Multistage Detection Research Articles

A Multi-Stage Detection Framework Based on TFA and Multiframe Correlation for HFSWR

A Multi-Stage Detection Framework Based on TFA and Multiframe Correlation for HFSWR

A Customized CNN Architecture with CLAHE for Multi-Stage Diabetic Retinopathy Classification

This paper presents a customized Convolutional Neural Network (CNN) architecture for multi-stage detection of Diabetic Retinopathy (DR), a leading cause of vision impairment and blindness. The proposed model incorporates advanced image enhancement techniques, particularly Contrast Limited Adaptive Histogram Equalization (CLAHE), to improve the visibility of critical retinal features associated with DR. By integrating CLAHE with a finely tuned CNN, the proposed approach significantly enhances accuracy and robustness, allowing for more precise detection across various stages of DR. The proposed model was evaluated against several state-of-the-art techniques, with the customized CNN alone achieving an overall accuracy of 97.69%. The addition of CLAHE further boosts the performance, achieving an accuracy of 99.69%, underscoring the effectiveness of combining CLAHE with CNN for automated DR detection. This approach provides an efficient, scalable, and highly accurate solution for early and multistage DR detection, which is crucial for timely intervention and prevention of vision loss.

Benchmarking the Robustness of Instance Segmentation Models.

This article presents a comprehensive evaluation of instance segmentation models with respect to real-world image corruptions as well as out-of-domain image collections, e.g., images captured by a different set-up than the training dataset. The out-of-domain image evaluation shows the generalization capability of models, an essential aspect of real-world applications, and an extensively studied topic of domain adaptation. These presented robustness and generalization evaluations are important when designing instance segmentation models for real-world applications and picking an off-the-shelf pretrained model to directly use for the task at hand. Specifically, this benchmark study includes state-of-the-art network architectures, network backbones, normalization layers, models trained starting from scratch versus pretrained networks, and the effect of multitask training on robustness and generalization. Through this study, we gain several insights. For example, we find that group normalization (GN) enhances the robustness of networks across corruptions where the image contents stay the same but corruptions are added on top. On the other hand, batch normalization (BN) improves the generalization of the models across different datasets where statistics of image features change. We also find that single-stage detectors do not generalize well to larger image resolutions than their training size. On the other hand, multistage detectors can easily be used on images of different sizes. We hope that our comprehensive study will motivate the development of more robust and reliable instance segmentation models.

Federated Deep Learning Model for False Data Injection Attack Detection in Cyber Physical Power Systems

Cyber-physical power systems (CPPS) integrate information and communication technology into conventional electric power systems to facilitate bidirectional communication of information and electric power between users and power grids. Despite its benefits, the open communication environment of CPPS is vulnerable to various security attacks. This paper proposes a federated deep learning-based architecture to detect false data injection attacks (FDIAs) in CPPS. The proposed work offers a strong, decentralized alternative with the ability to boost detection accuracy while maintaining data privacy, presenting a significant opportunity for real-world applications in the smart grid. This framework combines state-of-the-art machine learning and deep learning models, which are used in both centralized and federated learning configurations, to boost the detection of false data injection attacks in cyber-physical power systems. In particular, the research uses a multi-stage detection framework that combines several models, including classic machine learning classifiers like Random Forest and ExtraTrees Classifiers, and deep learning architectures such as Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU). The results demonstrate that Bidirectional GRU and LSTM models with attention layers in a federated learning setup achieve superior performance, with accuracy approaching 99.8%. This approach enhances both detection accuracy and data privacy, offering a robust solution for FDIA detection in real-world smart grid applications.

Advanced Security Framework for 6G Networks: Integrating Deep Learning and Physical Layer Security

This paper presents an advanced framework for securing 6G communication by integrating deep learning and physical layer security (PLS). The proposed model incorporates multi-stage detection mechanisms to enhance security against various attacks on the 6G air interface. Deep neural networks and a hybrid model are employed for sequential learning to improve classification accuracy and handle complex data patterns. Additionally, spoofing, jamming, and eavesdropping attacks are simulated to refine detection mechanisms. An anomaly detection system is developed to identify unusual signal patterns indicating potential attacks. The results demonstrate that machine learning (ML) and hybrid models outperform conventional approaches, showing improvements of up to 85% in bit error rate (BER) and 24% in accuracy, especially under attack conditions. This research contributes to the advancement of secure 6G communication systems, offering details on effective defence mechanisms against physical layer attacks.

