Search

Crop canopy temperature can often be acquired using the thermal imager. Non-contact and non-destructive automated detection can be expected to achieve for crop water stress status. Automatic image alignment can be used to treat the fuzzy edge distribution, strong noise, as well as shape and texture information lacking in thermal infrared images, according to the information complementarity between visible light and thermal infrared images. The automated extraction can be realized on the crop canopy temperature. This study aims to solve the problems of differences in the radiation, shape, and texture between visible light images and thermal infrared images, leading to the low align images of different modalities. Multimodal image registration was also proposed to integrate the improved brain storm optimization (BSO) and Powell algorithm. Firstly, the original visible light image was downsampled and cropped, according to the normalized cross-correlation value. The area with the most similarity region was obtained in the thermal infrared image under the same resolution; Then, the target area was extracted from the cropped image. The target area image and the original thermal infrared image were decomposed by wavelet transform, where the multilayered low-frequency information was retained; Thirdly, the primitive affine transformation matrix was obtained by the image moments in the low-resolution layer; At the same time, the global search was used to optimize the affine transform matrix in the low-resolution layer using the improved BSO; Fourthly, the optimization was used as the initial point of the Powell algorithm. The optimization was performed in the high-resolution layer; Lastly, the optimization in the previous step was input into the Powell algorithm again. The original image layer was optimized again to obtain the final affine transformation matrix. The original BSO optimization was improved for the optimal affine transformation matrix in the image alignment task. The specific improvements included the following five aspects: The BSO population distribution was initialized using a chaotic mapping function; The mutation range of new individual was modified; The number of K-means clusters was dynamically adjusted in the BSO by the elbow; The chaotic local search was incorporated into the strategy of individual variation; and the probability parameters were dynamically adjusted, according to the different BSO in the early and late stages. Mutual information (MI), normalized mutual information (NMI), root mean square error (RMSE) and mean structure similarity index measure (MSSIM) were taken as the evaluation indexes. A comparison was made with Powell optimization, genetic algorithm (GA) and BSO_Powell algorithm. Specifically, MI indexes were improved by 0.054 2, 0.076 9, 0.040 5, respectively; NMI indexes were improved by 0.015 9, 0.023 1, 0.052 7, respectively; RMSE indexes were reduced by 15.02, 13.03, 27.08, respectively; and MSSIM indexes were improved by 0.0523, 0.0488, 0.1224, respectively, in greenhouse data; In field data, MI indexes were improved by 0.064 2, 0.066 7, 0.035 5, respectively; NMI indexes were improved by 0.007 7, 0.0125, 0.0124, respectively; RMSE indexes were reduced by 14.06, 10.57, 15.40, respectively; and MSSIM indexes were improved by 0.047 1, 0.038 1, 0.042 9, respectively. The strong robustness can accurately achieved in the multimodal image registration tasks for potatoes under complex environments. [ABSTRACT FROM AUTHOR]

A set of algorithms with high positioning accuracy and recognition stability is proposed to meet the requirements of accurate positioning and recognition of ring-code targets. A method based on concentric projection transformation to solve the circle center is proposed for the precise positioning of annular coded targets. In the recognition of coded targets, the ellipse is changed into a standard circle by affine transformation, and then the internal coded band is decoded to get its unique decoded value. The experimental results show that the average error of the circle center extraction method is 0.225 pixels with the ideal circle center, 0.501 pixels with the ellipse fitting to extract the outer circle center, and 0.294 pixels with the inner circle center, and its accuracy is improved by 122.05% and 30.26% respectively. The angle between the camera and the coding target needs to be controlled within 75°, when the angle is less than 75°, the recognition rate of the coding target can reach 100%. The study finds that the coded target recognition and positioning method meets the photogrammetry requirements and has practical significance because it is more accurate than the ellipse fitting algorithm. [ABSTRACT FROM AUTHOR]

