Pyramid Algorithm Research Articles

Image Color Balance with Laplacian and Gaussian Pyramid (CBLGP) Algorithm

In recent times, technology has rapidly and significantly evolved across all sectors. Digital image processing stands out as a modern technology aimed at achieving clear images. However, digitized images often encounter issues of low quality, such as unclear or underwater images that require enhancement for better visibility. These problems stem from factors like deficient focusing, lighting, and various constraints leading to low contrast, shading, and artifacts. Underwater and satellite images consistently face less-than-ideal conditions due to environmental factors like light refraction in water, particle scattering, and dust in aquatic environments. Similarly, challenges in space, such as poor illumination and lack of contrast, further complicate image analysis. Overcoming these obstacles is crucial for extracting valuable information, necessitating advanced processing techniques. This paper introduces an enhanced Gaussian/Laplace color balance-fusion algorithm designed to improve image visibility. Modifications to certain equations result in sharper and clearer images. The algorithm begins by determining the white balance of the input RGB color image and subsequently enhances its intensity. Edge improvement is carried out separately using a depth filter. The weights for each image are then determined and combined to form a Laplace Pyramid. A color restoration technique is applied to process the resulting image, producing the final enhanced image. While existing methods for image contrast enhancement typically focus on image features, they often neglect user characteristics. This paper explores the application of image sharpening, a prominent image enhancement technique, in clearing underwater or low-quality images using the proposed algorithm. Keywords: EDSHE, High pass filter, White patch ratix, Laplacian pyramid, Color restoration.

Deep Learning Techniques for Spatiotemporal Weighted Pose Taekwondo Features and Their Application in Tactical Analysis

Taekwondo behavior recognition has become a popular study issue in the past few decades due to its vast range of applications in the visual realm. The research of Taekwondo behavior recognition based on skeleton sequences has received increasing attention in recent years due to the widespread use of depth sensors and the development of real-time skeleton estimate methods based on depth images. In order to characterize the behavioral sequences, the majority of research work currently in existence extracts the spatial domain information of various skeleton joints within frames and the temporal domain information of the skeleton joints between frames. However, this research work ignores the fact that different joints and postures play different roles in determining the behavioral categories. Consequently, this paper presents a spatio-temporal weighted gesture Taekwondo features-based approach for Taekwondo recognition that employs a bilinear classifier to iteratively compute the weights of the static gestures and joint points relative to the action category in order to identify the joint points and gestures with high information content; concurrently, this paper introduces dynamic temporal regularization and Fourier time pyramid algorithms for temporal modeling in order to provide a better temporal analysis of the behavioural features, and ultimately employs support vector machines to complete the behavioural classification. According to experimental results on several datasets, this strategy outperforms certain other methods in terms of recognition accuracy and is highly competitive.

Influence of train-generated vibrations on embankment

Roads and railway lines are often constructed on different geotechnical structures such as tunnels, cuttings, and/or embankments. Three main parts are necessary to consider to evaluate vibration: the source of vibrations, vibration propagation path, and receiver of the signal. This paper describes a review of the influence of train-generated vibrations on an embankment and a building in the surroundings. The first presented case study documents an interpretation of seismic signal in the frequency domain using wavelet transform. The algorithm, which we apply to the computation of the wavelet transform of the velocity component record, is based on the pyramidal algorithm, and the result of this procedure is used for an interpretation of data. The discrete wavelet transform was applied to the construction of a 3-dimension mapping of the time-frequency decomposition. An example of the numerical model on the FEM method (the MIDAS GTS software) shows the vertical displacement of the embankment body during the movement of a train. The creation of these models is strictly based on the results of experimental seismological measurements. Then, the source of vibration is represented by a typical train/vehicle that runs on the nearest part of the railway/road at the most efficient velocity.

