Low complexity object detection and tracking with inter-layer graph mapping and intra-layer graph refinement in H.264/SVC bitstreams

Object detection and tracking is one of the key applications of wireless sensor networks (WSNs). The key issues associated with this application include network lifetime, object detection and localization accuracy. To ensure the high quality of the service, there should be a trade-off between energy efficiency and detection accuracy, which is challenging in a resource-constrained WSN. Most researchers have enhanced the application lifetime while achieving target detection accuracy at the cost of high node density. They neither considered the system cost nor the object localization accuracy. Some researchers focused on object detection accuracy while achieving energy efficiency by limiting the detection to a predefined target trajectory. In particular, some researchers only focused on node clustering and node scheduling for energy efficiency. In this study, we proposed a mobile object detection and tracking framework named the Energy Efficient Object Detection and Tracking Framework (EEODTF) for heterogeneous WSNs, which minimizes energy consumption during tracking while not affecting the object detection and localization accuracy. It focuses on achieving energy efficiency via node optimization, mobile node trajectory optimization, node clustering, data reporting optimization and detection optimization. We compared the performance of the EEODTF with the Energy Efficient Tracking and Localization of Object (EETLO) model and the Particle-Swarm-Optimization-based Energy Efficient Target Tracking Model (PSOEETTM). It was found that the EEODTF is more energy efficient than the EETLO and PSOEETTM models.

Diabetic retinopathy (DR) poses a significant threat to vision if left undetected and untreated. This paper addresses this challenge by utilizing advanced deep learning (DL) algorithms with established image processing techniques to enhance accuracy and efficiency in detection. Image processing extracts critical features from retinal images, acting as early warning signs for DR. Our proposed hybrid model combines image processing and machine learning (ML) strengths, leveraging discriminative abilities and custom features. The methodology involves data acquisition from a diverse dataset, data augmentation to enrich training data, and a multistep image processing pipeline. Feature extraction utilizes ResNet50, InceptionV3, and visual geometry group (VGG)‐19 and combines their outputs for classification. Classification employs a decision tree (DT), K‐nearest neighbor (KNN), support vector machine (SVM), and a modified convolutional neural network (CNN) with a spatial attention layer. Our work proposed a hybrid attention‐based stacking ensemble with the mentioned models in the base layer and logistic regression model as meta layer, which further enhanced accuracy. The system, evaluated through metrics like confusion matrix, accuracy, and receiver operating characteristic (ROC) curve, promises improved diagnostic capabilities. The proposed methodology yields an accuracy of 99.768%.

With the continuous growth of electricity demand, the safety and stability of transmission lines have become increasingly important. To ensure the reliability of power supply, it is essential to promptly detect and address foreign object intrusions on transmission lines, such as tree branches, kites, and balloons. Addressing the issues where foreign objects can cause power outages and severe safety accidents, as well as the inefficiency, time consumption, and labor-intensiveness of traditional manual inspection methods, especially in large-scale power transmission lines, we propose an enhanced YOLOv8-based model for detecting foreign objects. This model incorporates the Swin Transformer, AFPN (Asymptotic Feature Pyramid Network), and a novel loss function, Focal SIoU, to improve both the accuracy and real-time detection of hazards. The integration of the Swin Transformer into the YOLOv8 backbone network significantly improves feature extraction capabilities. The AFPN enhances the multi-scale feature fusion process, effectively integrating information from different levels and improving detection accuracy, especially for small and occluded objects. The introduction of the Focal SIoU loss function optimizes the model’s training process, enhancing its ability to handle hard-to-classify samples and uncertain predictions. This method achieves efficient automatic detection of foreign objects by comprehensively utilizing multi-level feature information and optimized label matching strategies. The dataset used in this study consists of images of foreign objects on power transmission lines provided by a power supply company in Jilin, China. These images were captured by drones, offering a comprehensive view of the transmission lines and enabling the collection of detailed data on various foreign objects. Experimental results show that the improved YOLOv8 network has high accuracy and recall rates in detecting foreign objects such as balloons, kites, and bird nests, while also possessing good real-time processing capabilities.

