Approach For Boundary Detection Research Articles

Fall Detection and Boundary Detection in Care Homes

The elderly population represents a significant and rapidly expanding demographic, with a majority experiencing frequent daily accidents, notably falls. Falls rank as the second leading cause of accidental injury deaths globally. To address this issue, we propose a video classification system designed specifically for fall detection. Our fall detection framework comprises two key steps: firstly, the detection of human posture within video frames, followed by fall classification using Convolutional Neural Networks (CNNs). Additionally, we introduce a novel approach for boundary detection, utilizing object detection techniques beyond a predefined line of surveillance captured by a single camera. Through this integrated methodology, we aim to enhance fall detection and boundary breach detection capabilities, thereby contributing to the advancement of elderly care and safety. (Abstract).

A Real-Time Road Boundary Detection Approach in Surface Mine Based on Meta Random Forest

A Real-Time Road Boundary Detection Approach in Surface Mine Based on Meta Random Forest

Method for detecting tree ring boundary in conifers and broadleaf trees using Mask R-CNN and linear interpolation

As tree rings can reveal various information regarding climate and environmental factors, increasing research is being conducted on them. Although tree ring analysis software such as Windendro has been applied, research on the development of analysis software using image preprocessing algorithms and deep learning is recently being attempted as computer vision technology. In this study, Mask R-CNN and linear interpolation were applied from images collected using a smartphone (SM-G973, Samsung, Suwon) and a scanner (CanoScan 9000F, Canon, Otaku) to propose an effective method for detecting tree ring boundaries. Pitch pine (Pinus rigida), Korean pine (Pinus koraiensis), white birch (Betula platyphylla), and cork oak (Quercus variabilis) were selected as tree species. Of the 300 images, 240 were classified as training data and 60 as validation data. As a result of learning, smartphones detected 86.0 % (381 ring boundaries) of the rings in pitch pine, 82.1 % (367 ring boundaries) in Korean pine, 84.7 % (309 ring boundaries) in white birch, and 78.7 % (318 ring boundaries) in cork oak. The scanner detected 93.2 % (413 ring boundaries) of the rings in pitch pine, 90.8 % (405 ring boundaries) in Korean pine, 88.2 % (322 ring boundaries) in white birch, and 89.4 % (361 ring boundaries) in cork oak. In particular, the smartphone showed satisfactory results of 84.7 % and 78.7 % for detecting tree ring boundaries of white birch and cork oak, where the boundaries of the rings were unclear. In the annual growth analysis results, both smartphones and scanners were statistically insignificant, and there was no difference compared with those of Windendro. Therefore, Mask R-CNN might be an effective approach for tree ring boundary detection as it showed satisfactory results, even with smartphones. In addition, although there was distortion in cases where images were acquired with a circular lens, there was no statistically significant difference from Windendro results. Thus, Mask R-CNN and linear interpolation can be used for tree ring boundary detection and growth measurement.

Towards Automated Ethogramming: Cognitively-Inspired Event Segmentation for Streaming Wildlife Video Monitoring

Advances in visual perceptual tasks have been mainly driven by the amount, and types, of annotations of large-scale datasets. Researchers have focused on fully-supervised settings to train models using offline epoch-based schemes. Despite the evident advancements, limitations and cost of manually annotated datasets have hindered further development for event perceptual tasks, such as detection and localization of objects and events in videos. The problem is more apparent in zoological applications due to the scarcity of annotations and length of videos-most videos are at most ten minutes long. Inspired by cognitive theories, we present a self-supervised perceptual prediction framework to tackle the problem of temporal event segmentation by building a stable representation of event-related objects. The approach is simple but effective. We rely on LSTM predictions of high-level features computed by a standard deep learning backbone. For spatial segmentation, the stable representation of the object is used by an attention mechanism to filter the input features before the prediction step. The self-learned attention maps effectively localize the object as a side effect of perceptual prediction. We demonstrate our approach on long videos from continuous wildlife video monitoring, spanning multiple days at 25 FPS. We aim to facilitate automated ethogramming by detecting and localizing events without the need for labels. Our approach is trained in an online manner on streaming input and requires only a single pass through the video, with no separate training set. Given the lack of long and realistic (includes real-world challenges) datasets, we introduce a new wildlife video dataset–nest monitoring of the Kagu (a flightless bird from New Caledonia)–to benchmark our approach. Our dataset features a video from 10 days (over 23 million frames) of continuous monitoring of the Kagu in its natural habitat. We annotate every frame with bounding boxes and event labels. Additionally, each frame is annotated with time-of-day and illumination conditions. We will make the dataset, which is the first of its kind, and the code available to the research community. We find that the approach significantly outperforms other self-supervised, traditional (e.g., Optical Flow, Background Subtraction) and NN-based (e.g., PA-DPC, DINO, iBOT), baselines and performs on par with supervised boundary detection approaches (i.e., PC). At a recall rate of 80%, our best performing model detects one false positive activity every 50 min of training. On average, we at least double the performance of self-supervised approaches for spatial segmentation. Additionally, we show that our approach is robust to various environmental conditions (e.g., moving shadows). We also benchmark the framework on other datasets (i.e., Kinetics-GEBD, TAPOS) from different domains to demonstrate its generalizability. The data and code are available on our project page: https://aix.eng.usf.edu/research_automated_ethogramming.html

