Edges Of Objects Research Articles

Non-local affinity adaptive acceleration propagation network for generating dense depth maps from LiDAR.

Depth completion aims to generate dense depth maps from the sparse depth images generated by LiDAR. In this paper, we propose a non-local affinity adaptive accelerated (NL-3A) propagation network for depth completion to solve the mixing depth problem of different objects on the depth boundary. In the network, we design the NL-3A prediction layer to predict the initial dense depth maps and their reliability, non-local neighbors and affinities of each pixel, and learnable normalization factors. Compared with the traditional fixed-neighbor affinity refinement scheme, the non-local neighbors predicted by the network can overcome the propagation error problem of mixed depth objects. Subsequently, we combine the learnable normalized propagation of non-local neighbor affinity with pixel depth reliability in the NL-3A propagation layer, so that it can adaptively adjust the propagation weight of each neighbor during the propagation process, which enhances the robustness of the network. Finally, we design an accelerated propagation model. This model enables parallel propagation of all neighbor affinities and improves the efficiency of refining dense depth maps. Experiments on KITTI depth completion and NYU Depth V2 datasets show that our network is superior to most algorithms in terms of accuracy and efficiency of depth completion. In particular, we predict and reconstruct more smoothly and consistently at the pixel edges of different objects.

Multi-Scale Aggregation Stereo Matching Network Based on Dense Grouping Atrous Convolution

The key to image depth estimation is to accurately find corresponding points between the left and right images. A binocular camera can directly estimate the depth of the left and right image range, which completely avoids the requirement of target recognition accuracy in a monocular depth estimation. However, it is difficult for binocular stereo matching to accurately segment objects and find matching points in the ill-posed areas (weak texture, deformation, object edge, etc.) of the left and right images. In the semantic segmentation task, atrous convolution is used to solve the contradiction between the receptive field and the segmentation accuracy. This research focused on balancing the impact of holes on the segmentation task. In addition, in order to solve the issue where matching points in the ill-posed regions of left and right images are affected by noise, we used a 3D convolution to aggregate the cost volume to obtain better accuracy. However, the 3D convolution method is prone to mismatching in ill-posed areas of the image. To tackle the problems above, we proposed a dense grouping atrous convolution spatial pyramid pooling (DenseGASPP) method. The feature of the DenseGASPP method is that there is a dense connection between the group atrous convolutions to fully integrate feature information. This method can expand the receptive field and balance the effect of holes on the segmentation task. Moreover, we introduced multi-scale cost aggregation into our method, which uses the repeated exchange of information between cost volumes of different scales to obtain rich contextual information and reduce the mismatching of the network. To evaluate the performance of our method, we conducted several groups of typical algorithm experiments on the scene flow and KITTI 2015 standard datasets. From the results, our model achieves better performance, reducing the EPE from 1.09 to 0.67, which improves the mismatching ability of binocular depth estimation algorithm in ill-posed regions.

A progressive segmentation with weight contrast label enhancement for weakly supervised video salient object detection

AbstractScribble labels have gained increasing attention in the field of weakly supervised video salient object detection (VSOD). Based on scribble labels, latest methods can spread labeled pixels to unlabeled regions using local coherence loss, but predicted objects often lose detail and boundary information. In this work, a novel method based on back‐foreground weight contrast is proposed that adds label enhancement points to facilitate the model to learn the edge, detail and location of salient object. Additionally, a new VSOD framework based on global structural localization is introduced. Enhanced scribble labels are used to assist the model for global localization, and then the located regions are finely segmented by the trained model. Extensive experiments demonstrate that the method achieves the state‐of‐the‐art performance on common VSOD datasets, with an improvement of 3.75%, 4.68%, and 0.88% in S‐measure, F‐measure, and MAE, respectively.

Overlap Functions-Based Fuzzy Mathematical Morphological Operators and Their Applications in Image Edge Extraction

As special aggregation functions, overlap functions have been widely used in the soft computing field. In this work, with the aid of overlap functions, two new groups of fuzzy mathematical morphology (FMM) operators were proposed and applied to image processing, and they obtained better results than existing algorithms. First, based on overlap functions and structuring elements, the first group of new FMM operators (called OSFMM operators) was proposed, and their properties were systematically analyzed. With the implementation of OSFMM operators and the fuzzy C-means (FCM) algorithm, a new image edge extraction algorithm (called the OS-FCM algorithm) was proposed. Then, the second group of new FMM operators (called ORFMM operators) was proposed based on overlap functions and fuzzy relations. Another new image edge extraction algorithm (called OR-FCM algorithm) was proposed by using ORFMM operators and FCM algorithm. Finally, through the edge segmentation experiments of multiple standard images, the actual segmentation effects of the above-mentioned two algorithms and relevant algorithms were compared. The acquired results demonstrate that the image edge extraction algorithms proposed in this work can extract the complete edge of foreground objects on the basis of introducing the least noise.

