33 results about "Multispectral image classification" patented technology

The invention relates to a hyperspectral image space-spectrum joint classification method based on 3DCNN. Aiming at the characteristic that hyperspectral image data is a three-dimensional structure, a three-dimensional convolutional network suitable for hyperspectral images is constructed to complete hyperspectral image space-spectrum joint classification. First, from the original hyperspectral image, a data block in a certain neighborhood centered on the pixel to be classified is extracted as the initial spatial spectral feature, and the 3DCNN network constructed is trained in combination with the label of the pixel to be classified. Then, the hyperspectral image space-spectrum joint classification is accomplished using the trained 3DCNN. Beneficial effects are: 1) solve the complex processing problem of spectrum space dimensionality reduction or compression in the existing classification technology; Rich information and saves the trouble of artificially pre-setting features; 3) 3DCNN-based hyperspectral image space-spectrum joint classification method. 4) The hyperspectral image classification accuracy is improved.

The invention discloses a multi-spectral image classification method based on threshold self-adaptation and convolutional neural network, which inputs multi-spectral images of satellites to be classified in different time phases and different bands, and converts the marked parts of the same band images of all cities All pixels are normalized; the selected 9 bands are stacked into an image as a training data set; a classification model based on convolutional neural network is constructed, and the training data set is used to train the classification model to obtain a probability model based on OSM. The model and the confidence strategy adjust the softmax output results to obtain the final classification model, and finally upload the test results to the IEEE website to obtain the classification accuracy. The multi-spectral image classification method provided by the present invention makes full use of the characteristics of multi-spectral image with multiple bands, large data volume, and large information redundancy, and solves the problem that it is difficult to classify complex types of ground objects, and can not only improve the classification accuracy , Reduce the misclassification rate, and can also improve the classification speed.

The invention discloses a hyperspectral image classification method based on ridgelet and deep convolution network, which mainly solves the problems of low classification accuracy and high computational complexity of hyperspectral image classification in the prior art. The implementation steps are: 1. Select training samples in the hyperspectral image; 2. Extract the spectral information and spatial information of the training samples; 3. Combine the spectral information and spatial information to form a training sample set; 4. Construct a five-layer deep convolutional network , and design a ridgelet filter to initialize the network; 5. Use the training sample set to train the constructed neural network; 6. Classify the remaining samples with the trained neural network to complete the image classification. The invention has the advantages of high classification accuracy and fast classification speed, and can be used in meteorological monitoring, environmental monitoring, urban planning and disaster prevention and reduction.

The invention belongs to the field of financial tools and discloses a multispectral image acquisition and processing method for a contact image sensor, aiming at solving the defects in the prior art that noise points exist in an acquired image, overall brightness difference between segments of the acquired image is great, and images of the same paper money under different light sources cannot synchronously acquired. The method comprises the following steps: an upper multiple-light-source CIS image sensor and a lower multiple-light-source CIS image sensor which are symmetrical to each other are arranged to acquire original images; acquired analog signals are subjected to filtering and then are sent to two independent A / D sampling modules to be quantized so as to obtain digital signals; the A / D sampling modules send the digital signals to a FPGA (Field Programmable Gate Array) for compensating, splicing, compressing and storing; the FPGA sends the signals to a main control chip; the main control chip puts the two-path information into two independent address areas of an external RAM (Random Access Memory) for caching; after whole images are acquired, a DSP (Digital Signal Processor) takes out the images from the external RAM to process. The multispectral image acquisition and processing method has the advantages that the acquired images have less noise; the images of the paper money under different light sources can be synchronously acquired; the acquired images are relatively smooth and the quality of the images is relatively high.

The present invention provides a classification method and device for fusing panchromatic images and multispectral images, wherein the classification method for fusing panchromatic images and multispectral images includes: collecting panchromatic images and multispectral images of the area to be measured; Segment the panchromatic image to obtain an over-segmented volume of the panchromatic image; merge the over-segmented volumes of the panchromatic image to determine a segmented volume unit; perform segmentation on the multispectral image according to the segmented volume unit classification, obtaining classification labels of the multi-spectral image; wherein, the segmented volume unit includes at least one over-segmented volume. Through the classification method and device for fusing panchromatic images and multispectral images provided by the present invention, the spatial information of panchromatic images can flow to the multispectral image classification process, and the spatial information and multispectral images in panchromatic images can be fully and effectively utilized. The spatial information in the image reduces the dependence of image classification on spectral information, improves the accuracy of classification, and makes the classification labels clear.

The invention discloses a hyperspectral image classification method based on local cooperative expression and neighbourhood information constraint, and is mainly used for solving the problem of high computation complexity in the prior art. The hyperspectral image classification method comprises the following realization steps of: (1) forming a neighbourhood matrix by M samples in a neighbourhood of a hyperspectral image tested sample and a tested sample; (2) forming a dictionary by all training samples, and calculating a cooperative expression coefficient matrix of the neighbourhood matrix by the dictionary; (3) calculating 12 norms of each row of the coefficient matrix, selecting N atoms from the dictionary according to large N row marks of the 12 norms to form a sub dictionary, and calculating a cooperative expression coefficient of the tested sample by the sub dictionary; (4) dividing the cooperative expression coefficient and the sub dictionary into n parts according to the number of every class of training samples; and (5) calculating and comparing a residuals between the tested sample and each reconstruction of the n parts, wherein a class mark of the tested sample is corresponding to a subscript of the minimum residual. According to the hyperspectral image classification method disclosed by the invention, the local cooperative expression is used, thus reducing the quantity of the atoms and reducing the computation complexity; and the hyperspectral image classification method can be used for solving the problem of hyperspectral image classification.

The invention discloses a method for classifying multispectral images based on surface wave CNN. The multispectral images to be classified are input, the multispectral data are normalized to obtain a matrix, and the normalized matrix is ​​obtained by taking the center pixel. block to obtain the training data set and test set; construct a classification model based on surface wave CNN; use the training data set to train the classification model; use the trained classification model to classify the test data set. The invention introduces a multi-scale depth filter, improves the classification accuracy of multi-spectral images, and can be used for object classification.

The invention discloses a multi-spectral remote sensing image feature classification method based on spectrum and texture features. The method adopts quadtree block technology to perform multi-level block processing on the image, and extracts the spectrum and feature of the feature in the form of image blocks. Texture features, the SVM classifier is used to classify the ground objects of the image block, and the edge area of ​​the image block classification is processed by the region growing method. Compared with the existing technology, this multispectral remote sensing image classification method improves the anti-noise performance of spectral features and texture features in ground object classification, avoids the problem of texture feature extraction window size, and makes the classification results have strong regional consistency and low noise. Less pros.