Highly Sensitive and Durable, Triboelectric Based Self‐Powered Nanosensor for Boundary Detection in Sports Event

AbstractAssisted adjudication of sports activities and events is becoming more intelligent with the rapid development of the Internet of Things (IoTs). Sensors such as pressure sensors and image sensors have been widely used in sports events, but their durability and energy supply are still challenge. Herein, a novel boundary detection sensor based on hyperelastic triboelectric nanogenerator (H‐TENG) for intelligent boundary detection is proposed. The stress–strain of a tennis ball colliding with H‐TENG at high speed and the sensing stability are investigated by simulation analysis and experimental validation. The pressure sensitivity of 2.96 V kPa−1 is achieved with excellent linearity (R2 = 0.957082) at the pressure of 2.8–13 kPa. And at the velocity of 2–4.47 m s−1, the velocity sensitivity reaches ‐10.76 V (m s−1)−1 with excellent linearity (R2 = 0.948758). Furthermore, a four‐channels signal acquisition system is constructed for enhancing the detection accuracy, and the response times of signal feedback are less than 45 ms. This work not only provides a novel approach for intelligent boundary detection in sporting events, but also demonstrates its promising applications in multiple challenges and quick penalties in sports competitions, as well as in intelligent and digital training of athletes.

Real-world sentence boundary detection using multitask learning: A case study on French

AbstractWe propose a novel approach for sentence boundary detection in text datasets in which boundaries are not evident (e.g., sentence fragments). Although detecting sentence boundaries without punctuation marks has rarely been explored in written text, current real-world textual data suffer from widespread lack of proper start/stop signaling. Herein, we annotate a dataset with linguistic information, such as parts of speech and named entity labels, to boost the sentence boundary detection task. Via experiments, we obtained F1 scores up to 98.07% using the proposed multitask neural model, including a score of 89.41% for sentences completely lacking punctuation marks. We also present an ablation study and provide a detailed analysis to demonstrate the effectiveness of the proposed multitask learning method.

Multidirectional Gabor Filter-Based Approach for Pectoral Muscle Boundary Detection

Accurate pectoral muscle boundary (PMB) detection is a crucial stage in any computer-aided detection (CAD) system, used for automatic detection of various possible signs of malignancy in a mammographic image. The presence of high-density glandular tissues overlapping PMB, pectoral muscle of small size and low density, presence of pectoralis minors, etc., poses a significant challenge for researchers working on automatic PMB detection problem. In mammograms with pectoral muscle superimposed by high-density glandular tissues, especially near the lower portion of the pectoral muscle, PMB forms fuzzy textural edges with surrounding mammary tissues regions. The performance of any intensity-based approach in detecting such fuzzy textural edges is poor. Here, we present a multidirectional Gabor filter (MDGF)-based approach for PMB detection. A set of three high-frequency bandpass Gabor filters is designed, which covers all the possible orientations of PMB present in a preprocessed mediolateral oblique (MLO) view mammogram. These filters are used to extract high- and mid-frequency range edge information corresponding to strong as well as weak fuzzy textural edges of PMB. The information obtained from magnitude and phase response along with a boundary search and merge algorithm (designed to connect broken PMB edges) is used to detect complete PMB with high accuracy. With PMB detection accuracy of 95.28% for MIAS, 96.50% for CBIS-DDSM, and 96.95% for INbreast database mammograms, the proposed method outperforms many state-of-the-art methods, thus show its suitability for a CAD system.

