Object Boundaries Research Articles

Three-Dimensional Instance Segmentation Using the Generalized Hough Transform and the Adaptive n-Shifted Shuffle Attention

The progress of 3D instance segmentation techniques has made it essential for several applications, such as augmented reality, autonomous driving, and robotics. Traditional methods usually have challenges with complex indoor scenes made of multiple objects with different occlusions and orientations. In this work, the authors present an innovative model that integrates a new adaptive n-shifted shuffle (ANSS) attention mechanism with the Generalized Hough Transform (GHT) for robust 3D instance segmentation of indoor scenes. The proposed technique leverages the n-shifted sigmoid activation function, which improves the adaptive shuffle attention mechanism, permitting the network to dynamically focus on relevant features across various regions. A learnable shuffling pattern is produced through the proposed ANSS attention mechanism to spatially rearrange the relevant features, thus augmenting the model’s ability to capture the object boundaries and their fine-grained details. The integration of GHT furnishes a vigorous framework to localize and detect objects in the 3D space, even when heavy noise and partial occlusions are present. The authors evaluate the proposed method on the challenging Stanford 3D Indoor Spaces Dataset (S3DIS), where it establishes its superiority over existing methods. The proposed approach achieves state-of-the-art performance in both mean Intersection over Union (IoU) and overall accuracy, showcasing its potential for practical deployment in real-world scenarios. These results illustrate that the integration of the ANSS and the GHT yields a robust solution for 3D instance segmentation tasks.

Информационно-аналитическая система детектирования движения объектов на пешеходном переходе

To manage pedestrian and vehicle flows at intersections, systems are implemented that use adaptive traffic light models, adjusting time intervals based on the volume of pedestrians and vehicles. These systems include video cameras that monitor road user movements, enhancing real-time traffic control. This paper introduces an information and analytical system for managing transport and pedestrian flows using the YOLO neural model, which enables object recognition. The system performs several operations: converting the original image to gray scale, applying Gaussian blurring, detecting object boundaries through the Canny filter and fuzzy logic for edge detection, and contour processing, where each identified contour is assigned a unique number. The neural network then compares detected contours to the training sample data, determining whether the object is a person or a vehicle. The paper presents experimental results for these algorithms in object recognition. Modified software and images of intersections with pedestrian crossings captured from street video cameras in Kursk were used in the experiments. The recognition accuracy rate from the experiments was 72.4%.

Figure-ground segmentation based medical image denoising using deep convolutional neural networks

Medical image noise can have a substantial impact on both diagnosis accuracy and image quality. Noise can cause problems with tasks related to diagnosis, like defining object boundaries, which are essential for precise diagnosis. By applying denoising techniques, medical imaging professionals can significantly improve image quality, reduce errors, and enhance the accuracy of diagnoses and treatments. This article presents a method for reducing noises like Gaussian noise, salt and pepper noise, speckle noise, and ring artefacts in medical images, such as magnetic resonance imaging (MRI), computed tomography (CT), and chest X-ray images. This study explores the integration of adaptive CNNs with guided image filtering for enhanced image quality and deep learning-driven Figure-Ground segmentation. The proposed method's performance is extensively evaluated on chest X-ray and MRI/CT images under diverse noise scenarios, with comparisons to existing techniques using established statistical metrics. The results validate that the proposed approach attains superior performance, yielding the highest values across these metrics.

CadastreVision: A benchmark dataset for cadastral boundary delineation from multi-resolution earth observation images