This paper presents a novel S-box generation scheme to enhance the security of the Advanced Encryption Standard（AES） algorithm. After analyzing the existing issues with S-boxes, a new S-box is constructed based on the principles of S-box construction and its cryptographic properties. This is achieved by selecting new irreducible polynomials and affine transformations while adjusting the order of affine transformations and multiplicative inversion operations. The newly generated S-box is compared with the S-box of AES and other improved S-boxes in terms of algebraic terms and strict avalanche criteria distance. The results demonstrate that the new S-box exhibits superior algebraic properties and effectively defends against algebraic attacks. Furthermore, the new S-box is subjected to hardware design and optimization. The DC synthesis results reveal that the optimized implementation of the new S-box in the finite field consumes 12% fewer resources compared to traditional finite field implementations and 41% fewer resources compared to lookup table methods. This paper substantiates the superiority of the new S-box in terms of security over the existing S-boxes. It also applies the new S-box to AES software and hardware designs, with the correctness of the implementation verified through simulation testing. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Chongqing University of Posts & Telecommunications (Natural Science Edition) is the property of Chongqing University of Posts & Telecommunications and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Overlapping occlusion has seriously limited the yield estimation of bagged grapes in recent years, due to the ever-increasing grape volume after bagging and the large surface area of grape leaves. The unstable speed of manual video shooting can also lead to the loss of bagging grape targets. In this study, a yield estimation was proposed for the bagged grape using self-correcting Non-Maximum Suppression (NMS)-ByteTrack. Firstly, the bagged grapes were detected in the video using object detection (YOLOv5s). The NMS operation was also post-positioned to the tracking stage to retain the fruit detection boxes that filtered under the occlusion. Specifically, the detection boxes of bagged grapes were detected by object detection (YOLOv5s), whereas, the prediction boxes of bagged grapes were predicted to calculate the intersection over union using the Kalman filter. If the intersection over the union was less than the given threshold, the detection box was filtered to reserve the detection boxes closer to the predicted position. Then, the final detection box was obtained using the NMS operation. Secondly, the camera motion compensation and improved Kalman filter algorithm were added to automatically correct the position of the fruit prediction boxes and track them using ByteTrack. Specifically, the camera motion compensation was used to first extract the background key points in the bagged grape pictures of the previous frame and the current frame except for the tracking target. The sparse optical flow was used to match the extracted background in the key points of the bagged grapes. Then the affine transformation matrix of background motion was calculated by the RANSAC algorithm, and the Kalman filter was utilized to predict the bagged grape prediction boxes of the current frame. Finally, the affine transformation matrix was obtained to convert the prediction boxes in the coordinate system from the previous to the current frame, in order to realize the position information correction for the prediction boxes of the current frame. In addition, the improved Kalman filter algorithm can be used to change the aspect ratio in the state vector, and then to express the position of the bagged grape tracking boxes in the Kalman filter directly as the width, in order to more accurately estimate the position of the bagged grape tracking boxes. As such, a line-counting strategy was proposed to automatically count the bagged grapes. The strategy was also to set the counting line in the middle of the video, and also retain the idle frames without the bagged grapes in the first few seconds of the video. Furthermore, the bagged grapes with the same ID were only counted once to avoid repeated collision line counting. The successful collision between the center point of the tracking box of bagged grapes and the counting line was achieved in the automatic counting of bagged grapes. The dataset was collected from the Paidengte Agricultural Science and Technology Demonstration Park, Bishan District, Chongqing of China. The mobile phone cameras of Redmi K40 and OPPO Reno6pro+ were selected to capture the pictures of the same bagged grape at 8:00, 12:00, and 18:00 from different angles, such as frontal, sideways, and overhead shots. The total shooting time was about 6 h, the shooting height was about 1.5 m from the ground, and the shooting route was line by line. A total of 500 images and six videos were obtained for the bagged grapes. Among them, 500 images were expanded to 2000 images after saturation, brightness enhancement, brightness reduction, and mirror operations. Then, 2000 images were randomly divided into the training and validation sets in the ratio of 8:2, where six valid videos were used as the test set. Relevant experiments were conducted using this dataset. The experimental results showed that the yield estimation achieved a significant improvement in the tracking performance of bagged grapes using self-correcting NMS-ByteTrack. The multi-object tracking accuracy and precision, as well as the identification F1-score, were 64.6%, 82.4% and 80.8%, respectively, which increased by 1.7, 1.0 and 4.1 percentage points, respectively, compared with the ByteTrack. The number of ID switch was reduced by 3 times. Then, the average counting accuracy reached 82.8% in terms of counting performance, compared with manual counting. In addition, a comparison was also made with the five tracking methods. A better tracking performance was achieved, compared with the rest. The applicability of this estimation was also verified in tracking and counting bagged grapes. Therefore, the yield estimation can be expected to effectively promote the tracking and counting of bagged grapes in real scenarios using self-correcting NMS-ByteTrack. More accurate yield estimation of bagged grapes was also achieved in this field. [ABSTRACT FROM AUTHOR]