A novel segmentation approach for work mode boundary detection in MFR pulse sequence

Understanding and analysis of multi-function radar (MFR) work modes play a key role in radar countermeasures. Many methods have been proposed for recognizing the work modes. However, segmentation of pulse sequence is prior to the mode recognition as the mode transition boundaries are not known in advance for the whole sequence. To solve the boundary detection problem, an unsupervised segmentation method based on recurrence plot (RP) and singular value decomposition (SVD) is proposed in this paper. The method utilizes RP to reveal the characteristic change of the pulse sequence, and makes a quantitative analysis through SVD to extract the main information of work mode. Then, discrepancy measure is employed to detect the boundary, thus determining whether or not the mode transition has occurred. The proposed method can recognize the transition boundaries at different granularity levels. Experimental results show that our method achieves better performance than existing segmentation methods and is robust to non-ideal conditions.

Video retrieval framework based on color co-occurrence feature of adaptive low rank extracted keyframes and graph pattern matching

In recent times, exploration of multimedia required ever increasing demand and application for intelligent video retrieval from repositories. This paper presents an efficient video retrieval framework by employing the effective singular value decomposition and computationally low complex ordered dither block truncation coding to extract simple, compact, and well discriminative Color Co-occurrence Feature (CCF). In this context, the occurrence probability of a video frame pixel in the neighborhood is employed to formulate this specific and distinct feature. Moreover, we applied a new adaptive low rank thresholding based on energy concentricity, transposition, and replacement invariance characteristics to formulate a unified fast shot boundary detection approach to solve the protuberant bottleneck problem for real-time cut and gradual transition that eventually contributes for effective keyframes extraction. Therefore, we can assert that the keyframes are distinct and discriminative to represent the whole video content. For effective indexing and retrieval, it is imperative to formulate similarity score evaluator for the encapsulated contextual video information with substantial temporal consistency, least computation, and post-processing. Therefore, we introduced graph-based pattern matching for video retrieval with an aim to sustain temporal consistency, accuracy and time overhead. Experimental results signify that the proposed method on average provides 7.40% and 17.91% better retrieval accuracy and 23.21% and 20.44% faster than the recent state-of-the-art methods for UCF11 and HMDB51 standard video dataset, respectively.

Chinese named-entity recognition via self-attention mechanism and position-aware influence propagation embedding

Chinese Named Entity Recognition (NER) has received extensive research attention in recent years. However, Chinese texts lack delimiters to divide the boundaries of words, and some existing approaches cannot capture the long-distance interdependent features. In this paper, we propose a novel end-to-end model for Chinese NER. A new global word boundary detection approach is designed to capture the semantic dependency via a self-attention mechanism to represent character embedding by assigning compatible weights for each character in a sentence. To improve the representation ability of Chinese named-entity boundaries, we introduce position-aware influence propagation with the Gaussian kernel for each character, which combines convergence propagation and radiation propagation. Convergence propagation mainly measures the influence of surrounding characters on the target character. The purpose of radiation propagation is to measure the range of influence of the target character on surrounding characters. The proposed method has been evaluated and shown to offer strong performance in two Chinese NER datasets: MSRA and PFR.

Efficient Lung Infection Detection using Machine Learning Approach

Extraction of various structures from the chest X-ray (CXR) pictures ANd abnormal classification ar typically performed as an initial step in computer-aided diagnosis/detection (CAD) systems. With the growing range of patients, the doctors overwork and can't counsel and beware of all their patients. This paper presents our machine-controlled approach for respiratory organ boundary detection and CXR classification in standard poster anterior chest radiographs. We tend to extract the respiratory organ regions, sizes of regions, and form irregularities with segmentation techniques that are utilized in image process. At the start data sets were collected and preprocessed to avoid unwanted or howling data and born-again into needed image size. CNN is employed to investigate pictures and notice whether or not the actual patient is full of respiratory organ infection or not. By utilizing deep learning approach correct detection of unwellness infection has been done. With relevancy current scenario each traditional and covid pictures are utilized for prediction.