Approximately 70%–75% of people worldwide have no formally registered land rights. Fit-For-Purpose Land Administration was introduced to address this problem and focuses on delineating visible cadastral boundaries from earth observation imagery. Recent studies have shown the potential of deep learning models to extract these visible cadastral boundaries automatically. However, studies are limited by the small size and geographical coverage of available datasets and by the lack of information about which cadastral boundaries are visible, i.e., associated with a physical object boundary. To overcome these problems, we present CadastreVision, a benchmark dataset containing cadastral reference data and corresponding multi-resolution earth observation imagery from The Netherlands, with a spatial resolution ranging from 0.1 m to 10 m. The ratio between visible and non-visible cadastral boundaries is essential to evaluate the potential automation level in cadastral boundary extraction from earth observation images and interpret results obtained by deep learning models. We investigate this ratio using a novel analysis pipeline that overlays cadastral reference data with visible topographic object boundaries. Our results show that approximately 72% of the total length of cadastral boundaries in The Netherlands are visible. CadastreVision will enable new developments in cadastral boundary delineation and future endeavours to investigate knowledge transfer to data-scarce areas. Our data and code is available at https://github.com/jeroengrift/cadastrevision.

MR electrical properties mapping using vision transformers and canny edge detectors.

We developed a 3D vision transformer-based neural network to reconstruct electrical properties (EP) from magnetic resonance measurements. Our network uses the magnitude of the transmit magnetic field of a birdcage coil, the associated transceive phase, and a Canny edge mask that identifies the object boundaries as inputs to compute the EP maps. We trained our network on a dataset of 10 000 synthetic tissue-mimicking phantoms and fine-tuned it on a dataset of 11 000 realistic head models. We assessed performance in-distribution simulated data and out-of-distribution head models, with and without synthetic lesions. We further evaluated our network in experiments for an inhomogeneous phantom and a volunteer. The conductivity and permittivity maps had an average peak normalized absolute error (PNAE) of 1.3% and 1.7% for the synthetic phantoms, respectively. For the realistic heads, the average PNAE for the conductivity and permittivity was 1.8% and 2.7%, respectively. The location of synthetic lesions was accurately identified, with reconstructed conductivity and permittivity values within 15% and 25% of the ground-truth, respectively. The conductivity and permittivity for the phantom experiment yielded 2.7% and 2.1% average PNAEs with respect to probe-measured values, respectively. The in vivo EP reconstruction truthfully preserved the subject's anatomy with average values over the entire head similar to the expected literature values. We introduced a new learning-based approach for reconstructing EP from MR measurements obtained with a birdcage coil, marking an important step towards the development of clinically-usable in vivo EP reconstruction protocols.

Research on Improved Image Segmentation Algorithm Based on GrabCut

The classic interactive image segmentation algorithm GrabCut achieves segmentation through iterative optimization. However, GrabCut requires multiple iterations, resulting in slower performance. Moreover, relying solely on a rectangular bounding box can sometimes lead to inaccuracies, especially when dealing with complex shapes or intricate object boundaries. To address these issues in GrabCut, an improvement is introduced by incorporating appearance overlap terms to optimize segmentation energy function, thereby achieving optimal segmentation results in a single iteration. This enhancement significantly reduces computational costs while improving the overall segmentation speed without compromising accuracy. Additionally, users can directly provide seed points on the image to more accurately indicate foreground and background regions, rather than relying solely on a bounding box. This interactive approach not only enhances the algorithm’s ability to accurately segment complex objects but also simplifies the user experience. We evaluate the experimental results through qualitative and quantitative analysis. In qualitative analysis, improvements in segmentation accuracy are visibly demonstrated through segmented images and residual segmentation results. In quantitative analysis, the improved algorithm outperforms GrabCut and min_cut algorithms in processing speed. When dealing with scenes where complex objects or foreground objects are very similar to the background, the improved algorithm will display more stable segmentation results.

An Object-Aware Network Embedding Deep Superpixel for Semantic Segmentation of Remote Sensing Images

Semantic segmentation forms the foundation for understanding very high resolution (VHR) remote sensing images, with extensive demand and practical application value. The convolutional neural networks (CNNs), known for their prowess in hierarchical feature representation, have dominated the field of semantic image segmentation. Recently, hierarchical vision transformers such as Swin have also shown excellent performance for semantic segmentation tasks. However, the hierarchical structure enlarges the receptive field to accumulate features and inevitably leads to the blurring of object boundaries. We introduce a novel object-aware network, Embedding deep SuperPixel, for VHR image semantic segmentation called ESPNet, which integrates advanced ConvNeXt and the learnable superpixel algorithm. Specifically, the developed task-oriented superpixel generation module can refine the results of the semantic segmentation branch by preserving object boundaries. This study reveals the capability of utilizing deep convolutional neural networks to accomplish both superpixel generation and semantic segmentation of VHR images within an integrated end-to-end framework. The proposed method achieved mIoU scores of 84.32, 90.13, and 55.73 on the Vaihingen, Potsdam, and LoveDA datasets, respectively. These results indicate that our model surpasses the current advanced methods, thus demonstrating the effectiveness of the proposed scheme.