An Improved Visual SLAM Method with Adaptive Feature Extraction

The feature point method is the mainstream method to accomplish inter-frame estimation in visual Simultaneous Localization and Mapping (SLAM) methods, among which the Oriented FAST and Rotated BRIEF (ORB) feature-based method provides an equilibrium of accuracy as well as efficiency. However, the ORB algorithm is prone to clustering phenomena, and its unequal distribution of extracted feature points is not conducive to the subsequent camera tracking. To solve the above problems, this paper suggests an adaptive feature extraction algorithm that first constructs multiple-scale images using an adaptive Gaussian pyramid algorithm, calculates adaptive thresholds, and uses an adaptive meshing method for regional feature point detection to adapt to different scenes. The method uses Adaptive and Generic Accelerated Segment Test (AGAST) to speed up feature detection and the non-maximum suppression method to filter feature points. The feature points are then divided equally by a quadtree technique, and the orientation of those points is determined by an intensity centroid approach. Experiments were conducted on publicly available datasets, and the outcomes demonstrate the algorithm has good adaptivity and solves the problem of a large number of corner point clusters that may result from using manually set detection thresholds. The RMSE of the absolute trajectory error of SLAM applying this method on four sequences of TUM RGB-D datasets is decreased by 13.88% when compared with ORB-SLAM3. It is demonstrated that the algorithm provides high-quality feature points for subsequent image alignment, and the application to SLAM improves the reliability and accuracy of SLAM.

A Novel Decoupled Feature Pyramid Networks for Multi-Target Ship Detection.

The efficiency and accuracy of ship detection is of great significance to ship safety, harbor management, and ocean surveillance in coastal harbors. The main limitations of current ship detection methods lie in the complexity of application scenarios, the difficulty in diverse scales object detection, and the low efficiency of network training. In order to solve these problems, a novel multi-target ship detection method based on a decoupled feature pyramid algorithm (DFPN) is proposed in this paper. First, a feature decoupling module is introduced to separate ship contour features and position features from the multi-scale fused features, to overcome the problem of similar features in multi-target ships. Second, a feature pyramid structure combined with a gating attention module is constructed to improve the feature resolution of small ships by enhancing contour features and spatial semantic information. Finally, a feature pyramid-based multi-feature fusion algorithm is proposed to improve the adaptability of the network to changes in ship scale according to the contextual relationship of ship features. Experiments on the multi-target ship detection dataset showed that the proposed method increased by 6.3% mAP and 20 FPS higher than YOLOv4, 7.6% mAP and 36 FPS higher than Faster-R-CNN, 5% mAP and 36 FPS higher than Mask-R-CNN, and 4.1% mAP and 35 FPS higher than DetectoRS. The results demonstrate that the DFPN can detect multi-target ships in different scenes with high accuracy and a fast detection speed.

Dance Rehearsal System Based on Linear Partial Differential Mathematical Equation

Abstract In this paper, a linear partial differential mathematical choreography model is proposed for the accuracy of action recognition in dance rehearsal systems. This paper more accurately represents the action change features. The article uses the pyramid algorithm (LK) to calculate pixels’ optical flow vector change in dt time. Then this paper adopts a multi-feature fusion module to fuse multi-channel features. Finally, the system completes the accurate identification of dance choreography movements. The research results show that the algorithm can perform dance movement recognition. The dance rehearsal system realizes the movement correction of dancers.

MSINet: Mining scale information from digital surface models for semantic segmentation of aerial images

Compared with other kinds of images, aerial images have more obvious object scale distinction and larger resolution, which results in that the whole scale information of aerial images can hardly be explored. To address this difficulty, we develop a novel network based on the digital surface models (DSMs) of aerial images in this paper. The proposed network termed MSINet can efficiently mine scale information through the DSMs from two aspects. Firstly, we propose an interpolation pyramid algorithm to encode the scale information from the DSMs and hence provide a scale prior information to the normal segmentation network. The interpolation pyramid algorithm implements interpolation operations with different scales on the DSMs and detects the pixel value change after the interpolation operations. Objects with different scales will express diverse changes, which provides useful information to encode their scale information. Secondly, aiming to address the problem that the DSMs contain a large amount of noise in the boundary part, a spatial information enhancement module and a mutual-guidance module are developed in this paper. These two modules can fix the misleading guidance information caused by the noise in the boundary part of the DSMs and hence achieve more accurate scale information inserting. The extensive experimental results prove that our methods can outperform other competitors in terms of qualitative and quantitative performance.

