment and storage medium

The invention relates to the technical field of neural networks of the artificial intelligence technology, and provides an image enhancement processing method and device, computer equipment and a storage medium, and the method comprises the steps: carrying out the amplification of an image of a data set through employing a data enhancement algorithm, carrying out the classification of a target image through employing a digital recognition model, and obtaining a classification result; screening out a first target image which is correctly classified and a second target image which is wrongly classified; obtaining a first weight vector and a feature vector of the first target image of each category, and training a pre-constructed image recognition model by using the first target image to obtain a trained image recognition model; and predicting the second target image by using the trained image recognition model to obtain a prediction result, generating a second weight vector according to the prediction result, and multiplying the second weight vector by the second target image to obtain a quality-enhanced training image, so that inherent noise existing in the second target image can be suppressed, and the quality of the target image is improved. And the quality of the image after data enhancement is improved.
Owner:PING AN TECH (SHENZHEN) CO LTD

High-voltage cable partial discharge mode identification method, computer equipment and storage medium

The invention provides a high-voltage cable partial discharge mode recognition method, and the method comprises the following steps: obtaining training data through laboratory data, dividing the training data into a training set and a test set, and collecting onsite to-be-recognized data; respectively inputting the training set into a plurality of classifiers for training, respectively inputting the test set into the trained classifiers for testing, and inputting to-be-identified data acquired on site into the trained classifiers to obtain a preliminary identification result; taking the preliminary identification result as input data, constructing a partial discharge mode identification model by adopting a learning method taking a support vector machine as a classifier, and then inputtingthe input data into the partial discharge mode identification model for testing to obtain a tested partial discharge mode identification model; and inputting to-be-identified data acquired on site into the tested partial discharge mode identification model, and outputting to obtain a high-voltage cable partial discharge integrated mode identification result.
Owner:GUANGDONG POWER GRID CO LTD +1

Image tracking method and device

The invention discloses an image tracking method and device, and the method includes: an image tracking method. The tracking method includes: determining a plurality of original areas corresponding to different target images in the video; expanding the boundaries of the original areas in the video according to a predetermined ratio to obtain a plurality of target areas, so that the multiple target areas are located The range of the image is greater than the range of the image where the multiple original areas are located; the multiple target areas are scaled to a predetermined size to obtain multiple predetermined target areas. The present invention expands the window of the original tracking object by a certain proportion, and then scales it to a fixed size, thereby greatly reducing the number of detection and search windows, and aiming at the commonality of similar multiple targets, all target images share the same Learners, online models and detectors to improve the tracking efficiency of target images.
Owner:北京智诺英特科技有限公司 +1

Classified storage method and system based on big data

The invention discloses a classified storage method and a system based on big data, relates to the technical field of information, and is used for realizing that the big data is classified into structured data, semi-structured data and non-structured data, and the structured data are directly stored by adopting a relational database; mode extraction is performed on the semi-structured data, the semi-structured data are mapped into structured data, and the structured data are stored by adopting an object-based relational database; the non-structured data are subjected to feature extraction, virtual classification and object creation to be converted into structured data to be stored. The method has the advantages of being small in classification error, high in efficiency, good in compatibility and capable of achieving normalization and standardization of information data management.
Owner:GUANGDONG INST OF SCI & TECH

Power distribution network fault classification method and system based on deep learning, and medium

The invention relates to a power distribution network fault classification method and system based on deep learning, and a medium. The method comprises the steps: obtaining a plurality of original fault waveform data sets; respectively processing each original fault waveform data set to obtain target sample data; making all target sample data into a data set, dividing the data set into a trainingset and a test set, constructing a deep learning network model, and training the deep learning network model by using the training set to obtain an original fault classification model; performing parameter tuning on the original fault classification model by using the test set to obtain an optimized fault classification model; acquiring a real-time fault waveform data set, processing the real-timefault waveform data set to obtain to-be-detected fault data, and performing real-time identification on the to-be-detected fault data by utilizing the optimized fault classification model to obtain areal-time fault classification result. According to the method, the faults in the power distribution network are quickly and reliably recognized and classified by utilizing the strong classificationadvantage of deep learning, the recognition efficiency is high, and the classification accuracy is high.
Owner:HUAZHONG UNIV OF SCI & TECH +1

Multi-directional multi-level double-cross robustness identification based on face structure features

The invention discloses a multi-directional multi-level double-cross robustness identification based on face structure features. The method being a novel method for extracting face expression features mainly studies two main components of face recognition: face representation extraction and face matching. Face representation is extracted by means of double-crossed two-group-dividing coding in eight directions of an inner circle and an outer circle, so that face features are summarized comprehensively and the computing load is reduced. Multi-directional gradient filtering and multi-level face representation are added and a gray-scale face image is transformed into a multi-directional gradient image by using a Gaussian first-order operator derivative, so that influences caused by illumination, image blurring, shielding, attitudes, and expressions can be reduced and thus robustness of illumination changing can be enhanced. According to a three-criterion optimal gradient filter, SNR maximization, edge positioning precision keeping, and single edge response are realized, so that the interference during face expression extraction can be reduced and thus face expression features can be extracted accurately and the computing cost can be saved.
Owner:NANJING UNIV OF POSTS & TELECOMM

Garment image classification method, device and equipment and image classification method, device and equipment

The embodiment of the invention provides a garment image classification method, device and equipment and an image classification method, device and equipment. The garment image classification method comprises the steps: acquiring a plurality of garment images; for any garment image, dividing the garment image into a plurality of area images; respectively extracting color histogram features of theplurality of region images; performing weighting processing on the color histogram features of the plurality of region images to obtain image features of the garment image; clustering the plurality ofgarment images based on the image features of the plurality of garment images to obtain a plurality of image sets; and determining the number of images of at least one garment image corresponding tothe plurality of image sets. According to the technical scheme provided by the embodiment of the invention, the garment classification precision is improved.
Owner:ALIBABA GRP HLDG LTD

Autonomously updated indoor positioning method

The invention discloses an autonomously updated indoor positioning method. The method comprises the following steps: constructing a feature extraction network; constructing a hidden Markov model; constructing a new landmark detection network; calculating two-dimensional plane coordinates of the new landmark; writing the calculated two-dimensional plane coordinates of the new landmark into a database; and obtaining a new feature extraction network by taking the ROI and the category of the new landmark and the ROI and the category of the unchanged landmark as training data. By combining the hidden Markov model and the motion recovery structure technology, the output of the feature extraction network is judged, the classification error of the feature extraction network can be further reduced,and the misjudgment rate is effectively reduced; meanwhile, a new landmark detection network is constructed; according to the method, the relative positions of the horizontal plane of the three-dimensional point cloud and the new landmark can be determined, then the three-dimensional coordinates of the new landmark are mapped back to the planar map space, indoor map updating is completed, a largeamount of manpower does not need to be consumed for updating and maintaining the indoor planar map, and the later-period maintenance cost of video indoor positioning is greatly reduced.
Owner:SUN YAT SEN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products