Gradient Magnitude Based Image Classification and Edge Detection for Pattern Recognition in Grayscale Images

Image classification is a crucial technique in digital image processing, used in various applications such as object recognition, surveillance systems, and medical image analysis. This research explores the use of gradient magnitude-based edge detection and Robert's Cross methods in improving the classification accuracy of grayscale images. Edge detection is used to identify object boundaries, while gradient magnitude amplifies intensity differences, thus clarifying existing patterns. Through experiments conducted on grayscale images, the results show that this method is able to detect edges with significant accuracy. The gradient values obtained from the combination of Rx and Ry matrices give a strong indication of the presence of edges, which plays an important role in image classification. With an accuracy of 75%, the method proved to be effective, although there are still challenges in dealing with images with high noise or low contrast. The conclusion of this study shows that the combination of edge detection and gradient magnitude is a promising approach for image classification, providing results that can be applied in various domains, including medical and surveillance. Further research is recommended to optimize this approach and extend its application to more complex datasets.

The use of groups of drones for diagnostics of subsurface objects in the radio range

Diagnostics of objects that are bodies of complex shape can be based on representing their boundaries of such objects (including subsurface ones) in the form of a set of paraboloids. It is shown that the determination of specific geometric characteristics of such paraboloids is ensured through the artificial synthesis of a distributed lens, the individual elements of which are placed on individual unmanned aerial vehicles. Technically, lens synthesis is achieved by changing the phase of radio frequency radiation, carried out using phase shifters. The method is implemented through scanning the object under study by adjusting the effective optical power and its orientation in space. Model calculations are presented that prove the prospects of using the proposed method. Specific examples of radio-electronic circuits that ensure the implementation of the proposed approach are presented. A feature of the phase shifters used is the preliminary detection of the phase of the signal arriving at each of the elements of the distributed lens, and the subsequent introduction of an additional phase difference due to the weighted summation of harmonic signals that are in antiphase.

3D Point Cloud Semantic Segmentation based on Multi-scale Dense Nested Networks

Aiming at the problem that the relationship between geometric features and semantic features is ignored in the point cloud data downsampling process, which leads to inaccurate segmentation of object boundaries and structural details, this paper proposes a 3D point cloud semantic segmentation network based on multi-scale dense nested type. Firstly, a dense nested network architecture is constructed by nesting multiple multi-scale feature fusion modules to fuse multi-scale features of different directions between encoder-decoder paths, so as to effectively propagate local ge-ometric context information and enhance the ability of cross-scale information interaction. Secondly, a local feature aggregation unit is constructed in the multi-scale feature fusion module, which strengthens the structural awareness within the local point set based on graph convolution and attention mechanism, and promotes the complementarity of local geometric features and abstract semantic information. Then, the cross-layer multi-loss supervision module is combined to further optimize the multi-scale feature propagation, which makes the network training more stable and improves the point cloud segmentation accuracy. Finally, this paper verified the proposed network on the S3DIS dataset. The experimental results show that the proposed network has the mean intersection over Union of 71.2% and the overall accuracy of 88.7%, which is 1.2 and 0.7 percentage points higher than RandLA-Net, respectively, which proves that the proposed network can effectively improve the accuracy of 3D point cloud semantic segmentation.