Camouflaged objects detection network via contradiction detection and feature aggregation

Camouflaged Object Detection(COD) aims to segment objects with a similar appearance to the background. There are some problems in existing algorithms, such as blurred edges and incomplete detection. To address the above issues, we propose a novel COD framework termed CFNet. Our network consists of the Contradiction Area Detection Module(CADM) and Feature Aggregation Module(FAM). In the CADM, we propose an improved receptive field mechanism, which utilizes max pooling operation and convolution block to highlight the contradictory areas and refine the edge of the hidden object. Besides, the FAM is designed to connect two adjacent layers via attention and anti-attention strategy, leading to cross-layer feature enhancement and information fusion. More specifically, the self-attention mechanism helps supplement semantic information, and the anti-attention mechanism contributes to removing redundant information. Extensive experiments conducted on the four public COD datasets show the comparable performance of the proposed CFNet with SOTAs, and the ablation experiments demonstrate the effectiveness of the proposed modules.

Prior information-based motion blur image restoration method for the low-frequency sinusoidal vibration measurements with machine vision

The sinusoidal vibration is the basic unit of motion control and measurement, which can constitute the arbitrary plane and space motions and is essential to the low-frequency vibration calibration. At present, the machine vision (MV) method has been widely applied to measure the low-frequency vibration, which can promote the improvement of low-frequency vibration calibration and metrology traceability. However, the MV method is always inevitably affected by the motion blur which decreases its measurement accuracy. In this study, a novel prior information-based motion blur image restoration method is investigated, which applies the known sinusoidal information and the Lucy-Richardson (LR) method with Non-Local (NL)-Means to eliminate the motion blur and improve the measurement accuracy. Meanwhile, the objective evaluation indexes and edge detection method are adopted to verify the restoration effect. Several simulations and actual experiment show that the investigated method can significantly improve the quality of the sinusoidal motion blur images, and further make the accuracies of the edge detection method and MV method increase 0.3 pixel and 0.3%, respectively.

Automation Strategies for the Photogrammetric Reconstruction of Pipelines

A responsible use of energy resources is currently more important than ever. For the effective insulation of industrial plants, a three-camera measurement system was, therefore, developed. With this system, the as-built geometry of pipelines can be captured, which is the basis for the production of a precisely fitting and effective insulation. In addition, the digital twin can also be used for Building Information Modelling, e.g. for planning purposes or maintenance work. In contrast to the classical approach of processing the images by calculating a point cloud, the reconstruction is performed directly on the basis of the object edges in the image. For the optimisation of the, initially purely geometrically calculated components, an adjustment approach is used. In addition to the image information, this approach takes into account standardised parameters (such as the diameter) as well as the positional relationships between the components and thus eliminates discontinuities at the transitions. Furthermore, different automation approaches were developed to facilitate the evaluation of the images and the manual object recognition in the images for the user. For straight pipes, the selection of the object edges in one image is sufficient in most cases to calculate the 3D cylinder. Based on the normalised diameter, the missing depth can be derived approximately. Elbows can be localised on the basis of coplanar neighbouring elements. The other elbow parameters can be determined by matching the back projection with the image edges. The same applies to flanges. For merging multiple viewpoints, a transformation approach is used which works with homologous components instead of control points and minimises the orthogonal distances between the component axes in the datasets.