Sequence-based visual place recognition: a scale-space approach for boundary detection

Sequence-based visual place recognition: a scale-space approach for boundary detection

A novel bifold-stage shot boundary detection algorithm: invariant to motion and illumination

Shot boundary detection is mainly considered as a stepping stone in the broad arena of content-based video retrieval. Ample systematic investigation has been carried out in the terrain of shot boundary detection. The attainment of shot boundary detection procedures is greatly hindered due to the presence of unforeseen illumination change and motion effects in a video. This work proposes a novel bifold-stage technique to recognize abrupt transition in videos, invariant to motion, and illumination effects. In the first stage, the local ternary patterns feature is used to extract information from each frame in a video. Then, a set of novel adaptive thresholds such as $${\gamma }$$ and $${{{\beta }}}$$ are used to find the possible transition frames. In the confirmation stage, Lab color difference along with an adaptive threshold $${\delta }$$ is used to extract actual transition frames. The experimental result depicts that the motion effect is also scaled down in the initial stage. The Lab color difference passed down in the second stage also handles the illumination and motion effects which are not managed in the initial stage. Experimentation is done using TRECVid 2001 and 2007 standard datasets and palpable that the proposed technique outperforms most of the contemporary shot boundary detection approaches.

Multiview video summarization using video partitioning and clustering

Multiview video summarization plays a crucial role in abstracting essential information form multiple videos of the same location and time. In this paper, we propose a new approach for the multiview summarization. The proposed approach uses the BIRCH clustering algorithm for the first time on the initial set of frames to get rid of the static and redundant. The work presents a new approach for shot boundary detection using frame similarity measures Jaccard and Dice. The algorithm performs effectively synchronized merging of keyframes from all camera-views to obtain the final summary. Extensive experimentation conducted on various datasets suggests that the proposed approach significantly outperforms most of the existing video summarization approaches. To state a few, a 1.5% improvement on video length reduction, 24.28% improvement in compression ratio, and 6.4% improvement in quality assessment ratio is observed on the lobby dataset.

Shot based keyframe extraction using edge-LBP approach

Advancement in technology has led to tremendous increase in the online video content that requires efficient and effective content based video analysis approaches. In this regard, efficient approach for abrupt Shot Boundary Detection (SBD) and keyframe extraction has been presented. The proposed method detects abrupt shots by extracting binarized edge information from frames for texture characterisation using Local Binary Pattern (LBP) method. Further, Euclidean distance has been applied on the histogram features constructed and an adaptive threshold is used to detect abrupt shots. During keyframe extraction phase, magnitude gradient using Sobel operator has been extracted from each frame of the segmented shot. Subsequently, magnitude values are transformed into Z-score which describes the position of each pixelin terms of its distance from themean, when measured in standard deviation units of every frame. Finally, Co-efficient of variation is computed for each frame and the frame possessing the highest value is selected as a keyframe from every shot. Experiments were conducted on TRECVID 2001 dataset to analyze and validate the proposed approach. Experimental result manifest that the proposed SBD and keyframe extraction method outperforms some of the state-of-the-art algorithms with average F1-score of 98.15% and average fidelity measure of 90% respectively.

Retinal Boundary Segmentation in Stargardt Disease Optical Coherence Tomography Images Using Automated Deep Learning.

PurposeTo use a deep learning model to develop a fully automated method (fully semantic network and graph search [FS-GS]) of retinal segmentation for optical coherence tomography (OCT) images from patients with Stargardt disease.MethodsEighty-seven manually segmented (ground truth) OCT volume scan sets (5171 B-scans) from 22 patients with Stargardt disease were used for training, validation and testing of a novel retinal boundary detection approach (FS-GS) that combines a fully semantic deep learning segmentation method, which generates a per-pixel class prediction map with a graph-search method to extract retinal boundary positions. The performance was evaluated using the mean absolute boundary error and the differences in two clinical metrics (retinal thickness and volume) compared with the ground truth. The performance of a separate deep learning method and two publicly available software algorithms were also evaluated against the ground truth.ResultsFS-GS showed an excellent agreement with the ground truth, with a boundary mean absolute error of 0.23 and 1.12 pixels for the internal limiting membrane and the base of retinal pigment epithelium or Bruch's membrane, respectively. The mean difference in thickness and volume across the central 6 mm zone were 2.10 µm and 0.059 mm3. The performance of the proposed method was more accurate and consistent than the publicly available OCTExplorer and AURA tools.ConclusionsThe FS-GS method delivers good performance in segmentation of OCT images of pathologic retina in Stargardt disease.Translational RelevanceDeep learning models can provide a robust method for retinal segmentation and support a high-throughput analysis pipeline for measuring retinal thickness and volume in Stargardt disease.