Using Hough transform to define track boundaries as part of machine vision by train traffic-tracking hardware and software systems

Aim. In the context of machine vision, the problem of detected object boundary definition is usually solved using semantic segmentation that requires a high computational resource. Its application increases the complexity and the cost of the implemented hardware and software systems. This paper proposes an alternative method for defining the boundary of a segmented object, i.e., a railway track, for a train traffic tracking system. Methods. Since a railway track in an image can be represented by an n-th order polynomial, it is suggested to solve the problem of track boundary detection by using approximations in the form of straight lines. It is suggested using the Hough transform to detect straight lines. The former’s parametric space will be arranged in accordance with the problem to be solved. Conclusions. The proposed approximation will allow abandoning semantic segmentation and reduce the computational complexity and load.

NeRF-OR: neural radiance fields for operating room scene reconstruction from sparse-view RGB-D videos.

RGB-D cameras in the operating room (OR) provide synchronized views of complex surgical scenes. Assimilation of this multi-view data into a unified representation allows for downstream tasks such as object detection and tracking, pose estimation, and action recognition. Neural radiance fields (NeRFs) can provide continuous representations of complex scenes with limited memory footprint. However, existing NeRF methods perform poorly in real-world OR settings, where a small set of cameras capture the room from entirely different vantage points. In this work, we propose NeRF-OR, a method for 3D reconstruction of dynamic surgical scenes in the OR. Where other methods for sparse-view datasets use either time-of-flight sensor depth or dense depth estimated from color images, NeRF-OR uses a combination of both. The depth estimations mitigate the missing values that occur in sensor depth images due to reflective materials and object boundaries. We propose to supervise with surface normals calculated from the estimated depths, because these are largely scale invariant. We fit NeRF-OR to static surgical scenes in the 4D-OR dataset and show that its representations are geometrically accurate, where state of the art collapses to sub-optimal solutions. Compared to earlier work, NeRF-OR grasps fine scene details while training 30 faster. Additionally, NeRF-OR can capture whole-surgery videos while synthesizing views at intermediate time values with an average PSNR of 24.86dB. Last, we find that our approach has merit in sparse-view settings beyond those in the OR, by benchmarking on the NVS-RGBD dataset that contains as few as three training views. NeRF-OR synthesizes images with a PSNR of 26.72dB, a 1.7% improvement over state of the art. Our results show that NeRF-OR allows for novel view synthesis with videos captured by a small number of cameras with entirely different vantage points, which is the typical camera setting in the OR. Code is available via: github.com/Beerend/NeRF-OR .

YOLO V3 AND CCN FOR THE TRACKING AND CLASSIFICATION OF AERIAL OBJECT AND DRONES

The goal of this study is to give headways in aeronautical article ID that will help with making recognitions that are both more exact and more precise. Specifically, we revamp the meaning of the article recognition anchor enclose request to remember turns for expansion to level and width, and besides, we make it conceivable to have erratic four corner point structures. Furthermore, the consideration of new anchor boxes gives the model additional adaptability to address protests that are focused at a pivot of turn that gives a 45-degree point. By accomplishing these results, we can make an organization that considers negligible tradeoffs about speed and unwavering quality, while likewise giving more exact restrictions. The latest ways to deal with PC vision and article acknowledgment are for the most part dependent on brain organizations and different advances that utilize profound learning. This powerful field of study is utilized in various applications, including military and observation, aeronautical photography, independent driving, and airborne perception. To precisely locate the location of an item, contemporary object identification techniques make use of bounding boxes that are drawn over the object and have a rectangular form (horizontal and vertical). These orthogonal bounding boxes do not consider the posture of the object, which leads to a decrease in the amount of object localization and restricts subsequent tasks such as object comprehension and tracking. We have used the DOTA dataset to present all of the results, demonstrating the value of flexible object boundaries, particularly with rotated and non-rectangular objects. We have also achieved an accuracy of 98.47% for the detection and classification of aerial objects, with forty percent of the data being used for training and the remaining twenty percent being used for testing. There was a minimum of 2.8 seconds of processing time required for the whole program to be executed to categorize all of the aerial items that were parked on the base.

