Edges Of Objects Research Articles

MSRMNet: Multi-scale skip residual and multi-mixed features network for salient object detection

The current models for the salient object detection (SOD) have made remarkable progress through multi-scale feature fusion strategies. However, the existing models have large deviations in the detection of different scales, and the target boundaries of the prediction images are still blurred. In this paper, we propose a new model addressing these issues using a transformer backbone to capture multiple feature layers. The model uses multi-scale skip residual connections during encoding to improve the accuracy of the model’s predicted object position and edge pixel information. Furthermore, to extract richer multi-scale semantic information, we perform multiple mixed feature operations in the decoding stage. In addition, we add the structure similarity index measure (SSIM) function with coefficients in the loss function to enhance the accurate prediction performance of the boundaries. Experiments demonstrate that our algorithm achieves state-of-the-art results on five public datasets, and improves the performance metrics of the existing SOD tasks. Codes and results are available at: https://github.com/xxwudi508/MSRMNet.

Photo-Aligned Ferroelectric Liquid Crystal Fork Grating-Mediated Fast Switchable Spiral Phase Contrast Imaging

Extensive research has been devoted to spiral phase contrast imaging because of its notable capacity to enhance the edges of both phase and amplitude objects. We demonstrate a setup using ferroelectric liquid crystal (FLC) fork grating (FG) to enable switchable spiral phase contrast imaging within sub-milli-second responses. This system enables the electrical toggling between images featuring edge enhancement and those without it. The specially designed FLC FG generates a vortex beam while in a diffractive state and transmits a Gaussian beam when in a transmissive state. Using a two-step photo-alignment method, the produced FLC FG exhibits exceptional efficiency at approximately 35% and impressively rapid switching at around 307 μs. By introducing this method, we expand the potential applications of spiral phase contrast imaging, particularly in fields such as bio-sensing and photonics.

A comprehensive review on helmet detection and number plate recognition approaches

Motorbikes serve as the primary mode of transportation in most countries as they are cost effective and appropriate for a nuclear family. But it has been observed that more than 70% of the users do not prefer to wear safety helmets for various reasons jeopardizing their lives and falling prey to accidents. The most prevalent method for ensuring this right now is traffic police manually monitoring the motorcyclists. But due to excess traffic and limited traffic personnels, many violators go unrecognized and continue to practice the same. Thus, it is important to eliminate the human intervention and automate the monitoring system using deep learning and computer vision-based techniques. Our proposed system implements this by extracting number plate of helmet violators and generates an e-challan on the registered mobile number. We propose using a custom trained YOLO-v8 model for violation detection and YOLO-v8 + EasyOCR for number plate detection and extraction. Canny Edge Detection is a preprocessing step that can be used to enhance the edges of objects in an image, making them more distinguishable. This system holds great potential for enhancing safety-related policies and ensuring strict enforcement of traffic regulations. Additionally, it contributes to the advancement of traffic management through the implementation of an AI-based automated traffic violation and ticketing system.

Neuromorphic Imaging With Joint Image Deblurring and Event Denoising.

Neuromorphic imaging reacts to per-pixel brightness changes of a dynamic scene with high temporal precision and responds with asynchronous streaming events as a result. It also often supports a simultaneous output of an intensity image. Nevertheless, the raw events typically involve a large amount of noise due to the high sensitivity of the sensor, while capturing fast-moving objects at low frame rates results in blurry images. These deficiencies significantly degrade human observation and machine processing. Fortunately, the two information sources are inherently complementary - events with microsecond-level temporal resolution, which are triggered by the edges of objects recorded in a latent sharp image, can supply rich motion details missing from the blurry one. In this work, we bring the two types of data together and introduce a simple yet effective unifying algorithm to jointly reconstruct blur-free images and noise-robust events in an iterative coarse-to-fine fashion. Specifically, an event-regularized prior offers precise high-frequency structures and dynamic features for blind deblurring, while image gradients serve as a kind of faithful supervision in regulating neuromorphic noise removal. Comprehensively evaluated on real and synthetic samples, such a synergy delivers superior reconstruction quality for both images with severe motion blur and raw event streams with a storm of noise, and also exhibits greater robustness to challenging realistic scenarios such as varying levels of illumination, contrast and motion magnitude. Meanwhile, it can be driven by much fewer events and holds a competitive edge at computational time overhead, rendering itself preferable as available computing resources are limited. Our solution gives impetus to the improvement of both sensing data and paves the way for highly accurate neuromorphic reasoning and analysis.