Optimization of the Preprocessing Method for Edge Detection on Overlapping Cells at PAP Smear Images

The complexity of the cell structure and high overlap cause poor image contrast. Complex imaging factors can make automatic visual interpretation more difficult. Segmentation separates a digital image into different parts with homogeneous attributes so that different areas have different features. The challenges faced in performing nucleus segmentation on Pap Smear (PS) images are poor contrast, the presence of neutrophils, and uneven staining of overlapping cells. This research was conducted to improve image quality in identifying the nucleus accurately. The method used is the Polynomial Contrast Enhancement (PCE) model as an approach to preprocessing. This method functions to change the contrast of the Pap smear image against the overlapping cells so that it becomes a significant contrast in detecting the edge of the nucleus object. The detection process uses the Robert and Prewitt edge detection method to test the identification of the nucleus object on 797 PS Repository images of the University of Nusa Mandiri (RepomedUNM). The accuracy result obtained is 86.8%. Comparing Robert's edge detection and Prewitt's edge detection shows that the PCE approach as a filter method can overcome color contrast problems and detect more accurately. The difficulty in detecting the nucleus from the PS image against the overlapping cells can be solved. This method can distinguish overlapping cells from their core during testing, thus becoming a reference in identifying cells with improved accuracy and testing larger data sets.

RETRACTED ARTICLE: Application of adaptive moving object detection and edge calculation in police physical education training app course

RETRACTED ARTICLE: Application of adaptive moving object detection and edge calculation in police physical education training app course

Evaluation of Single and Dual image Object Detection through Image Segmentation Using ResNet18 in Robotic Vision Applications

This study presents a method for enhancing the accuracy of object detection in industrial automation applications using ResNet18-based image segmentation. The objective is to extract object images from the background image accurately and efficiently. The study includes three experiments, RGB to grayscale conversion, single image processing, and dual image processing. The results of the experiments show that dual image processing is superior to both RGB to grayscale conversion and single image processing techniques in accurately identifying object edges, determining CG values, and cutting background images and gripper heads. The program achieved a 100% success rate for objects located in the workpiece tray, while also identifying the color and shape of the object using ResNet-18. However, single image processing may have advantages in certain scenarios with sufficient image information and favorable lighting conditions. Both methods have limitations, and future research could focus on further improvements and optimization of these methods, including separating objects into boxes of each type and converting image coordinate data into robot working area coordinates. Overall, this study provides valuable insights into the strengths and limitations of different object recognition techniques for industrial automation applications.

Dual-mode adaptive-SVD ghost imaging.

In this paper, we present a dual-mode adaptive singular value decomposition ghost imaging (A-SVD GI), which can be easily switched between the modes of imaging and edge detection. It can adaptively localize the foreground pixels via a threshold selection method. Then only the foreground region is illuminated by the singular value decomposition (SVD) - based patterns, consequently retrieving high-quality images with fewer sampling ratios. By changing the selecting range of foreground pixels, the A-SVD GI can be switched to the mode of edge detection to directly reveal the edge of objects, without needing the original image. We investigate the performance of these two modes through both numerical simulations and experiments. We also develop a single-round scheme to halve measurement numbers in experiments, instead of separately illuminating positive and negative patterns in traditional methods. The binarized SVD patterns, generated by the spatial dithering method, are modulated by a digital micromirror device (DMD) to speed up the data acquisition. This dual-mode A-SVD GI can be applied in various applications, such as remote sensing or target recognition, and could be further extended for multi-modality functional imaging/detection.

Edge-Based Monocular Thermal-Inertial Odometry in Visually Degraded Environments

State estimation in complex illumination environments based on conventional visual-inertial odometry is a challenging task due to the severe visual degradation of the visual camera. The thermal infrared camera is capable of all-day time and is less affected by illumination variation. However, most existing visual data association algorithms are incompatible because the thermal infrared data contains large noise and low contrast. Motivated by the phenomenon that thermal radiation varies most significantly at the edges of objects, the study proposes an ETIO, the first edge-based monocular thermal-inertial odometry, for robust state estimation in visually degraded environments. Instead of the raw image, we utilize the binarized image from edge extraction for pose estimation to overcome the poor thermal infrared image quality. Then, an adaptive feature tracking strategy ADT-KLT is developed for robust data association based on limited edge information and its distance distribution. Finally, a pose graph optimization performs real-time estimation over a sliding window of recent states by combining IMU pre-integration with reprojection error of all edge feature observations. We evaluated the performance of the proposed system on public datasets and real-world experiments and compared it against state-of-the-art methods. The proposed ETIO was verified with the ability to enable accurate and robust state estimation all-day time.