Proton Radiation Effects of CMOS Image Sensors on Different Star Map Recognition Algorithms for Star Sensors

Star sensors are widely used by satellites for their precise pointing accuracy. However, protons in space will cause cumulative effects and single-event transients in the imaging systems of star sensors. These effects will affect the success rate of star map recognition of star sensors. In this paper, proton irradiation experiments and field tests were carried out in turn, and three typical star recognition algorithms were used to recognize the star maps. The results showed that cumulative effects led to a decrease in the number of identifiable stars, which greatly affected the recognition success rate of the grid algorithm. Hot pixels caused by displacement damage effects increased the star centroid positioning error, leading to a decrease in the recognition success rate of the triangle algorithm and pyramid algorithm. Single-event transients produced by protons hitting the image sensor are similar to the grayscale value and shape of a star, and were recognized as “false stars”, which had a significant impact on the success rate of the three recognition algorithms. In general, the pyramid algorithm was more effective than the other two algorithms in identifying the affected star map, and the recognition success rate of the grid algorithm was significantly reduced.

BiRPN-YOLOvX: A weighted bidirectional recursive feature pyramid algorithm for lung nodule detection.

Lung cancer has the second highest cancer mortality rate in the world today. Although lung cancer screening using CT images is a common way for early lung cancer detection, accurately detecting lung nodules remains a challenged issue in clinical practice. This study aims to develop a new weighted bidirectional recursive pyramid algorithm to address the problems of small size of lung nodules, large proportion of background region, and complex lung structures in lung nodule detection of CT images. First, the weighted bidirectional recursive feature pyramid network (BiPRN) is proposed, which can increase the ability of network model to extract feature information and achieve multi-scale fusion information. Second, a CBAM_CSPDarknet53 structure is developed to incorporate an attention mechanism as a feature extraction module, which can aggregate both spatial information and channel information of the feature map. Third, the weighted BiRPN and CBAM_CSPDarknet53 are applied to the YOLOvX model for lung nodule detection experiments, named BiRPN-YOLOvX, where YOLOvX represents different versions of YOLO. To verify the effectiveness of our weighted BiRPN and CBAM_ CSPDarknet53 algorithm, they are fused with different models of YOLOv3, YOLOv4 and YOLOv5, and extensive experiments are carried out using the publicly available lung nodule datasets LUNA16 and LIDC-IDRI. The training set of LUNA16 contains 949 images, and the validation and testing sets each contain 118 images. There are 1987, 248 and 248 images in LIDC-IDRI's training, validation and testing sets, respectively. The sensitivity of lung nodule detection using BiRPN-YOLOv5 reaches 98.7% on LUNA16 and 96.2% on LIDC-IDRI, respectively. This study demonstrates that the proposed new method has potential to help improve the sensitivity of lung nodule detection in future clinical practice.

Generalized de Boor–Cox Formulas and Pyramids for Multi-Degree Spline Basis Functions

The conventional B-splines possess the de Boor–Cox formula, which relates to a pyramid algorithm. However, for multi-degree splines, a de Boor–Cox-type evaluation algorithm only exists in some special cases. This paper considers any multi-degree spline with arbitrary degree and continuity, and provides two generalized de Boor–Cox-type relations. One uses several lower degree polynomials to build a combination to evaluate basis functions, whose form is similar to using the de Boor–Cox formula several times. The other is a linear combination of two functions out of the recursive definition, which keeps the combination coefficient polynomials of degree 1, so it is more similar to the de Boor–Cox formula and can be illustrated by several pyramids with different heights. In the process of calculating the recursions, a recursive representation using the Bernstein basis is used and numerically analyzed.

