Object Extraction Research Articles

Perforation induced ligament evolution in low-temperature swirl spray via off-axis holography

Ligaments generated from a perforated sheet are commonly observed in the primary breakup process and have a fundamental influence on spray characteristics. Ignition and combustion instabilities of aeroengines at high altitudes raise the demand for dynamic measurement of ligaments in a low-temperature spray. Picosecond pulsed digital off-axis holography (DOH) system with 65 kHz high-speed and 4.5μm equivalent pixel size high-resolution setups is established. Three-dimensional (3D) evolution of ligaments in a pressure swirl spray under fuel temperature of 245–250 K and fuel pressure of 0.2–0.8 MPa is characterized. The stringy object extraction method optimized by FMCs cross correlation algorithm successfully extracts a 3D arc-shaped ligament in the spray at 0.2 MPa. The transition of ligaments into droplets during two modes of sheet perforation as hole–edge and two-hole interactions at 0.5 MPa is quantified with time resolution up to 15.4μs. Both the nucleation and growth of perforations are found involved with surface waves, and their early diameter growth velocities remain stable in the short term, consistent with Taylor–Culick velocity characteristics. The 3D velocity of a pair of ligaments in the spray at 0.5 MPa is obtained based on the spatial displacement of their daughter droplets within double frames, indicating a downward helical movement trend after separation from the conical swirling sheet. This work demonstrates DOH a powerful tool for 3D morphology extraction and dynamic analysis of ligaments and perforations in the pressure swirl atomization scenario.

Federated Deep Learning With Prototype Matching for Object Extraction From Very-High-Resolution Remote Sensing Images

Deep convolutional neural networks (DCNNs) have become the leading tools for object extraction from very-high-resolution (VHR) remote sensing images. However, the label scarcity problem of local datasets hinders the prediction performances of DCNNs, and privacy concerns regarding remote sensing data often arise in the traditional deep learning schemes. To cope with these problems, we propose a novel federated learning scheme with prototype matching (FedPM) to collaboratively learn a richer DCNN model by leveraging remote sensing data distributed among multiple clients. This scheme conducts federated optimization of DCNNs by aggregating clients’ knowledge in the gradient space without compromising data privacy. Specifically, the prototype matching method is developed to regularize the local training using prototypical representations while reducing the distribution divergence across heterogeneous image data. Furthermore, the derived deviations across local and global prototypes are applied to quantify the effects of local models on the decision boundary and optimize the global model updating via the attention-weighted aggregation scheme. Finally, the sparse ternary compression (STC) method is used to alleviate communication costs. Extensive experimental results derived from VHR aerial and satellite image datasets verify that the FedPM can dramatically improve the prediction performance of DCNNs on object extraction with lower communication costs. To the best of our knowledge, this is the first time federated learning has been applied for remote sensing visual tasks.

ResAt-UNet: A U-Shaped Network Using ResNet and Attention Module for Image Segmentation of Urban Buildings

Architectural image segmentation refers to the extraction of architectural objects from remote sensing images. At present, most neural networks ignore the relationship between feature information, and there are problems such as model overfitting and gradient explosion. Thus, this paper proposes an improved UNet based on ResNet34 and Attention Module (ResAt-UNet) to solve the related problems. The algorithm adds a two-layer residual structure (BasicBlock) and a regional enhancement attention mechanism (Space Enhancement Area Enhancement, SEAE) to the original framework of UNet, which enhances the network depth, improves the fitting performance, and extracts small objects more accurately. The experimental results show that the network has achieved MIOU of 78.81% in the Massachusetts dataset, and the newly developed model outperforms UNet in both quantitative and qualitative aspects.

Call rating based on objective data extraction

Interaction channels are special opportunities to improve customer satisfaction by offering a consistent problem-solving experience. Contact center employees are the link between the company and the customer. They are responsible for maintaining an appropriate relationship between the company and the customer. So, they are personally responsible for the customer experience. In this paper, we present an objective evaluation method for evaluating customer-agent interaction, i.e., evaluating the effectiveness of the realization of customer requests from calls. The evaluation method is automatic and does not depend on the relationship between the call center manager and the employees. The motivation for evaluating calls stems from the key performance characteristics of a contact center, of which we particularly emphasize service time, first call resolution, handling time, and others.