EGMT-CD: Edge-Guided Multimodal Transformers Change Detection from Satellite and Aerial Images

Change detection from heterogeneous satellite and aerial images plays a progressively important role in many fields, including disaster assessment, urban construction, and land use monitoring. Currently, researchers have mainly devoted their attention to change detection using homologous image pairs and achieved many remarkable results. It is sometimes necessary to use heterogeneous images for change detection in practical scenarios due to missing images, emergency situations, and cloud and fog occlusion. However, heterogeneous change detection still faces great challenges, especially using satellite and aerial images. The main challenges in satellite and aerial image change detection are related to the resolution gap and blurred edge. Previous studies used interpolation or shallow feature alignment before traditional homologous change detection methods, which ignored the high-level feature interaction and edge information. Therefore, we propose a new heterogeneous change detection model based on multimodal transformers combined with edge guidance. In order to alleviate the resolution gap between satellite and aerial images, we design an improved spatially aligned transformer (SP-T) with a sub-pixel module to align the satellite features to the same size of the aerial ones supervised by a token loss. Moreover, we introduce an edge detection branch to guide change features using the object edge with an auxiliary edge-change loss. Finally, we conduct considerable experiments to verify the effectiveness and superiority of our proposed model (EGMT-CD) on a new satellite–aerial heterogeneous change dataset, named SACD. The experiments show that our method (EGMT-CD) outperforms many previously superior change detection methods and fully demonstrates its potential in heterogeneous change detection from satellite–aerial images.

BACKPACK SYSTEM FOR CAPTURING 3D POINT CLOUDS OF FORESTS

Abstract. A 3D model can be useful for inventory management and monitoring of forests. For this task, we present our prototype mobile mapping backpack system for collecting 3D point clouds of forest vegetation. However, data collection in forests is challenging due to unreliable GNSS positioning, moving objects caused by winds, unclear object edges, and uneven ground to walk on. We include LiDAR and IMU with Simultaneous Localisation and Mapping (SLAM). We describe in detail our backpack system, its development for the forest environment, and evaluate it. Furthermore, we compare two open code SLAM algorithms for ROS, as well as data collection and laser scan quality between TLS and MLS for forest environments. Finally, we installed and tested the MicaSense multi-spectral camera on our backpack and discuss the advantages and drawbacks of it. We conclude, that the backpack is convenient to use in forest environments and produces a good point cloud. It can be carried easily off trail and on rough terrain. The system needs less storage space, computation and less collection time than TLS.

Wavelet Approximation-Aware Residual Network for Single Image Deraining.

It has been made great progress on single image deraining based on deep convolutional neural networks (CNN). In most existing deep deraining methods, CNNs aim to learn a direct mapping from rainy images to clean rain-less images, and their architectures are becoming more and more complex. However, due to the limitation of mixing rain with object edges and background, it is difficult to separate rain and object/background, and the edge details of the image cannot be effectively recovered in the reconstruction process. To address this problem, we propose a novel wavelet approximation-aware residual network (WAAR), wherein rain is effectively removed from both low-frequency structures and high-frequency details at each level separately, especially in low-frequency sub-images at each level. After wavelet transform, we propose novel approximation aware (AAM) and approximation level blending (ALB) mechanisms to further aid the low-frequency networks at each level recover the structure and texture of low-frequency sub-images recursively, while the high-frequency network can effectively eliminate rain streaks through block connection and achieve different degrees of edge detail enhancement by adjusting hyperparameters. In addition, we also introduce block connection to enrich the high-frequency details in the high-frequency network, which is favorable for obtaining potential interdependencies between high- and low-frequency features. Experimental results indicate that the proposed WAAR exhibits strong performance in reconstructing clean and rain-free images, recovering real and undistorted texture structures, and enhancing image edges in comparison with the state-of-the-art approaches on synthetic and real image datasets. It shows the effectiveness of our method, especially on image edges and texture details.

The Contrastive Network With Convolution and Self-Attention Mechanisms for Unsupervised Cell Segmentation.