In order to solve the problem that the existing text guided image inpainting models lack efficient fusion of information between modes when dealing with text image fusion, resulting in unreal repair results and poor semantic consistency, this paper proposed a text guided image inpainting model BATF, which integrated image text features through conditional batch normalization. Firstly, it normalized the damaged and undamaged regions respectively by the spatial region normalization encoder to reduce the influence of direct feature normalization on the mean variance shift. Secondly, through the depth affine transformation, it fused the extracted image features and the text feature vectors to enhance the visual semantic embedding of the generator network feature map, so that the image and the features could be fused more effectively. Finally, it designed an efficient discriminator and introduced a target perception discriminator in this paper to enhance the texture authenticity and semantic consistency of the repaired image. Quantitative and qualitative experiments on CUB bird, a text-labeled dataset, show that the proposed model achieves 20.86,0.836,and 23.832 for PSNR, SSIM, and MAE, respectively. BATF model is better than the existing models MMFL and ALMR, and the repaired images both meet the requirements of given text attributes and have high semantic consistency. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Remote Sensing is the property of Editorial Office of Journal of Remote Sensing & Science Publishing Co. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Basic Sciences Journal of Textile Universities / Fangzhi Gaoxiao Jichu Kexue Xuebao is the property of Basic Sciences Journal of Textile Universities and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Chongqing University of Posts & Telecommunications (Natural Science Edition) is the property of Chongqing University of Posts & Telecommunications and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Objectives: The registration of remote sensing image data and GIS ( geographic information system ) vector data is the basis of the integration of remote sensing and GIS, which is widely used in the fields of map data update, city monitoring, map change detection and so on. At present, the key to the registration of remote sensing images and vector data is the extraction of remote sensing image features. However, the existing remote sensing image feature extraction has problems such as incomplete feature extraction, which leads to registration failure or low accuracy. This paper proposes a registration method for remote sensing images and vector data based on Mask region -based convolutional neural network (Mask R -CNN). Methods: Firstly, we select the road intersection as the distinctive feature of the same name in the remote sensing image and vector data, and create a road intersection image data set to train Mask R -CNN model. Secondly, according to the geometric topological relationship, the vector data road intersections are selected as vector control points. And take the intersection control point of the vector data as the center, we use 400 × 400 pixels window to crop the remote sensing image data and input it into the Mask R-CNN model, extract the border of the road intersection in the image. The control points of the same name are determined according to the Euclidean distance between the remote sensing image and the vector data control points, and the control points of the same name are cleaned using the density-based spatial clustering of applications with noise algorithm. Finally, the affine transformation parameters are calculated according to the filtered control points of the same name to realize the registration of remote sensing image and vector data. The registration data of Shanghai vector data and Gaofen-2 image data were selected for registration experiment. Results: Experimental results show that the average deviations of the experimental data before were 15. 34 m and 1. 44 m, before and after registration based on Mask R -CNN. This method can correctly register remote sensing images and vector data, and the proposed method has better application prospects in urban data registration, and has the characteristics of strong robustness and high accuracy. Conclusions: The proposed method in this paper can automatically register remote sensing images and vector data from different sources in areas such as mountains, grasslands, and deserts. In the next step, the amount of sample data of remote sensing images will be increased, including types of remote sensing images and types of features. [ABSTRACT FROM AUTHOR]

The single-frame image super-resolution（SISR） method based on deep networks is currently a hotspot in SR research. However, most of these methods mainly focus on exploring the network depth structure during feature extraction, ignoring the similarity between the feature layers in the intermediate space, and neglect the feature differences between the feature layers during reconstruction. This paper proposed a progressive network based on spatial feature transformation and back-projection reconstruction to solve this problem. The main feature of this method was to perform feature affine transformation on the feature space when extracting image features to increase the different similarities between feature layers, so as to obtain progressive features and spatial transformation features. In the image reconstruction stage, the reconstruction module adopted the strategy of multi-scale back projection to integrate the multi-source features of the image, which made the module pay more attention to the difference between features. Finally, the experimental results show that compared with most super-resolution methods, the proposed method has greatly improved the evaluation indexes such as PSNR/SSIM during image super-resolution reconstruction, and the texture information of the reconstructed image is more abundant. [ABSTRACT FROM AUTHOR]