Multi-Step Object Extraction Planning From Clutter Based on Support Relations

Multi-Step Object Extraction Planning From Clutter Based on Support Relations

A Two-Stage Method for Polyp Detection in Colonoscopy Images Based on Saliency Object Extraction and Transformers

A Two-Stage Method for Polyp Detection in Colonoscopy Images Based on Saliency Object Extraction and Transformers

Weakly Supervised Local–Global Anchor Guidance Network for Landslide Extraction With Image-Level Annotations

Weakly supervised learning using image-level annotations has become a popular choice for reducing labeling efforts of remote sensing object extraction. Existing methods exploit inter-pixel relations within an individual image patch for object localizations. When facing large-scale remote sensing images, it is still challenging to obtain global semantic contexts across image patches for feature representation, resulting in inaccurate object localizations. To remedy these issues, we propose a local-global anchor guidance network (LGAGNet) for weakly supervised landslide extraction. Specifically, a structure-aware object locating (SOL) module is developed to capture the spatial structure of landslide objects and extract local category anchors containing informative feature embeddings. Furthermore, we leverage a global anchor aggregation (GAA) module to excavate semantic patterns across image patches based on a memory bank, which is then used as additional context cues to enhance the feature presentation through a cross-attention mechanism. Finally, a hybrid loss function is designed to guide the network training, considering category-aware semantic contrasts and local activation consistency. Experimental results on high-resolution aerial and satellite image datasets verify the effectiveness of the proposed approach on landslide extraction.

Active Actions in the Extraction of Urban Objects for Information Quality and Knowledge Recommendation with Machine Learning.

Due to the increasing urban development, it has become important for municipalities to permanently understand land use and ecological processes, and make cities smart and sustainable by implementing technological tools for land monitoring. An important problem is the absence of technologies that certify the quality of information for the creation of strategies. In this context, expressive volumes of data are used, requiring great effort to understand their structures, and then access information with the desired quality. This study are designed to provide an initial response to the need for mapping zones in the city of Itajaí (SC), Brazil. The solution proposes to aid object recognition employing object-based classifiers OneR, NaiveBayes, J48, IBk, and Hoeffding Tree algorithms used together with GeoDMA, and a first approach in the use of Region-based Convolutional Neural Network (R-CNN) and the YOLO algorithm. All this is to characterize vegetation zones, exposed soil zones, asphalt, and buildings within an urban and rural area. Through the implemented model for active identification of geospatial objects with similarity levels, it was possible to apply the data crossover after detecting the best classifier with accuracy (85%) and the kappa agreement coefficient (76%). The case study presents the dynamics of urban and rural expansion, where expressive volumes of data are obtained and submitted to different methods of cataloging and preparation to subsidize rapid control actions. Finally, the research describes a practical and systematic approach, evaluating the extraction of information to the recommendation of knowledge with greater scientific relevance. Allowing the methods presented to apply the calibration of values for each object, to achieve results with greater accuracy, which is proposed to help improve conservation and management decisions related to the zones within the city, leaving as a legacy the construction of a minimum technological infrastructure to support the decision.

Fast Semantic-Aware Motion State Detection for Visual SLAM in Dynamic Environment

Existing visual SLAM (vSLAM) systems fail to perform well in dynamic environments as they cannot effectively ignore moving objects during pose estimation and mapping. We propose a lightweight approach to improve the robustness of existing feature based RGB-D and stereo vSLAM by accurately removing dynamic outliers in the scene that contribute to failures in pose estimation and mapping. First, a novel motion state detection algorithm using the depth and feature flow information is presented to identify regions in the scene with high moving probability. This information is then fused with semantic cues via a probability framework to enable accurate and robust moving object extraction to retain the useful features for pose estimation and mapping. To reduce the computational complexity of extracting semantic information in every frame, we propose to extract semantics only on keyframes with significant changes in image content. Semantic propagation is used to compensate for the changes in the intermediate frames (i.e., non-keyframes). This is achieved by computing the dense transformation map using the available feature flow vectors. The proposed techniques can be integrated into existing vSLAM systems to increase their robustness in dynamic environments without incurring much computation cost. Our work highlights the importance of distinguishing between motion states of potential moving objects for vSLAM in highly dynamic environments. We provide extensive experimental results on four well-known RGB-D and stereo datasets to show that the proposed technique outperforms existing vSLAM methods in indoor and outdoor environments under various dynamic scenarios including crowded scenes. We also perform our experiments on a low-cost embedded platform, i.e., Jetson TX1, to demonstrate the computational efficiency of our method.

Topology-based fluorescence image analysis for automated cell identification and segmentation.