Deep learning for cell instance segmentation is a significant research direction in biomedical image analysis. The traditional supervised learning methods rely on pixel-wise annotation of object images to train the models, which is often accompanied by time-consuming and labor-intensive. Various modified segmentation methods, based on weakly supervised or semi-supervised learning, have been proposed to recognize cell regions by only using rough annotations of cell positions. However, it is still hard to achieve the fully unsupervised in most approaches that the utilization of few annotations for training is still inevitable. In this article, we propose an end-to-end unsupervised model that can segment individual cell regions on hematoxylin and eosin (H&E) stained slides without any annotation. Compared with weakly or semi-supervised methods, the input of our model is in the form of raw data without any identifiers and there is no need to generate pseudo-labelling during training. We demonstrated that the performance of our model is satisfactory and also has a great generalization ability on various validation sets compared with supervised models. The ablation experiment shows that our backbone has superior performance in capturing object edge and context information than pure CNN or transformer under our unsupervised method.

Comparison Of Accuracy Level Of Krisch And Prewitt Methods For Measurement Of Human Body Weight Using Digital Images

Current image processing provides an opportunity for humans to develop systems capable of identifying digital images. Edge detection is a process to produce the edges of an image object. The problem of this research is how to compare the level of accuracy of the Krisch and Prewitt method for measuring human body weight with digital images. The aim of this research is to compare the level of accuracy between the Krisch and Prewitt methods in measuring human body weight using digital images. This research uses an experimental method by taking images of the human body, cropping, resizing, and converting them into grayscale images. Next, edge detection was carried out using the Krisch and Prewitt method. Edge detection results are used to measure human body weight by calculating the pixel distance between certain points on the edge of the object in the image. The results of this study show that the Krisch and Prewitt methods have different levels of accuracy in measuring human body weight. Based on tests that have been carried out on 15 image data samples using the confusion matrix approach, where the accuracy level of the Prewitt method is 60% while the Krisch method is 40%. The conclusion of the research is that the Prewitt method has the best level of accuracy compared to the Krisch method

Remote Sensing Image Ship Matching Utilising Line Features for Resource-Limited Satellites

The existing image matching methods for remote sensing scenes are usually based on local features. The most common local features like SIFT can be used to extract point features. However, this kind of methods may extract too many keypoints on the background, resulting in low attention to the main object in a single image, increasing resource consumption and limiting their performance. To address this issue, we propose a method that could be implemented well on resource-limited satellites for remote sensing images ship matching by leveraging line features. A keypoint extraction strategy called line feature based keypoint detection (LFKD) is designed using line features to choose and filter keypoints. It can strengthen the features at corners and edges of objects and also can significantly reduce the number of keypoints that cause false matches. We also present an end-to-end matching process dependent on a new crop patching function, which helps to reduce complexity. The matching accuracy achieved by the proposed method reaches 0.972 with only 313 M memory and 138 ms testing time. Compared to the state-of-the-art methods in remote sensing scenes in extensive experiments, our keypoint extraction method can be combined with all existing CNN models that can obtain descriptors, and also improve the matching accuracy. The results show that our method can achieve ∼50% test speed boost and ∼30% memory saving in our created dataset and public datasets.

Polychromatic Dual-Mode Imaging with Structured Chiral Photonic Crystals.

Optical spatial differentiation is a typical operation of optical analog computing and can single out the edge to accelerate the subsequent image processing, but in some cases, overall information about the object needs to be presented synchronously. Here, we propose a multifunctional optical device based on structured chiral photonic crystals for the simultaneous realization of real-time dual-mode imaging. This optical differentiator is realized by self-organized large-birefringence cholesteric liquid crystals, which are photopatterned to encode with a special integrated geometric phase. Two highly spin-selective modes of second-order spatial differentiation and bright-field imaging are exhibited in the reflected and transmitted directions, respectively. Two-dimensional edges of both amplitude and phase objects have been efficiently enhanced in high contrast and the broadband spectrum. This work extends the ingenious building of hierarchical chiral nanostructures, enriches their applications in the emerging frontiers of optical computing, and boasts considerable potential in machine vision and microscopy.