3-D Structure-Oriented Adaptive Gaussian Pyramid for Seismic Multiscale Fracture Detection

Gaussian pyramid (GP) has the property of decomposing the 2D data into multiple scales. It has been successfully applied in image processing, but rarely used in seismic data processing and interpretation. Specifically, seismic data is not just a 2D image in one time slice or horizon. Moreover, the pattern of geological body varies rapidly in 3D spaces. Hence, the classical GP method exists a limitation in processing 3D seismic data. Especially in fracture detection, the 2D isotropic Gaussian kernel used in GP tends to blur the fracture details. In this letter, to match the high dimensional seismic data, we propose a structure-oriented adaptive Gaussian pyramid (SOA-GP) algorithm, which expand the 2D GP method to 3D situation. In this case, to eliminate the influence of transverse change of wave impedance and consider stratigraphic characteristics, the 2D Gaussian filter is also substituted by the 3D structure adaptive anisotropic Gaussian kernel, which is constructed by instantaneous phase-based gradient structure tensor (GST) method. Meanwhile, seismic attributes are applied to the multi-resolution seismic data decomposed by SOA-GP method to realize multi-scale fracture detection. Finally, we apply this new 3D SOA-GP method to a field data. It demonstrates that the multi-scale decomposition of the new method could produce more details of fracture and less disturbs from noise.

Fusion of remote sensing images based on multi-resolution analysis

A fast and reliable fusion algorithm is the key to the practical application of image fusion technology, so the research of the fast fusion algorithm with a good fusion effect is particularly important. Based on the multi-resolution analysis, this paper discusses the principles of the PCNN fusion algorithm, wavelet transform and Laplace pyramid algorithm, and then performs image fusion experiments. Experimental results show that the fusion effect of the wavelet transform and PCNN algorithm is significantly higher than that of the Laplace pyramid algorithm.

3D face recognition algorithm based on deep Laplacian pyramid under the normalization of epidemic control

Under the normalization of epidemic control in COVID-19, it is essential to realize fast and high-precision face recognition without feeling for epidemic prevention and control. This paper proposes an innovative Laplacian pyramid algorithm for deep 3D face recognition, which can be used in public. Through multi-mode fusion, dense 3D alignment and multi-scale residual fusion are ensured. Firstly, the 2D to 3D structure representation method is used to fully correlate the information of crucial points, and dense alignment modeling is carried out. Then, based on the 3D critical point model, a five-layer Laplacian depth network is constructed. High-precision recognition can be achieved by multi-scale and multi-modal mapping and reconstruction of 3D face depth images. Finally, in the training process, the multi-scale residual weight is embedded into the loss function to improve the network’s performance. In addition, to achieve high real-time performance, our network is designed in an end-to-end cascade. While ensuring the accuracy of identification, it guarantees personnel screening under the normalization of epidemic control. This ensures fast and high-precision face recognition and establishes a 3D face database. This method is adaptable and robust in harsh, low light, and noise environments. Moreover, it can complete face reconstruction and recognize various skin colors and postures.

A non-uniform illumination image enhancement method based on fusion of events and frames

The dynamic range of standard frame-based cameras is much smaller than that of natural scenes. Images captured by standard cameras in non-uniform illumination scenes may be over-exposure, under-exposure, or a combination of both, limiting the visibility of the images. Enhancing images with uneven illumination is a tough assignment. Although most of the existing non-uniform illumination image enhancement methods can preserve details well in dark areas, they cannot regain details in bright regions and may produce noise and halos. Event cameras have a higher dynamic range and are less affected by scene lighting than standard cameras. In this paper, we utilize the complementary advantages of event cameras and standard cameras to improve the visibility of unevenly illumination images, enhance the brightness of dark areas, and recover details in bright areas. First, events and frames are converted into intensity frames by corresponding preprocessing methods, which are subjected to a gamma correction operation to obtain artificial multi-exposure image sequences. Then, the weight map of each artificially exposed image is designed using several evaluation terms, namely contrast, well-exposure, and average brightness. After that, the weight terms are combined with the Laplacian pyramid algorithm to get a fused image. Finally, the final image is created by color restoration and contrast enhancement. Quantitative and qualitative experimental results demonstrate that our method enhances the details and visibility of non-uniform illumination images more effectively than several contrast algorithms.