Video shot boundary detection using block based cumulative approach

Video data is becoming an indispensable part of today’s Big Data due to evolution of social web and mobile technology. Content based video analysis has become crucial for video management. Shot boundary detection is one of the most essential task in video content analysis. In view of this, an efficient shot boundary detection approach to detect abrupt and gradual transition in videos is proposed in this work. The approach extracts block based Mean Cumulative Sum Histogram (MCSH) from each edge gradient fuzzified frame as a combination of local and global feature. The relative standard deviation (RSD) statistical measure is applied on the obtained MCSH to detect abrupt and gradual shots in the video. Efficacy of the proposed method is measured by conducting experiments on TRECVID 2001, TRECVID 2007 and VideoSeg datasets. The proposed method shows relatively a good performance when compared to some of the state-of-the-art shot boundary detection approaches.

Domain Generalization for Named Entity Boundary Detection via Metalearning.

Named entity recognition (NER) aims to recognize mentions of rigid designators from text belonging to predefined semantic types, such as person, location, and organization. In this article, we focus on a fundamental subtask of NER, named entity boundary detection, which aims at detecting the start and end boundaries of an entity mention in the text, without predicting its semantic type. The entity boundary detection is essentially a sequence labeling problem. Existing sequence labeling methods either suffer from sparse boundary tags (i.e., entities are rare and nonentities are common) or they cannot well handle the issue of variable size output vocabulary (i.e., need to retrain models with respect to different vocabularies). To address these two issues, we propose a novel entity boundary labeling model that leverages pointer networks to effectively infer boundaries depending on the input sequence. On the other hand, training models on source domains that generalize to new target domains at the test time are a challenging problem because of the performance degradation. To alleviate this issue, we propose Metabdry, a novel domain generalization approach for entity boundary detection without requiring any access to target domain information. Especially, adversarial learning is adopted to encourage domain-invariant representations. Meanwhile, metalearning is used to explicitly simulate a domain shift during training so that metaknowledge from multiple resource domains can be effectively aggregated. As such, Metabdry explicitly optimizes the capability of "learning to generalize," resulting in a more general and robust model to reduce the domain discrepancy. We first conduct experiments to demonstrate the effectiveness of our novel boundary labeling model. We then extensively evaluate Metabdry on eight data sets under domain generalization settings. The experimental results show that Metabdry achieves state-of-the-art results against the recent seven baselines.

Tooth segmentation and gingival tissue deformation framework for 3D orthodontic treatment planning and evaluating.

In this study, we propose an integrated tooth segmentation and gingival tissue deformation simulation framework used to design and evaluate the orthodontic treatment plan especially with invisible aligners. Firstly, the bio-characteristics information of the digital impression is analyzed quantitatively and demonstrated visually. With the derived information, the transitional regions of tooth-tooth and tooth-gingiva are extracted as the solution domain of the segmentation boundaries. Then, a boundary detection approach is proposed, which is used for the tooth segmentation and region division of the digital impression. After tooth segmentation, we propose the deformation simulation framework driven by energy function based on the biological deformation properties of gingival tissues. The correctness and availability of the proposed segmentation and gingival tissue deformation simulation framework are demonstrated with typical cases and qualitative analysis. Experimental results show that segmentation boundaries calculated by the proposed method are accurate, and local details of the digital impression under study are preserved well during deformation simulation. Qualitative analysis results of the gingival tissues' surface area and volume variations indicate that the proposed gingival tissue deformation simulation framework is consistent with the clinical gingival tissue deformation characteristics, and it can be used to predict the rationality of the treatment plan from both visual inspection and numerical simulation. The proposed tooth segmentation and gingival tissue deformation simulation framework is shown to be effective and has good practicability, but accurate quantitative analysis based on clinical results is still an open problem in this study. Combined with tooth rearrangement steps, it can be used to design the orthodontic treatment plan, and to output the data for production of invisible aligners. Graphical abstract.

Dual Tree Discrete Wavelet Transform and Entropy based Approach for Video Shot Boundary Detection

Shot Boundary detection is one of the most prominent steps for the various video processing techniques like indexing of videos, video retrieval, video summarization, video scene analysis, etc. In this paper, we have projected a useful technique based on dual-tree Discrete Wavelet Transform. The dual-tree structure with selected filters returns the approximate decomposition in an analytical manner. Due to the existence of the two trees, the noise component is characterized precisely. The outcome of the DTDWT is distortion less with normalized localized function and exact reconstruction of the signal. WE have used the entropy function to measure the uncertainty in the random variable. Finally, we evaluated the algorithm using Recall, Precision, and F1 measure. Experimental results demonstrate the efficiency of the given method.