Attentive context and semantic enhancement mechanism for printed circuit board defect detection with two-stage and multi-stage object detectors

Printed Circuit Boards (PCBs) are key devices for the modern-day electronic technologies. During the production of these boards, defects may occur. Several methods have been proposed to detect PCB defects. However, detecting significantly smaller and visually unrecognizable defects has been a long-standing challenge. The existing two-stage and multi-stage object detectors that use only one layer of the backbone, such as Resnet’s third layer (C4\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$C_4$$\\end{document}) or fourth layer (C5\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$C_5$$\\end{document}), suffer from low accuracy, and those that use multi-layer feature maps extractors, such as Feature Pyramid Network (FPN), incur higher computational cost. Founded by these challenges, we propose a robust, less computationally intensive, and plug-and-play Attentive Context and Semantic Enhancement Module (ACASEM) for two-stage and multi-stage detectors to enhance PCB defects detection. This module consists of two main parts, namely adaptable feature fusion and attention sub-modules. The proposed model, ACASEM, takes in feature maps from different layers of the backbone and fuses them in a way that enriches the resulting feature maps with more context and semantic information. We test our module with state-of-the-art two-stage object detectors, Faster R-CNN and Double-Head R-CNN, and with multi-stage Cascade R-CNN detector on DeepPCB and Augmented PCB Defect datasets. Empirical results demonstrate improvement in the accuracy of defect detection.

Lightweight Network of Multi-Stage Strawberry Detection Based on Improved YOLOv7-Tiny

The color features of strawberries at different growth stages vary slightly and occluded during growth. To address these challenges, this study proposes a lightweight multi-stage detection method based on You Only Look Once version 7-tiny (YOLOv7-tiny) for strawberries in complex environments. First, the size of the model is reduced by replacing the ordinary convolution of the neck network used for deep feature extraction and fusion with lightweight Ghost convolution. Then, by introducing the Coordinate Attention (CA) module, the model’s focus on the target detection area is enhanced, thereby improving the detection accuracy of strawberries. The Wise Intersection over Union (WIoU) loss function is integrated to accelerate model convergence and enhance the recognition accuracy of occluded targets. The advanced Adaptive nesterov momentum algorithm (Adan) is utilized for gradient descent, processing averaged sample data. Additionally, considering the small size of strawberry targets, a detection head specifically for small targets is added, performing detection on a 160 × 160 × 64 feature map, which significantly improves the detection performance for small strawberries. Experimental results demonstrate that the improved network model achieves an mAP@0.5 of 88.2% for multi-stage strawberry detection, which is 2.44% higher than the original YOLOv7-tiny algorithm. Meanwhile, GFLOPs and Params are reduced by 1.54% and 12.10%, respectively. In practical detection and inference, the improved model outperforms current mainstream target detection models, enabling a quicker and more accurate identification of strawberries at different growth stages, thus providing technical support for intelligent strawberry picking.

Synchronizing real-time and high-precision LDoS defense of learning model-based in AIoT with programmable data plane, SDN

Synchronizing real-time and high-precision LDoS defense of learning model-based in AIoT with programmable data plane, SDN

Multi-stage progressive detection method for water deficit detection in vertical greenery plants

Detecting the water deficit status of vertical greenery plants rapidly and accurately is a significant challenge in the process of cultivating and planting greenery plants. Currently, the mainstream method involves utilizing a single target detection algorithm for this task. However, in complex real-world scenarios, the accuracy of detection is influenced by factors such as image quality and background environment. Therefore, we propose a multi-stage progressive detection method aimed at enhancing detection accuracy by gradually filtering, processing, and detecting images through a multi-stage architecture. Additionally, to reduce the additional computational load brought by multiple stages and improve overall detection efficiency, we introduce a Swin Transformer based on mobile windows and hierarchical representations for feature extraction, along with global feature modeling through a self-attention mechanism. The experimental results demonstrate that our multi-stage detection approach achieves high accuracy in vertical greenery plants detection tasks, with an average precision of 93.5%. This represents an improvement of 19.2%, 17.3%, 13.8%, and 9.2% compared to Mask R-CNN (74.3%), YOLOv7 (76.2%), DETR (79.7%), and Deformable DETR (84.3%), respectively.