A cascading l0 regularization reconstruction method in nonsubsampled contourlet domain for limited-angle CT

In some computed tomography (CT) practical applications, the projection data is incomplete, which makes some limited-angle artifacts presented in the reconstructed image. Total variation (TV) regularization method is used to suppress the artifacts, but the edge of reconstructed image is distorted or some tiny details are missed. To preserve the edge of reconstructed image, a cascading ℓ0 regularization-based reconstruction model in nonsubsampled contourlet transform (NSCT) domain is proposed, which considers both the directional peculiarity of artifacts and the smooth of low frequency of the reconstructed image. In the proposed reconstruction model, a ℓ0 regularization term in the high frequency is used to suppress the artifacts and noise, and a ℓ0 regularization of gradient image in low frequency is used to suppress the limited-angle artifacts, to preserve the edge of object and to smooth the reconstructed image. To solve the proposed model, a proximal alternating linearized Peaceman–Rachford splitting method (PAL-PRSM) is proposed, which uses the Peaceman–Rachford splitting method that updates the Lagrange multiplier twice, one after each minimization of the subproblem, to deal with the optimization problem firstly, and then the proximal linearization is used to avoid computing the inverse of a huge system matrix. In addition, to compensate the proximal linearization, we add an additional term into Lagrange multiplier updating. Real data experiments are investigated to demonstrate the effectiveness of PAL-PRSM method, and the results show that the proposed method outperforms two other CT reconstruction methods on preserving the edge of reconstructed image. On the whole, the proposed method is a compromise between denoising and preserving the edge of reconstructed image.

Systematic Review of Aggregation Functions Applied to Image Edge Detection

Edge detection is a crucial process in numerous stages of computer vision. This field of study has recently gained momentum due to its importance in various applications. The uncertainty, among other characteristics of images, makes it difficult to accurately determine the edge of objects. Furthermore, even the definition of an edge is vague as an edge can be considered as the maximum boundary between two regions with different properties. Given the advancement of research in image discontinuity detection, especially using aggregation and pre-aggregation functions, and the lack of systematic literature reviews on this topic, this paper aims to gather and synthesize the current state of the art of this topic. To achieve this, this paper presents a systematic review of the literature, which selected 24 papers filtered from 428 articles found in computer databases in the last seven years. It was possible to synthesize important related information, which was grouped into three approaches: (i) based on both multiple descriptor extraction and data aggregation, (ii) based on both the aggregation of distance functions and fuzzy C-means, and (iii) based on fuzzy theory, namely type-2 fuzzy and neutrosophic sets. As a conclusion, this review provides interesting gaps that can be explored in future work.

Self-progress aggregate learning for weakly supervised salient object detection

The task of salient object detection aims to find the most salient object from the samples. In the field of weakly supervised learning, the existing weakly supervised salient object detection (WSSOD) methods often fail to utilize the limited label information (such as self-affinity or edge features, and scale transform) for learning. Therefore, this paper proposes a self-progress aggregate learning method named SPAL. First, the feature optimization scheme of the edge information module is put forward based on analysis of the problems existing in the current convolutional neural network for detection of the edge information of the object. Obviously, the salient object has a low requirement for high-level information, In particular, in order to improve the utilization rate of the network structure without increasing its complexity, the affinity global context is design in view of the particularity of the structure of a salient object. The structure of a salient object not only depends on the deep-level semantic feature information to a certain extent, but also has a certain guiding effect on the object position and edge information. Second, high-level affinity information is used to complement the slight-level edge information globally, and the scale attention module is adopted to guide the network to adapt the multi-scale reinforcement feature learning ability for the salient object regions. Our method SPAL achieved better experimental results than the other competitive models for comparison on five benchmark data sets (i.e. for DUTS-TEST, compared with CCFNet our method achieved an improvement of 0.6% for mean absolute error (MAE), 5.1% for Fb, and 1.1% for Eℰ ), which demonstrates the effectiveness of our proposed method.

An incremental facility location clustering with a new hybrid constrained pseudometric

The Euclidean metric, one of the classical similarity measures applied in clustering algorithms, has drawbacks when applied to spatial clustering. The resulting clusters are spherical and similarly sized, and the edges of objects are considerably smoothed. This paper proposes a novel hybrid constrained pseudometric formed by the linear combination of the Euclidean metric and a pseudometric plus penalty. The pseudometric is used in a new deterministic incremental heuristic facility location algorithm (IHFL). Our method generates larger, isotropic, and partially overlapping clusters of different sizes and spatial densities, better adapting to the surface complexity than the classical non-deterministic clustering. Cluster properties are used to derive new features for supervised/unsupervised learning. Possible applications are the classification of point clouds, their simplification, detection, filtering, and extraction of different structural patterns or sampled objects. Experiments were run on point clouds derived from laser scanning and images.