Cell segmentation refers to the body of techniques used to identify cells in images and extract biologically relevant information from them; however, manual segmentation is laborious and subjective. We present Topological Boundary Line Estimation using Recurrence Of Neighbouring Emissions (TOBLERONE), a topological image analysis tool which identifies persistent homological image features as opposed to the geometric analysis commonly employed. We demonstrate that topological data analysis can provide accurate segmentation of arbitrarily-shaped cells, offering a means for automatic and objective data extraction. One cellular feature of particular interest in biology is the plasma membrane, which has been shown to present varying degrees of lipid packing, or membrane order, depending on the function and morphology of the cell type. With the use of environmentally-sensitive dyes, images derived from confocal microscopy can be used to quantify the degree of membrane order. We demonstrate that TOBLERONE is capable of automating this task.

Object extraction from image with big size based on bilateral grid

Currently image with big size segmentation suffers from low efficiency and inaccurate results, in this paper a novel object extraction approach from image with big size based on the application of a bilateral grid is proposed. Firstly, the bilateral grid is constructed according to the spatial ratio and color sampling ratios, which are determined by both image size and color range. Then, the big image data is splatted into the bilateral grid, the sampled data among the grid vertices are assigned by the nearest vertex data, and all grid vertices are assigned the object label via random forest classification. Finally, the segmentation is reconstructed from the grid data by interpolation. Experiment results show that the proposed algorithm could effectively improve the big image segmentation efficiency, and achieve the better segmentation results than state-of-the-art methods.

MAN-MADE OBJECT EXTRACTION FROM REMOTE SENSING IMAGES USING GABOR ENERGY FEATURES AND PROBABILISTIC NEURAL NETWORKS

This paper presents a novel approach for man-made object extraction in remote sensing images. This paper focuses on the design and implementation of a system that allows a user to extract multiple objects such as buildings or roads from an input image without much user intervention. The framework includes five main stages: 1) Pre-processing Stage. 2) Extraction of Local energy features using edge information and Gabor filter followed by down sampling to reduce the redundant information. 3) Further reduction of the size of feature vectors using Wavelet decomposition. 4) Classification and recognition of man-made structures using Probabilistic Neural Network (PNN) 5) NDVI based post-classification refinement. Experiments are conducted on a dataset of 200 RS images. The proposed framework yields overall accuracy of 93%. Experimental results validate the effective performance of the suggested technique for extracting man-made objects from RS images. Compared with other methods; the proposed framework exhibits significantly improved accuracy results and computationally much more efficient. Most notably, it has a much smaller input size, which makes it more feasible in practical applications.

An Object-Based Weighting Approach to Spatiotemporal Fusion of High Spatial Resolution Satellite Images for Small-Scale Cropland Monitoring

Continuous crop monitoring often requires a time-series set of satellite images. Since satellite images have a trade-off in spatial and temporal resolution, spatiotemporal image fusion (STIF) has been applied to construct time-series images at a consistent scale. With the increased availability of high spatial resolution images, it is necessary to develop a new STIF model that can effectively reflect the properties of high spatial resolution satellite images for small-scale crop field monitoring. This paper proposes an advanced STIF model using a single image pair, called high spatial resolution image fusion using object-based weighting (HIFOW), for blending high spatial resolution satellite images. The four-step weighted-function approach of HIFOW includes (1) temporal relationship modeling, (2) object extraction using image segmentation, (3) weighting based on object information, and (4) residual correction to quantify temporal variability between the base and prediction dates and also represent both spectral patterns at the prediction date and spatial details of fine-scale images. The specific procedures tailored for blending fine-scale images are the extraction of object-based change and structural information and their application to weight determination. The potential of HIFOW was evaluated from the experiments on agricultural sites using Sentinel-2 and RapidEye images. HIFOW was compared with three existing STIF models, including the spatial and temporal adaptive reflectance fusion model (STARFM), flexible spatiotemporal data fusion (FSDAF), and Fit-FC. Experimental results revealed that the HIFOW prediction could restore detailed spatial patterns within crop fields and clear crop boundaries with less spectral distortion, which was not represented in the prediction results of the other three models. Consequently, HIFOW achieved the best prediction performance in terms of accuracy and structural similarity for all the spectral bands. Other than the reflectance prediction, HIFOW also yielded superior prediction performance for blending normalized difference vegetation index images. These findings indicate that HIFOW could be a potential solution for constructing high spatial resolution time-series images in small-scale croplands.