Search and recovery network for camouflaged object detection

Camouflaged object detection aims to accurately identify objects blending into the background. However, existing methods often struggle, especially with small object or multiple objects, due to their reliance on singular strategies. To address this, we introduce a novel Search and Recovery Network (SRNet) using a bionic approach and auxiliary features. SRNet comprises three key modules: the Region Search Module (RSM), Boundary Recovery Module (BRM), and Camouflaged Object Predictor (COP). The RSM mimics predator behavior to locate potential object regions, enhancing object location detection. The BRM refines texture features and recovers object boundaries. The COP fuse multilevel features to predict final segmentation maps. Experimental results on three benchmark datasets show SRNet's superiority over SOTA models, particularly with small and multiple objects. Notably, SRNet achieves performance improvements without significantly increasing model parameters. Moreover, the method exhibits promising performance in downstream tasks such as defect detection, polyp segmentation and military camouflage detection.

Dual-consistency guidance semi-supervised medical image segmentation with low-level detail feature augmentation

In deep-learning-based medical image segmentation tasks, semi-supervised learning can greatly reduce the dependence of the model on labeled data. However, existing semi-supervised medical image segmentation methods face the challenges of object boundary ambiguity and a small amount of available data, which limit the application of segmentation models in clinical practice. To solve these problems, we propose a novel semi-supervised medical image segmentation network based on dual-consistency guidance, which can extract reliable semantic information from unlabeled data over a large spatial and dimensional range in a simple and effective manner. This serves to improve the contribution of unlabeled data to the model accuracy. Specifically, we construct a split weak and strong consistency constraint strategy to capture data-level and feature-level consistencies from unlabeled data to improve the learning efficiency of the model. Furthermore, we design a simple multi-scale low-level detail feature enhancement module to improve the extraction of low-level detail contextual information, which is crucial to accurately locate object contours and avoid omitting small objects in semi-supervised medical image dense prediction tasks. Quantitative and qualitative evaluations on six challenging datasets demonstrate that our model outperforms other semi-supervised segmentation models in terms of segmentation accuracy and presents advantages in terms of generalizability. Code is available at https://github.com/0Jmyy0/SSMIS-DC.

A novel multi-loss dynamic fusion-enhanced image segmentation model for welding spatter measurement

Quantitative detection of welding spatter is not only critical for evaluating and optimizing welding energy consumption, but also significant for improving welding quality. Inspired by the welder's visual estimation of the amount of spatter, a novel welding spatter measurement method based on image segmentation is proposed. Considering the challenges of welding spatter such as small object, aggregation, and unclear boundary, four loss functions, namely, Focal loss, Dice loss, Boundary loss, and Count loss, are designed to achieve global optimization for complex welding spatter. Furthermore, for the different spatter characteristics with different optimization difficulties, a multi-loss dynamic fusion method with differential optimization capability is designed. Finally, a welding spatter segmentation dataset is established and a comprehensive ablation and comparison test of the proposed methodology is carried out. The results indicate that the proposed method has an average F1-score metric of 83.52 % and a mean intersection over union metric of 75.11 %. These findings suggest the potential for vision-based quantitative estimation of welding spatter.

Depth Image Rectification Based on an Effective RGB–Depth Boundary Inconsistency Model

Depth image has been widely involved in various tasks of 3D systems with the advancement of depth acquisition sensors in recent years. Depth images suffer from serious distortions near object boundaries due to the limitations of depth sensors or estimation methods. In this paper, a simple method is proposed to rectify the erroneous object boundaries of depth images with the guidance of reference RGB images. First, an RGB–Depth boundary inconsistency model is developed to measure whether collocated pixels in depth and RGB images belong to the same object. The model extracts the structures of RGB and depth images, respectively, by Gaussian functions. The inconsistency of two collocated pixels is then statistically determined inside large-sized local windows. In this way, pixels near object boundaries of depth images are identified to be erroneous when they are inconsistent with collocated ones in RGB images. Second, a depth image rectification method is proposed by embedding the model into a simple weighted mean filter (WMF). Experiment results on two datasets verify that the proposed method well improves the RMSE and SSIM of depth images by 2.556 and 0.028, respectively, compared with recent optimization-based and learning-based methods.