Miper-MVS: Multi-scale iterative probability estimation with refinement for efficient multi-view stereo

Multi-view stereo reconstruction aims to construct 3D scenes from multiple 2D images. In recent years, learning-based multi-view stereo methods have achieved significant results in depth estimation for multi-view stereo reconstruction. However, the current popular multi-stage processing method cannot solve the low-efficiency problem satisfactorily owing to the use of 3D convolution and still involves significant amounts of calculation. Therefore, to further balance the efficiency and generalization performance, this study proposed a multi-scale iterative probability estimation with refinement, which is a highly efficient method for multi-view stereo reconstruction. It comprises three main modules: 1) a high-precision probability estimator, dilated-LSTM that encodes the pixel probability distribution of depth in the hidden state, 2) an efficient interactive multi-scale update module that fully integrates multi-scale information and improves parallelism by interacting information between adjacent scales, and 3) a Pi-error Refinement module that converts the depth error between views into a grayscale error map and refines the edges of objects in the depth map. Simultaneously, we introduced a large amount of high-frequency information to ensure the accuracy of the refined edges. Among the most efficient methods (e.g., runtime and memory), the proposed method achieved the best generalization on the Tanks & Temples benchmarks. Additionally, the performance of the Miper-MVS was highly competitive in DTU benchmark. Our code is available at https://github.com/zhz120/Miper-MVS.

Total dominator total chromatic numbers of cycles and paths

The total dominator total coloring of a graph is a total coloring of the graph such that each object (vertex or edge) of the graph is adjacent or incident to every object of some color class. The minimum number of the color classes of a total dominator total coloring of a graph is called the total dominator total chromatic number of the graph. In (A.P. Kazemi, F. Kazemnejad and S. Moradi, Contrib. Discrete Math. (2022).), the authors initiated to study the total dominator total coloring of a graph and found some useful results, and presented some problems. Finding the total dominator total chromatic numbers of cycles and paths were two of them which we consider them here.

RGB-T Semantic Segmentation With Location, Activation, and Sharpening

Semantic segmentation is important for scene understanding. To address the scenes of adverse illumination conditions of natural images, thermal infrared (TIR) images are introduced. Most existing RGB-T semantic segmentation methods follow three cross-modal fusion paradigms, i.e. encoder fusion, decoder fusion, and feature fusion. Some methods, unfortunately, ignore the properties of RGB and TIR features or the properties of features at different levels. In this paper, we propose a novel feature fusion-based network for RGB-T semantic segmentation, named \emph{LASNet}, which follows three steps of location, activation, and sharpening. The highlight of LASNet is that we fully consider the characteristics of cross-modal features at different levels, and accordingly propose three specific modules for better segmentation. Concretely, we propose a Collaborative Location Module (CLM) for high-level semantic features, aiming to locate all potential objects. We propose a Complementary Activation Module for middle-level features, aiming to activate exact regions of different objects. We propose an Edge Sharpening Module (ESM) for low-level texture features, aiming to sharpen the edges of objects. Furthermore, in the training phase, we attach a location supervision and an edge supervision after CLM and ESM, respectively, and impose two semantic supervisions in the decoder part to facilitate network convergence. Experimental results on two public datasets demonstrate that the superiority of our LASNet over relevant state-of-the-art methods. The code and results of our method are available at https://github.com/MathLee/LASNet.

Salient Object Detection based on Background Optimization

Aiming at the problems of low detection accuracy and blurred object edges in current salient object detection based on background algorithms, a new algorithm based on boundary prior to estimate background is proposed. Firstly, the super-pixel image segmentation algorithm (SLIC) is used to segment the image into super-pixels. According to the theory that the foreground and background are relative, the background is estimated by using the four-edges boundary prior of the image; At the same time, an optimal fusion algorithm is proposed to fuse the prior background and foreground with optimal weights to obtain the final saliency map. Quantitative and qualitative comparisons with 10 classic salient object detection algorithms, the results show that the proposed algorithm can not only detect salient objects of different sizes more accurately, but also effectively suppress background redundant information, preserving the object boundary. Therefore, the accuracy of our algorithm is better than 10 classical algorithms. The algorithm in this paper which serve as pre-processing for computer vision has great promise in the field of intelligent control of machine vision.