EFFICIENT SPARSE STREET FURNITURE EXTRACTION FROM MOBILE LASER SCANNING POINT CLOUDS

Abstract. Current mobile systems are capable of efficiently acquiring dense urban point clouds. Still, operational use of such data is hampered by the lack of efficient object extraction methodology. Notably methodology is lacking for automatically extracting objects that do not belong to the road furniture like street signs and light poles but do belong to the street furniture. As an example, object we consider public garbage bins, that are installed and should be maintained in public areas in every city. However, information about types, locations, and condition of these public garbage bins are rarely updated and only obtained through manual measurements. Therefore, an efficient way of collecting information on such public objects is of interest not only for urban management but also when developing digital twins of a city. This study proposes a new method to automatically extract public garbage bins from large urban mobile laser scanning (MLS) point clouds. The proposed method consists of three main steps: (1) cell-, (2) sub-cell-, and (3) surface-based filtering, in which both spatial information of the point clouds and contextual knowledge of the public garbage bins are incorporated to efficiently remove irrelevant 3D points at an early phase and identify and classify different types of public garbage bins. Contextual knowledge includes shape and dimensions, and the relationship between the public garbage bins and the ground surface. A MLS dataset of the city centre of Rotterdam, the Netherlands, consisting of 2.84 billion points organised in 166 tiles of 50 × 75m, and covering an area of about 750 × 750m was used to test the proposed method. Results show that the method can automatically extract ~90 public garbage bins with an overall detection rate of 89.1%. Moreover, the executing time for the entire dataset was only about 163.6 minutes, which is equivalent to 3.46 seconds per one million points. Although the method was tested here one public garbage bins, it can be easily tuned for the detection of other street furniture objects, like benches, post boxes or bollards.

Moving objects extraction for building environmental maps describing human walking activity using a 3D LiDAR

ABSTRACT This study proposes an indoor movable static object extraction approach for building environmental maps that describe indoor human activities. In particular, it is essential to distinguishing people from non-human movable objects. To address this issue, we classify static objects into three categories based on their features. Methods for extracting movable static objects using each feature are presented. We conducted experiments and confirmed that the movable static objects were successfully detected and redefined as backgrounds, and only people were determined as dynamic objects.

A new procedure for lung region segmentation from computed tomography images

<span lang="EN-US">Lung cancer is the leading cause of cancer death among people worldwide. The primary aim of this research is to establish an image processing method for lung cancer detection. This paper focuses on lung region segmentation from computed tomography (CT) scan images. In this work, a new procedure for lung region segmentation is proposed. First, the lung CT scan images will undergo an image thresholding stage before going through two morphological reconstruction and masking stages. In between morphological and masking stages, object extraction, border change, and object elimination will occur. Finally, the lung field will be annotated. The outcomes of the proposed procedure and previous lung segmentation methods i.e., the modified watershed segmentation method is compared with the ground truth images for performance evaluation that will be carried out both in qualitative and quantitative manners. Based on the analyses, the new proposed procedure for lung segmentation, denotes better performance, an increment by 0.02% to 3.5% in quantitative analysis. The proposed procedure produced better-segmented images for qualitative analysis and became the most frequently selected method by the 22 experts. This study shows that the outcome from the proposed method outperforms the existing modified watershed segmentation method.</span>

S2105 Rectal Foreign Body Necessitating Surgical Intervention

Introduction: Rectal foreign bodies (RFB) present a unique management dilemma due to the variety of objects transanally impacted and their subsequent range of local trauma. A reluctance to seek medical assistance and present a candid recount of the incident can make diagnosis challenging and pose delays, further worsening the degree of injury before timely intervention can be provided. Consequently, our case aims to illustrate a systematic approach to the diagnosis and management of irretrievable rectal foreign bodies. Case Description/Methods: The case illustrates a 45-year-old gentleman who presented to the ER with severe rectal pain. He reported that earlier in the day, he had felt adventurous and had self-inserted a rubber sex toy into his rectum. He had been unsuccessful in removing the toy despite multiple efforts and explained that, as time passed, he experienced worsening rectal pain with mild bleeding at the insertion site. Upon confirmation of a large palpable foreign body on the rectal exam, a computed tomography of the abdomen/pelvis showed a large triangular radiopaque foreign body within the rectum measuring 8.8 × 9.4 × 17.0 cm along with severe rectal wall thickening. The patient was immediately taken to the operating room where multiple attempts to transanally remove the impacted object were unsuccessful. This ultimately necessitated an exploratory laparotomy and colotomy with subsequent partial colectomy. An end colostomy was matured after field contamination from the spillage of colonic contents during the extraction of the foreign object (Figure). Discussion: Rectal foreign bodies continue to be a clinical challenge with their increasing incidence. Although there is a predominance of RFBs in males, it is important to keep an impartial perspective. Notably, it is crucial to understand that RFBs are not limited to sexual satisfaction - but instead could be used for non-sexual purposes (ie, packing of illicit drugs). Consequently, all RFBs need to be regarded as potentially hazardous. The presented case highlights the importance of a systematic approach which includes ruling out peritoneal signs via physical exam and imaging for potential evidence of perforation. Thereafter, it is important to attempt a manual and transanal removal of the RFB. If all approaches are unsuccessful, surgery via laparoscopy will be necessary. During surgery, the object can be "milked" toward the rectum to be removed transanally. If unsuccessful, however, a colotomy is imperative as illustrated in the presented case.Figure 1.: (a) CT Abdomen/Pelvis transverse view showing displaced anterior urinary bladder secondary to mass effect from the large rectal foreign body (b) Sagittal view of radiopaque foreign body within the rectum measuring 8.8 × 9.4 × 17.0 cm in greatest TV/AP/CC dimensions (c) Post-surgical removal after unsuccessful transanal extraction.