Ellipse Crater Recognition for Lost-in-Space Scenario

In the field of deep space exploration, a crater recognition algorithm is key to landing navigation based on craters. When there is only visual information, determining how to identify the crater and provide the initial pose of the lander for a lost-in-space (LIS) scenario is a difficulty in terrain relative navigation (TRN). In this paper, a fast and robust crater recognition method for absolute pose estimation based on projective invariants is proposed, which can provide an accurate initial pose for tracking navigation. First, the method selects navigation craters to establish a small-capacity and high-efficiency crater database, and crater pair serial numbers and projective invariants are stored. Second, our method uses a dynamic threshold to solve the problem that the projective invariants are sensitive to noise. Then, an iterative pyramid algorithm is proposed to quickly filter redundancies. Using a dynamic threshold, the matching rate was increased by at least 10%, and the average processing speed was increased by 40%. When the detection errors of the major and minor axes of the ellipse reached 5%, the detection error of the center point reached 1 pixel, and the tilt angle error reached 5°; the matching rate was still >80%. Finally, the pose was estimated by solving the perspective-n-point (PNP) problem based on the recognized craters. The initial pose error in the simulation environment was less than 2°, and the position error was less than 44 m.

Fast and Robust Star Identification Using Color Ratio Information

Star identification is a critical technology in the research of star sensors. Conventional star identification algorithms identify stars based only on the geometry position information. As a result, these algorithms are sensitive to positional noise or require a high number of imaged stars in the field of view (FOV). In this article, a star identification algorithm using color ratio information is proposed to solve this problem. An analytical model is developed to predict the performance of the proposed algorithm. In addition, an optimized strategy is proposed to reduce the identification time by selecting stars with the same color ratio information to construct the observation triangles. Experimental results on simulation and real sky images show that the proposed algorithm is robust to high-level position noise, and it requires three stars to find a unique match. Compared with the pyramid algorithm, the proposed algorithm uses fewer stars and achieves a higher star identification rate over the entire sky in a shorter time even under harsh conditions.

Combination of different observation types through a multi-resolution representation of the regional gravity field using the pyramid algorithm and parameter estimation

The optimal combination of different types of gravity observations is the key to obtaining a high-resolution and high-precision regional gravity model. Current studies based on spherical radial basis functions (SRBFs) majorly consider a single-level approach for data combination. Despite the promising results reported in numerous publications, it has been suspected that the single-level model might be biased towards high-resolution measurements. Instead, a multi-resolution representation (MRR) can be applied to further take into consideration the varying spectral sensitivities of different observation techniques. In this study, we develop a new MRR scheme based on the pyramid algorithm and sequential parameter estimation. We propose strategies to solve the challenges in the practical application of the pyramid algorithm, and this study represents its first successful realization in regional gravity field modeling. The modeling results based on both simulated and real gravity data show that either the single-level approach or the MRR without pyramid algorithm is able to capture gravity information from lower resolution measurements as sufficient as our newly developed MRR algorithm. In the simulated case, the RMS error w.r.t. the validation data obtained by the MRR based on the pyramid algorithm decreases by 50% and 35%, in comparison to that of the single-level model and the MRR without pyramid algorithm, respectively. In the real case, the improvement achieved by the MRR based on the pyramid algorithm is 35% and 23% in the onshore area, and it reaches 63% and 57% in the offshore area, compared to the single-level approach and the MRR without pyramid algorithm, respectively.