H.264/AVC의 확장 표준으로 제정된 SVC는 향상 계층에서 압축 효율을 높이기 위해 인트라 예측과 인터 예측뿐만 아니라 계층 간 예측을 추가로 수행한다. 그로 인해 부호화 계산량이 더욱 증가되는 문제점이 있다. 본 논문은 SVC 공간적 향상 계층에서 계산량을 효과적으로 감소시키는 빠른 인트라 부호화를 위한 효율적인 모드 결정 방법을 제안한다. 제안 방법은 크게 2단계로 이루어진다. 1단계에서는 Intra_BL 모드의 RD 값을 이웃 매크로블록의 최적 RD 값과 비교하고 이웃 매크로블록의 최적 예측 모드와 유사한 특성을 이용하여 Intra_BL 모드를 미리 결정한다. 2단계에서는 기본 계층과 향상 계층의 인트라 예측 모드의 상관성을 이용하여 인트라 예측의 후보 모드를 선택적으로 줄임으로써 전체 부호화 시간을 감소시킨다. 실험결과, 제안하는 방법은 JSVM 9.16보다 전체 부호화 시간을 48.15~56.32% 감소하면서 화질의 변화는 거의 없었다. SVC is an emerging video coding standard as an extension of H.264/AVC. This standard uses inter prediction, intra prediction and a new inter-layer prediction to improve coding performance of enhancement layers. However, it has high computational complexity. In this paper, we propose an efficient intra prediction mode decision method in the spatial enhancement layer to reduce the computational complexity. The proposed method consists of two phases. In the first phase, Intra_BL mode is selected using the RD cost of Intra_BL in advance. We exploit the fact that the RD cost and prediction mode are similar to those of neighbor macroblocks. In the second phase, we predict the enhancement layer mode using correlation between intra mode of enhancement layer and that of the base layer. Experimental results show that the proposed method could save from 48.15% to 56.32% in encoding time while degradation in video quality is negligible.

Psychometric methods for accurate and timely detection of item compromise have been a long‐standing topic. While Bayesian methods can incorporate prior knowledge or expert inputs as additional information for item compromise detection, they have not been employed in item compromise detection itself. The current study proposes a two‐phase Bayesian change‐point framework for both stationary and real‐time detection of changes in each item's compromise status. In Phase I, a stationary Bayesian change‐point model for compromise detection is fitted to the observed responses over a specified time‐frame. The model produces parameter estimates for the change‐point of each item from uncompromised to compromised, as well as structural parameters accounting for the post‐change response distribution. Using the post‐change model identified in Phase I, the Shiryaev procedure for sequential testing is employed in Phase II for real‐time monitoring of item compromise. The proposed methods are evaluated in terms of parameter recovery, detection accuracy, and detection efficiency under various simulation conditions and in a real data example. The proposed method also showed superior detection accuracy and efficiency compared to the cumulative sum procedure.

Substantial numbers of patients are reaching to a progressive breast cancer stage due to increase in the false negatives coming out of cumbersome and tedious job of continuously observing the mammograms in fatigue. Hence, the early detection of cancer with more accuracy is highly expected to reduce the death rate. Computer Aided Detection (CADe) can help radiologists in providing a second opinion increasing the overall accuracy of detection. Pectoral muscle is a predominant density area in most mammograms and may bias the results. Its extraction can increase accuracy and efficiency of cancer detection. This work is intended to provide the researchers a systematic and comprehensive overview of different techniques of pectoral muscle extraction which are categorized into groups based on intensity, region, gradient, transform, probability and polynomial, active contour, graph theory, and soft computing approaches. The performance of all these methods is summarized in tabular form for comparison purpose. The accuracy, efficiency and computational complexities of some selected methods are discussed in view of deciding a best approach in each of the categories.

With the rapid advancement of technology, satellite and drone technologies have had significant impacts on various fields, creating both opportunities and challenges. In areas like the military, urban planning, and environmental monitoring, the application of remote sensing technology is paramount. However, due to the unique characteristics of remote sensing images, such as high resolution, large-scale scenes, and small, densely packed targets, remote sensing object detection faces numerous technical challenges. Traditional detection methods are inadequate for effectively detecting small targets, rendering the accurate and efficient detection of objects in complex remote sensing images a pressing issue. Current detection techniques fall short in accurately detecting small targets compared to medium and large ones, primarily due to limited feature information, insufficient contextual data, and poor localization capabilities for small targets. In response, we propose an innovative detection method. Unlike previous approaches that often focused solely on either local or contextual information, we introduce a novel Global and Local Attention Mechanism (GAL), providing an in-depth modeling method for input images. Our method integrates fine-grained local feature analysis with global contextual information processing. The local attention concentrates on details and spatial relationships within local windows, enabling the model to recognize intricate details in complex images. Meanwhile, the global attention addresses the entire image’s global information, capturing overarching patterns and structures, thus enhancing the model’s high-level semantic understanding. Ultimately, a specific mechanism fuses local details with global context, allowing the model to consider both aspects for a more precise and comprehensive interpretation of images. Furthermore, we have developed a multi-head prediction module that leverages semantic information at various scales to capture the multi-scale characteristics of remote sensing targets. Adding decoupled prediction heads aims to improve the accuracy and robustness of target detection. Additionally, we have innovatively designed the Ziou loss function, an advanced loss calculation, to enhance the model’s precision in small target localization, thereby boosting its overall performance in small target detection. Experimental results on the Visdrone2019 and DOTA datasets demonstrate that our method significantly surpasses traditional methods in detecting small targets in remote sensing imagery.