Application of Embedded Intelligent Target Detection System in Basketball Movement Test

With the development of society, basketball has been deeply loved by people all over the world. Meanwhile, basketball has become one of the most watched events in the world. In order to adapt to the development of basketball and make people better understand the laws of basketball, this paper aims to study the application of embedded intelligent object detection system in basketball sports test and use the embedded intelligent object detection system to separate basketball sports. Compared with the general computer processing system, the embedded system has great differences. It cannot realize the large-capacity storage function because there is no matching large-capacity medium. Strengthen the learning of basketball theoretical knowledge through learning rules. Firstly, the research background of basketball and the research significance of moving target detection are introduced, and the embedded Linus operating system is introduced, including hardware design and software design. Then, four moving target detection algorithms are proposed. Object detection, also called object extraction, is an image segmentation based on the geometric and statistical features of objects, and its accuracy and real-time performance are an important capability of the entire system. Experiments show that when using the YCrCb domain detection algorithm, the average time-consuming is 292 ms, and the conversion frame rate is about 3.5fps. The YCrCb domain detection algorithm has good detection effect and high efficiency.

RERB: A Dataset for Residential Area Extraction with Regularized Boundary in Remote Sensing Imagery for Mapping Application

Due to the high automaticity and efficiency of image-based residential area extraction, it has become one of the research hotspots in surveying, mapping, and computer vision, etc. For the application of mapping residential area, the extracted contour is required to be regular. However, the contour results of existing deep-learning-based residential area extraction methods are assigned accurately according to the actual range of residential areas in imagery, which are difficult to directly apply to mapping due to the extractions being messy and irregular. Most of the existing ground object extraction datasets based on optical satellite images mainly promote the research of semantic segmentation, thereby ignoring the requirements of mapping applications. In this paper, we introduce an optical satellite images dataset named RERB (Residential area Extraction with Regularized Boundary) to support and advance end-to-end learning of residential area mapping. The characteristic of RERB is that it embeds the prior knowledge of regularized contour in the dataset. In detail, the RERB dataset contains 13,892 high-quality satellite images with a spatial resolution of 2 m acquired from different cities in China, and the size of each image is approximately 256 × 256 pixels, which covers an area of more than 3640 square kilometers. The novel published RERB dataset encompasses four superiorities: (1) Large-scale and high-resolution; (2) well annotated and regular label contour; (3) rich background; and (4) class imbalance. Therefore, the RERB dataset is suitable for both semantic segmentation and mapping application tasks. Furthermore, to validate the effectiveness of the RERB, a novel end-to-end regularization extraction algorithm of residential areas based on contour cross-entropy constraints is designed and implemented, which can significantly improve the regularization degree of extraction for the mapping of residential areas. The comparative experimental results demonstrate the preponderance and practicability of our public dataset and can further facilitate future research.

Foreground Detection Based on Superpixel and Semantic Segmentation.

Foreground detection is an essential step in computer vision and video processing. Accurate foreground object extraction is crucial for subsequent high-level tasks such as target recognition and tracking. Although many foreground detection algorithms have been proposed, foreground detection in complex scenes is still a challenging problem. This paper presents a foreground detection algorithm based on superpixel and semantic segmentation. It first uses multiscale superpixel segmentation to obtain the initial foreground mask. At the same time, a semantic segmentation network is applied to separate potential foreground objects, and then use the defined rules to combine the results of superpixel and semantic segmentation to get the final foreground object. Finally, the background model is updated with the refined foreground result. Experiments on the CDNet2014 dataset demonstrate the effectiveness of the proposed algorithm, which can accurately segment foreground objects in complex scenes.