Enhanced human motion detection with hybrid RDA-WOA-based RNN and multiple hypothesis tracking for occlusion handling

Human motion detection in complex scenarios poses challenges due to occlusions. This paper presents an integrated approach for accurate human motion detections by combining Adapted Canny Edge detection as a preprocessing step, backbone-modified Mask R-CNN for precise segmentation, Hybrid RDA-WOA-based RNN as a classification, and a Multiple-hypothesis model for effective occlusion handling. Adapted Canny Edge detection is utilized as an initial preprocessing step to highlight significant edges in the input image. The resulting edge map enhances object boundaries and highlights structural features, simplifying subsequent processing steps. The improved image is then passed through backbone-modified Mask R-CNN for the pixel-level segmentation of humans. Backbone-modified Mask R-CNN along with IoU, Euclidean Distance, and Z-Score recognizes moving objects in complex scenes exactly. After recognizing moving objects, the optimized Hybrid RDA-WOA-based RNN classifies humans. To handle the self-occlusion, Multiple Hypothesis Tracking (MHT) is used. Real-world situations frequently include occlusions where humans can be partially or completely hidden by objects. The proposed approach integrates a Multiple-hypothesis model into the detection pipeline to address this challenge. Moreover, the proposed human motion detection approach includes an optimized Hybrid RDA-WOA-based RNN trained with 2D representations of 3D skeletal motion. The proposed work was evaluated using the IXMAS, KTH, Weizmann, NTU RGB + D, and UCF101 Datasets. It achieved an accuracy of 98% on the IXMAS, KTH, Weizmann, and UCF101 Datasets and 97.1% on the NTU RGB + D Dataset. The simulation results unveil the superiority of the proposed methodology over the existing approaches.

Reverse cross-refinement network for camouflaged object detection

Due to the high intrinsic similarity between camouflaged objects and the background, camouflaged objects often exhibit blurred boundaries, making it challenging to distinguish the boundaries of objects. Existing methods still focus on the overall regional accuracy but not on the boundary quality and are not competent to identify camouflaged objects from the background in complex scenarios. Thus, we propose a novel reverse cross-refinement network called RCR-Net. Specifically, we design a diverse feature enhancement module that simulates the correspondingly expanded receptive fields of the human visual system by using convolutional kernels with different dilation rates in parallel. Also, the boundary attention module is used to reduce the noise of the bottom features. Moreover, a multi-scale feature aggregation module is proposed to transmit the diverse features from pixel-level camouflaged edges to the entire camouflaged object region in a coarse-to-fine manner, which consists of reverse guidance, group guidance, and position guidance. Reverse guidance mines complementary regions and details by erasing already estimated object regions. Group guidance and position guidance integrate different features through simple and effective splitting and connecting operations. Extensive experiments show that RCR-Net outperforms the existing 18 state-of-the-art methods on four widely-used COD datasets. Especially, compared with the existing top-1 model HitNet, RCR-Net significantly improves the performance by ∼16.4% (Mean Absolute Error) on the CAMO dataset, showing that RCR-Net could accurately detect camouflaged objects.

Inferring Object Boundaries and Their Roughness with Uncertainty Quantification

AbstractThis work describes a Bayesian framework for reconstructing the boundaries that represent targeted features in an image, as well as the regularity (i.e., roughness vs. smoothness) of these boundaries. This regularity often carries crucial information in many inverse problem applications, e.g., for identifying malignant tissues in medical imaging. We represent the boundary as a radial function and characterize the regularity of this function by means of its fractional differentiability. We propose a hierarchical Bayesian formulation which, simultaneously, estimates the function and its regularity, and in addition we quantify the uncertainties in the estimates. Numerical results suggest that the proposed method is a reliable approach for estimating and characterizing object boundaries in imaging applications, as illustrated with examples from high-intensity X-ray CT and image inpainting with Gaussian and Laplace additive noise models. We also show that our method can quantify uncertainties for these noise types, various noise levels, and incomplete data scenarios.