We propose a very simple scalable video coding (SVC) system based on the H.264 baseline profile codec. The proposed SVC algorithm can offer three levels of the temporal and spatial scalability - QVGA@15fps, QVGA@30fps, and VGA@30fps. The proposed system achieves the temporal scalability by encoding every other picture as the non-reference P-picture, so that the base layer codec dealing with the QVGA@15fps sequence is fully-compatible with the satellite-digital multimedia broadcasting (S-DMB) system in Korea. In addition, the same decoder can reconstruct the QVGA@30fps sequence when it receives the bits representing the non-reference pictures. For the spatial enhancement layer, the encoder follows the standard H.264 baseline profile except the inter-layer intra prediction. To reduce the computational burden of the encoder, the enhancement layer encoder may skip the motion estimation procedure by interpolating the motion field with that of the base layer. Simulation results show that the proposed system yields less then about 12% of loss in the reconstruction picture quality compared with the anchor H.264 JM encoder. The proposed SVC system still has a room for improvement of coding efficiency by trading with the computational complexity, so that lots of further works are required.

Object tracking is a dynamic optimization process based on the temporal information related to the previous frames. Proposing a method with higher precision in complex environments is a challenge for researchers in the field of study. In this research, efficient object detection and movement tracking video is proposed. Here we are considering the input video sequence is PETS and Hall monitor video. Kernel fuzzy c-means procedure still endures several downsides, such as reduced convergence rate, obtaining stuck in the local minima as well as at risk to initialization level of sensitivity. Ant colony optimization algorithm is a new population-based optimization technique that has actually been utilized effectively for resolving numerous complicated difficulties. This research suggested a new strategy called ACO–MKFCM to resolve MKFCM initialization issue making use of ant colony optimization (ACO) algorithm to locate optimum first cluster centres for the MKFCM, hence enhance all applications associated fuzzy clustering such as foreground segmentation in image processing. Initially, the background and foreground separation is done by hybridization of modified kernel fuzzy c means algorithm (MKFCM) with ant colony optimization. The recommended new technique is intellectual and also vibrant clustering method for splitting up of non-static object. Then object detection and tracking is done by gravitational search algorithm based deep belief neural network. The implementation will be in MATLAB. The performance of the suggested technique is appraised by means of precision, recall, F-measure, FPR, FNR, PWC, FAR, similarity, specificity, and accuracy. From the empirical effects, the future work outperforms than the state of art work. Here the proposed method attains maximum precision and recall value for both PETS and Hall monitor video when analyzed to the existent algorithm.

The road signs provide important information about road and traffic to drivers for safety driving. These signs include not only common traffic signs but also the information about unexpected obstacles and road constructions. Accurate detection and identification of road signs is one of the research topics in vehicle vision area. In this paper we propose a stereo vision technique to automatically detect and track road signs in a video sequence which is acquired from a stereo vision camera mounted on a vehicle. First, color information is used to initially detect the candidates of road signs. Second, the Support Vector Machine (SVM) is used to select true signs from the candidates. Once a road sign is detected in a video frame, it is tacked from the next frame until disappeared. The 2-D position of the detected sign on the next frame is predicted by the motion of the vehicle. Here, the vehicle motion means the 3-D Euclidean motion acquired by using a stereo matching method. Finally, the predicted 2-D position of the sign is corrected by the template matching of a scaled sign template in the near regions of the predicted position. Experimental results show that the proposed method can detect and track road signs successfully. Error comparisons with two different detection and tracking methods are shown.Keywordsstereotraffic signdetectiontrackingmotion