Polarimetric Chaotic Ground Penetrating Radar for Underground Pipes Detection

A polarimetric chaotic ground penetrating radar (GPR) is proposed to improve the detection accuracy of underground pipes. In this radar system, the chaotic signal is used as the probe signal and the multi-polarization detection mode is employed to gather the GPR data. Furthermore, the laplacian pyramid algorithm is applied to fuse multi-polarization components. The simulations demonstrate that by using the polarization chaotic GPR, the pipe responses are enhanced and their shape and distribution can be accurately obtained. Here, the information entropy, average gradient, spatial frequency, and standard deviation are introduced to quantitatively evaluate the imaging results. The corresponding experiment is consistent with the simulation. Additionally, to verify the performance of the polarimetric chaotic GPR, we compare the polarimetric chaotic GPR with the polarimetric stepped frequency continuous wave GPR. The experimental results show that the proposed radar improves the detection accuracy and enlarges the detection range.

Feature pyramid self-attention network for respiratory motion prediction in ultrasound image guided surgery.

The robot-assisted automated puncture system under ultrasound guidance can well improve the puncture accuracy in ablation surgery. The automated puncture system requires advanced definition of the puncture location, while the displacement of thoracic-abdominal tumors caused by respiratory motion makes it difficult for the system to locate the best puncture position. Predicting tumor motion is an effective way to help the automated puncture system output a more accurate puncture position. In this paper, we propose a self-attention-based feature pyramid algorithm FPSANet for time-series forecasting, which can extract both linear and nonlinear dependencies of time series. Firstly, we use the temporal convolutional network as the backbone to extract different scale time-series features, and the self-attention module is followed to weigh more significant features to improve nonlinear prediction. Secondly, we use autoregressive models to perform linear prediction. Finally, we directly combine the above two kinds of predictions as the final prediction. FPSANet is trained and tested on our private datasets captured from clinical individuals, and we predict the target position after 50ms, 150ms, 300ms and 400ms. The result shows the evaluation criteria of the MAE is less than 1mm at 50ms and 150ms, and less than 2mm at 300ms. Compared with the AR model, bidirectional LSTM and RVM, our method not only outperforms both models in accuracy (AR: ~ 7.7%; bidirectional LSTM: ~ 75.9%; RVM: ~ 76.5%) but is also more stable on different types of respiratory curves. Respiratory motion in the liver in actual clinical practice vary widely from person to person, while sometimes having less distinct periodic patterns. Under these conditions, our algorithm has the advantage of excellent stability for prediction on various sequences, and its running time of performing single sequence prediction can meet clinical requirements.

Analysis of Main Movement Characteristics of Hip Hop Dance Based on Deep Learning of Dance Movements.

In order to explore the main action characteristics of hip hop dance, a deep learning recognition system based on dance action is proposed. The network is based on convolution, pooling, and full connection calculation in a convolutional neural network (CNN). On the one hand, the pixel information in the video frame is extracted as the network input feature in the spatial domain. On the other hand, in the time domain, in order to better represent the change characteristics of video actions, optical flow information is introduced, and the optical flow vector change of pixels in DT time is calculated by the pyramid algorithm (LK) as the time domain convolution feature. In order to evaluate the performance of the network, this article takes the recognition of dance movements as an example to test the application of the algorithm. The test dataset contains 101 fully identified dance movements. The test results show that the proposed algorithm is 10.90% higher than F1 of inception V3, and the recognition accuracy is 10.85% and 5.27% higher than that of inception V3 and 3D-CNN networks, respectively. For the problems and difficulties brought by single-mode video action recognition, a multimodal action recognition method is introduced to achieve better results based on a large number of training data. Different depth networks have different characteristics. CNN network pays more attention to the relationship between local information, so it is suitable for image recognition and detection tasks. The RNN network is expanded in the time dimension, so it is suitable for the modal information related to similar videos. Therefore, based on multimodal information and a depth neural network, a depth feature extraction and fusion method for multimodal information is designed. Different methods of feature extraction and fusion are tried in the experiment, and the experimental results are analyzed. It proves that the deep learning and recognition of dance movement can effectively explore the main movement characteristics of hip hop dance.