Monocular Depth Estimation Algorithm Integrating Parallel Transformer and Multi-Scale Features

In the process of environmental perception, traditional CNN is often unable to effectively capture global context information due to its network structure, which leads to the problem of blurred edges of objects and scenes. Aiming at this problem, a self-supervised monocular depth estimation algorithm incorporating a Transformer is proposed. First of all, the encoder-decoder architecture is adopted. In the course of the encoding procedure, the input image generates images with different patch sizes but the same size. The multi-path Transformer network and single-path CNN network are used to extract global and local features, respectively, and feature fusion is achieved through interactive modules, which improves the network’s ability to acquire global information. Second, a multi-scale fusion structure of hierarchical features is designed to improve the utilization of features of different scales. Experiments for training the model were conducted using the KITTI dataset. The outcomes reveal that the proposed algorithm outperforms the mainstream algorithm. Compared with the latest CNN-Transformer algorithm, the proposed algorithm reduces the absolute relative error by 3.7% and the squared relative error by 3.9%.

A Deep Joint Network for Monocular Depth Estimation Based on Pseudo-Depth Supervision

Depth estimation from a single image is a significant task. Although deep learning methods hold great promise in this area, they still face a number of challenges, including the limited modeling of nonlocal dependencies, lack of effective loss function joint optimization models, and difficulty in accurately estimating object edges. In order to further increase the network’s prediction accuracy, a new structure and training method are proposed for single-image depth estimation in this research. A pseudo-depth network is first deployed for generating a single-image depth prior, and by constructing connecting paths between multi-scale local features using the proposed up-mapping and jumping modules, the network can integrate representations and recover fine details. A deep network is also designed to capture and convey global context by utilizing the Transformer Conv module and Unet Depth net to extract and refine global features. The two networks jointly provide meaningful coarse and fine features to predict high-quality depth images from single RGB images. In addition, multiple joint losses are utilized to enhance the training model. A series of experiments are carried out to confirm and demonstrate the efficacy of our method. The proposed method exceeds the advanced method DPT by 10% and 3.3% in terms of root mean square error (RMSE(log)) and 1.7% and 1.6% in terms of squared relative difference (SRD), respectively, according to experimental results on the NYU Depth V2 and KITTI depth estimation benchmarks.

A system and method for person identification and positioning incorporating object edge detection and scale-invariant feature transformation

During the overhead crane, due to the complex background and large image size, the direct processing algorithm usually leads to time-consuming operation and difficult to achieve accurate personnel positioning. To address these issues, we propose the feature points recognition and matching algorithm incorporating object edge detection and scale-invariant feature transform (SIFT), which is applied to the designed object detection and positioning algorithm for binocular stereo vision. The proposed method applies the Canny operator to extract contours from the locally cropped regions obtained using YOLOv5. The contour points are used as the key points of SIFT, and corresponding feature points are created descriptors, and feature points matching are performed. Experimental results indicate that the proposed method can filter feature points successfully. Moreover, the binocular stereo vision system with the binocular positioning algorithm designed has good performance, with the overall depth direction positioning error within 5% in a range of 12 m.

Edge-enhanced microscopy of complex objects using scalar and vectorial vortex filtering.

Recently, a 4f system containing a q-plate has been used to perform edge detection and enhancement of amplitude or phase objects. However, only a few studies have concentrated on edge enhancement of complex phase-amplitude objects. Here we experimentally verified the functional difference between scalar and vectorial vortex filtering with the q-plate using an onion cell as a complex object and the vectorial vortex filtering successfully enhanced the edges of phase and amplitude objects in the phase-amplitude object. One problem, however, is indistinguishability of the equally-enhanced edges of the phase and amplitude objects. To address this issue, we propose a method to isolate the edge of the phase object from the edge of the amplitude object using off-axis beam illumination. We theoretically calculated the isolation of the edge of the phase object from the amplitude object, and verified via numerical simulations.

Multi-Object Deep-Field Digital Holographic Imaging Based on Inverse Cross-Correlation

To address the complexity of small or unique reconstruction distances in digital holography, we propose an inverse cross-correlation-based algorithm for the digital holographic imaging of multiplanar objects with a large depth of field. In this method, a planar output mapping is closely around the objects, and it is established by calculating the image inverse cross-correlation matrix of the reconstructed image at similar reconstruction distances, whereby the object edges serve as the result guide. Combining the search for edge planes with the depth estimation operator, the depth of field of digital holography is improved, thus allowing for a digital holography that is capable of meeting the requirements of the holographic imaging of multiplanar objects. Compared with the traditional depth estimation operator method, the proposed method solves the reconstruction ambiguity problem in multiple planes with a simple optical path, and no additional optical or mechanical devices need to be added, thus greatly improving the reconstruction quality. The numerical calculation results and the experimental results with multiplanar samples validate the effectiveness of the proposed method.