Lung cancer, a prevalent and lethal tumor globally, has a five-year survival rate of only 10%-16% for late-stage patients. However, early diagnosis and treatment can increase this rate to 52%. Lung nodules, as crucial indicators of early lung cancer, are challenging to detect due to their small size and similar features to other lung tissues. Therefore, developing an automatic detection method to improve the efficiency and accuracy of lung nodule detection is vital. This paper proposes a new method based on the YOLOx model, called SwiF-YOLO, to enhance the precision and efficiency of lung nodule detection. We introduced the Swin transformer to replace the main network of yolox-m, adopted the Adaptively Spatial Feature Fusion (ASFF) as the feature fusion method, and replaced the Intersection over Union (IOU) regression loss function with Generalized Intersection over Union (GIoU). These improvements aim to enhance the accuracy and efficiency of lung nodule detection, assisting doctors in diagnosing more accurately and quickly.

Currently, the intelligent defect detection of massive grid transmission line inspection pictures using AI image recognition technology is an efficient and popular method. Usually, there are two technical routes for the construction of defect detection algorithm models: one is to use a lightweight network, which improves the efficiency, but it can generally only target a few types of defects and may reduce the detection accuracy; the other is to use a complex network model, which improves the accuracy, and can identify multiple types of defects at the same time, but it has a large computational volume and low efficiency. To maintain the model's high detection accuracy as well as its lightweight structure, this paper proposes a lightweight and efficient multi type defect detection method for transmission lines based on DCP-YOLOv8. The method employs deformable convolution (C2f_DCNv3) to enhance the defect feature extraction capability, and designs a re-parameterized cross phase feature fusion structure (RCSP) to optimize and fuse high-level semantic features with low level spatial features, thus improving the capability of the model to recognize defects at different scales while significantly reducing the model parameters; additionally, it combines the dynamic detection head and deformable convolutional v3's detection head (DCNv3-Dyhead) to enhance the feature expression capability and the utilization of contextual information to further improve the detection accuracy. Experimental results show that on a dataset containing 20 real transmission line defects, the method increases the average accuracy (mAP@0.5) to 72.2%, an increase of 4.3%, compared with the lightest baseline YOLOv8n model; the number of model parameters is only 2.8 M, a reduction of 9.15%, and the number of processed frames per second (FPS) reaches 103, which meets the real time detection demand. In the scenario of multi type defect detection, it effectively balances detection accuracy and performance with quantitative generalizability.

Detection efficiency, spatial and timing resolution of thermal and cold neutron counting MCP detectors

72 Background: Circulating tumor cells (CTCs) have clinical value in cancer diagnosis, prognosis, and treatment prediction. The On-Q-ity Microfluidic Chip (OnQchip) with a gradient design has the advantage of dual size and affinity capture resulting in increased efficiency. Accurately detecting and classifying these rare captured cells in patient blood however is difficult. We present an imaging platform for accurate and reproducible CTC detection, where identified cells and fragments are further classified into several subclasses that may have separate prognostic utilities. Methods: Whole blood from advanced stage cancer patients and non-diseased controls was processed within 36 hours of collection. Blood was run on OnQchips coated with anti-EpCAM antibody. Captured CTCs and cellular fragments were identified by on-chip immunofluorescence. Chips were imaged at 5X magnification on a rapid automated platform. Cytokeratin positive (CK+) events were identified and sorted via an advanced detection algorithm using a set of spatial and spectral features. Events were further validated and separated into subclasses by trained experts using 10X magnification. Results: Greater than 85% capture efficiency was repeatedly achieved in spiked blood with nearly 100% detection sensitivity and 3% false positive rate following automated sorting of CTC candidates. On a cohort of 27 prostate cancer patients and 33 normal subjects a median of 19 CK+events/7.5 ml blood were detected in cancer patients, compared to a median of only 6 in normals. ROC analysis yielded AUC values of 0.62 to 0.77 for separate subclasses of CTCs. An AUC of nearly 0.80 was achieved by combining two or more subclasses. Conclusions: Preliminary evaluation of this imaging platform shows efficient and reproducible CTC detection in spiked and patient samples. Enumeration using subclasses achieved high sensitivities and specificities in separating cancer patients from normals and therefore, makes this technology feasible for both research and clinical studies. Future clinical studies with large sample sizes will be performed to validate clinical significance of CTC subclasses.

Accurate Detection and Smoothness-Oriented Avoidance Method of Singularity in 5-Axis CNC Machining