The existing algorithms cannot deal with brightness, contrast, artifact and noise at the same time. This paper proposed the low-light enhancement network based on multi-branch residual and affine transformation. The key idea was to exert different modules to handle different tasks. Firstly, the illumination estimation module obtained the illumination variable of the low-light image. Secondly, it combined the illumination affine transformation module with the illumination encoding parameters to restore the illumination of the image. Finally, the detail reconstruction module fused more image details to obtain the final output. The experimental results show that the proposed method effectively enriches the image texture details, enhances brightness and contrast while suppressing the artifact and noise generated. Compared with popular methods, the results quantitatively and qualitatively prove that the method is better for low-light image enhancement. [ABSTRACT FROM AUTHOR]

In corner detection, the ability of two-dimensional Gabor feature to distinguish corners is not verified, and the description of pixel neighborhood features has defects.As the result, the robustness of corner detection is poor and the positioning accuracy is low. In order to solve the above problems, the directional derivative of the real part of the two-dimensional Gabor filter was used to extract the intensity variation difference of each corner model,with the multi-directional structure tensor and multi-scale screening mechanism, a new corner detection algorithm was proposed. Firstly, the input image was smoothed by the real part of the two-dimensional Gabor filter, and the gray variations in all directions were extracted. Secondly, the multi-directional structure tensor product was constructed by synthesizing the gray-scale variation information of the target pixel in each direction, and the corresponding corner measure was generated. Finally, the non-maximum suppression was used for preliminary screening, and then the target corners were obtained by multi-scale filtering. The performance of the proposed method was compared with seven classical detection algorithms under the conditions of image affine transformation and Gaussian noise interference. The proposed method has better detection robustness, and the positioning accuracy is also verified by matching experiment based on ground truth. [ABSTRACT FROM AUTHOR]

At present, deep learning has been widely used in MR medical image analysis, however, obtaining a large number of MR training data sets is a huge challenge. For the expansion of traditional physics-based data sets such as rotation, scaling, and affine transformation, there are major limitations, this paper proposed a new image synthesizer. First, it subjected the MR image data set to uniform size processing, then divided each image into non-overlapping blocks of equal size, and then extracted the code of the image block by an automatic encoder, and used the image block coding and random noise as input to the generator.Finally, it stitched the pseudo image blocks to generate a complete MR image. This method was used to carry out experiments on brain MR images, and to analyze the generated images qualitatively and quantitatively. Experimental results show that the proposed method can generate high-quality MR images and is superior to other mainstream methods. [ABSTRACT FROM AUTHOR]

Copyright of Telecommunication Engineering is the property of Telecommunication Engineering and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of China Sciencepaper is the property of China Sciencepaper and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In order to solve the problem of low efficiency and large influence of human factors on the airtightness testing of the valve body, a method based on improved SIFT lo detect the airtightness of the valve body is proposed. First of all* the algorithm of difference shadow is used to preprocess the collected images; Then based on the SIFT algorithm, combined with improved SUSAN operator, affine transformation, the image mosaic is matched; Finally, the traversal of the shape elements is repealed to obtain the real parameters of the air bubble, so as lo judge whether the valve is qualified. The experiments show that the method improves the bubble detection efficiency, and the detection accuracy reaches 98%, which is suitable for testing the airtightness of the same of valves. [ABSTRACT FROM AUTHOR]

In order to solve the problems of long time consuming and matching rate of SIFT algorithm in electronic label image matching, an image matching algorithm based on improved PCA-SIFT is proposed. Firstly, the key feature points of the image are obtained by SIFT algorithm, and the 128D feature vector is formed, then the K-means clustering is carried out after PCA dimension reduction is used to realize the effective identification of electronic tags, and the invalid pictures are initially eliminated. Finally, RANSAC affine transformation is used to realize the fast matching of electronic tags. The experimental results show that compared with other matching algorithms, the improved algorithm can quickly eliminate invalid pictures, improve the matching efficiency, and has a good detection effect in a more complex environment. Meanwhile, the improved SIFT algorithm based on PCA processing saves the processing time by 0.1 s, it can increase the processing speed by more than 2 times compared with the traditional single SIFT algorithm. The matching rate is increased by 6%, and this method has better matching effect. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Image & Graphics is the property of Editorial Office of Journal of Image & Graphics and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Aiming at the problem that the deep belief network (DBN) is susceptible to the training parameters during the fine-tune process, this paper proposed a kind of batch normalization DBN classification method (BNDBN). Firstly, this method used unsupervised learning to obtain high-level representation of raw data. Then through the introduction of scale transformation and translation transformation parameters, it processed the output characteristics of each layer by batch normalization. And it fed the post-processing characteristics into the nonlinear transformation activation layer. Finally, it trained and studied the parameters of the affine transformation and the original network by using the stochastic gradient descent method. The BNDBN method reduced the dependence of the gradient on the parameter size, which effectively resolved the problem of changing the value distribution of activation function caused by the change of network parameters and improved the training efficiency. To verify the effectiveness of the proposed method, it selected MNIST handwritten database and the USPS handwritten digital identification library for testing. Compared with the Dropout-DBN, DBN, ANN, SVM and KNN, the results show that the proposed method significantly improves the classification accuracy and had stronger feature extraction ability. [ABSTRACT FROM AUTHOR]