Robust unsupervised domain adaptation by retaining confident entropy via edge concatenation

The generalization capability of unsupervised domain adaptation can mitigate the need for extensive pixel-level annotations to train semantic segmentation networks by training models on synthetic data as a source with computer-generated annotations. Entropy-based adversarial networks are proposed to improve source domain prediction; however, they disregard significant external information, such as edges, which have the potential to identify and distinguish various objects within an image accurately. To address this issue, we introduce a novel approach to domain adaptation, leveraging the synergy of internal and external information within entropy-based adversarial networks. In this approach, we enrich the discriminator network with edge-predicted probability values within this innovative framework to enhance the clarity of class boundaries. Furthermore, we devised a probability-sharing network that integrates diverse information for more effective segmentation. Incorporating object edges addresses a pivotal aspect of unsupervised domain adaptation that has frequently been neglected in the past—the precise delineation of object boundaries. Conventional unsupervised domain adaptation methods usually center around aligning feature distributions and may not explicitly model object boundaries. Our approach effectively bridges this gap by offering clear guidance on object boundaries, thereby elevating the quality of domain adaptation. Our approach undergoes rigorous evaluation on the established unsupervised domain adaptation benchmarks, specifically in adapting SYNTHIA → Cityscapes and SYNTHIA → Mapillary. Experimental results show that the proposed model attains better performance than state-of-the-art methods. The superior performance across different unsupervised domain adaptation scenarios highlights the versatility and robustness of the proposed method.

Таблично-алгоритмічний метод для антиаліайзингу зображення відрізків прямих

Increasing the informativeness of computer graphics is achieved due to the formation of images that accurately reproduce the structural and visual features of the object. When forming such images, it is necessary to display graphic scenes with great detail, therefore, at this stage of the development of computer graphics, special attention is paid not only to the speed of forming graphic images, but also to their realism. In most modern computer graphics systems, the raster principle of image formation is used. When creating raster images, distortions occur due to the insufficient resolution of the raster. Artifacts appear on the images, one of the manifestations of which are pronounced steps or teeth on the edges of objects. The aliasing effect significantly affects the realism of the formed image, which necessitates the development of special methods and means of its elimination The tabular method of vector anti-aliasing was further developed. It is proposed to calculate the values of the evaluation function to store its values with a larger quantization step, and to calculate the intermediate ones according to the derived formula. The analysis showed that the use of the proposed approach allows reducing by 8¸17 times the amount of memory needed to calculate the pixel coverage area. The method involves hardware and software implementation and can be used in high-performance computer graphics systems.

Implementing the edge enhancement with vortex filter in both linear and nonlinear optics

The edge enhancement technique, as an effective method to represent the boundary of objects, plays an important role in image processing. Among them, the vortex filtering, which is based on the radial Hilbert transformation, has been paid great attention due to its ability to achieve isotropic and anisotropic edge enhancement. Recent years have witnessed a growing interest in the nonlinear vortex filter to skillfully realize the visualization of the object edge under invisible light irradiation. In this paper, we start from reviewing the achievements have been made with the vortex filtering technique in linear optics, and then discussed the recent processes of the scalar and vector vortex filter in nonlinear optics. We hope that the nonlinear optical vortex filter can motivate some promising applications in biological edge imaging with visible light-sensitive specimens.

A spatially variant high-order variational model for Rician noise removal.

Rician noise removal is an important problem in magnetic resonance (MR) imaging. Among the existing approaches, the variational method is an essential mathematical technique for Rician noise reduction. The previous variational methods mainly employ the total variation (TV) regularizer, which is a first-order term. Although the TV regularizer is able to remove noise while preserving object edges, it suffers the staircase effect. Besides, the adaptability has received little research attention. To this end, we propose a spatially variant high-order variational model (SVHOVM) for Rician noise reduction. We introduce a spatially variant TV regularizer, which can adjust the smoothing strength for each pixel depending on its characteristics. Furthermore, SVHOVM utilizes the bounded Hessian (BH) regularizer to diminish the staircase effect generated by the TV term. We develop a split Bregman algorithm to solve the proposed minimization problem. Extensive experiments are performed to demonstrate the superiority of SVHOVM over some existing variational models for Rician noise removal.