The matching accuracy of image-pair features directly affected the efficiency and performance of subsequent image analysis and processing, so it was necessary to purify and filter the feature matching-points of the image-pair. Firstly, using the SIFT(scale-invariant feature transform) algorithm to extract the salient features from the image and established a rough matching relationship. And applying the nearest neighbor ratio to initialize the matching probability. Then, using EM (expectationmaximization) to establish a spatial transformation model between matching-points based on the maximum likelihood of the hybrid model. After the EM iteration converged, utilizing the correspondences to filtered out the wrong matching-points. The experimental results demonstrate that the average accuracy of the proposed method can reach 96. 8%, the average recall rate is 81. 6%, the mean time consumption is 3.1 s. This method is higher than other algorithm on the extracting number of correct matching point-pairs and is robust for most cases including a large viewing angle, image rotation and affine transformation. [ABSTRACT FROM AUTHOR]

As the changing of the face pose, the rate of the face recognition becomes small. Object to the problem, the method which based on affine transformation and image-forming principle corrected the test face images pose to virtual the corresponding font face images. The method could correct the multi-pose face images which angle were among 45°. And the face recognition based on improved SURF (speeded up robust features) got better effect. The experiment shows that the method overcomes the effect of the pose-changing to some degree and the recognition rate is increased by 7. 0%. [ABSTRACT FROM AUTHOR]

A novel control scheme combining the nonlinear track differentiator and extended state observer (ESO) was presented for a class of chaotic systems with non-affine inputs. All uncertainties and external disturbances were modeled in backstepping. The nonlinear track differentiator was employed to approximate the derivative of the virtual control or the reference signals. The ESO was employed to estimate the uncertainties and disturbance in the system, furthermore, the convergence of ESO was proved. The main characteristics of the scheme are that the computation time is much less than other approaches presented in references and the tracking errors are guaranteed to be uniformly asymptotically stable. Foremost, the output of chaotic system can track arbitrary differentiable reference signal. Simulation results of chaotic systems with non-affine inputs, modeled uncertainties and external disturbances illustrate the feasibility and effectiveness of the proposed control method. [ABSTRACT FROM AUTHOR]

Eye movement information can promptly reflect the changes of human psychology and the consciousness tendencies. Although the human eyes are more sensitive than the hands, the image processing speed limits the utilization of frame rate. So it cannot effectively capture the eye movement and has the problem of low accurate rate. Aiming at the existing problems, this paper studied the image matching principle and designed the special eye movement recognition algorithm of multiple monocular templates. Then, it conducted a series of experiments in common interference and showed the data with analysis. Thus see that this algorithm has both perfect computing speed and higher accuracy which has a broad application value as a real-time eye movement recognition algorithm. [ABSTRACT FROM AUTHOR]

Based on the government bonds and corporate bonds trading data from the Shanghai stock exchange from 2003 to 2010, the time series of the yield of government bonds and corporate bonds to different maturities are obtained by solving five factors term structure model. Then two factors and four factors affine processes are respectively used to describe the dynamic change of treasury yields and corporate bond yields, and two factors model of affine term structure of corporate bond are developed. The parameters of the model can be solved with Kalman filtering method, and the dynamic changes of the corporate bond's credit spreads are predicted. Furthermore, the empirical results show that the affine model can describe the dynamic changes of the corporate bond credit spreads relative perfectly, which can provide the method support for pricing corporate bond and its derivates. [ABSTRACT FROM AUTHOR]