Vision-based multi-label detection framework for capturing occupant action and clothing information using large-scale dataset

Vision-based multi-label detection framework for capturing occupant action and clothing information using large-scale dataset

Detector Consistency Research on Remote Sensing Object Detection

Remote Sensing Image processing is a traditional research field, where RSI object detection is one of the most important directions. This paper focuses on an inherent problem of multi-stage object detection frameworks: the coupling error transmitting problem. In brief, because of the coupling method between the classifier and the regressor, the traditional multi-stage Detection frameworks tend to be fallible when encountering coarse object proposals. To deal with this problem, this article proposes a novel deep learning-based multi-stage object detection framework. Specifically, a novel network head architecture with a multi-to-one coupling method is proposed to avoid the coupling error of the traditional network head architecture. Moreover, it is found that the traditional network head architecture is more efficient than the novel network architecture when encountering fine object proposals. Considering this phenomenon, a proposal-consistent cooperation mechanism between the network heads is proposed. This mechanism makes the traditional network head and the novel network head develop each other’s advantages and avoid the disadvantages. Experiments with different backbone networks on three publicly available data sets have shown the effectiveness of the proposed method since mAP is proposed as 0.7% to 12.3% on most models and data sets.

A Rotation-Invariance Face Detector Based on RetinaNet

The use of deep convolutional neural networks has greatly improved the performance of general face detection. For detecting rotated faces, the mainstream approach is to use multi-stage detectors to gradually adjust the rotated face to a vertical orientation for detection, which increases the complexity of training as multiple networks are involved. In this study, we propose a new method for rotation-invariant face detection, which abandons the previously used cascaded architecture with multiple stages and instead uses a single-stage detector to achieve end-to-end detection of face classification, face box regression, and facial landmark regression. Extensive experiments on FDDB in multiple orientations have shown the effectiveness of our method. The results demonstrate that our method achieves good detection performance and the detection accuracy of our method even exceeds that of other rotated face detectors on the front-facing FDDB dataset.

Multistage Detection of Tetrodotoxin Traces in Diodon hystrix Collected in El Salvador.

This study describes a multistage methodology to detect minute amounts of tetrodotoxin in fishes, a plan that may be broadened to include other marine organisms. This methodology was applied to porcupinefish (Diodon hystrix) collected in Punta Chiquirín, El Salvador. A three-stage approach along with post-acquisition processing was employed, to wit: (a) Sample screening by selected reaction monitoring (HPLC-MS/MS-SRM) analyses to quickly identify possible toxin presence via a LC/MS/MS API 3200 system with a triple quadrupole; (b) HPLC-HRFTMS-full scan analyses using an ion trap-Orbitrap spectrometer combined with an MZmine 2-enhanced dereplication-like workflow to collect high-resolution mass spectra; and (c) HPLC-HRMS2 analyses. This is the first time tetrodotoxin has been reported in D. hystrix specimens collected in El Salvador.

AMA-Det: Enhancing Shared Head of One-Stage Object Detection With Adaptation, Merging, and Alignment

Feature adaptation(FA) and result alignment(RA) are critical issues in one-stage object detection, since FA amends feature misalignment problem by adapting sampling points to semantically significant locations, and RA corrects result misalignment problem by estimating the localization quality. For FA, the aligned and consistent prediction of sampling points is important. Previous studies directly inherit cascaded “proposal-refine” philosophy from multi-stage detectors and predict sampling points by approximating their minimal external rectangle to ground-truth bounding boxes. This manner generates poorly aligned and consistent sampling points and induces irrelevant features aggregated. Moreover, their sampling points for classification are conventionally generated through the localization branch, without feeding the corresponding features of the classification branch. For RA, previous studies have verified the superiority of utilizing the predicted edge distribution to estimate localization quality; however, their directly regressed distribution is incompatible with the cascaded regression framework. To solve these problems, we firstly propose a focused feature adaptation method by softening the supervision of the proposal points. This method can predict sampling points focused above the assigned objects with excellent alignment and consistency. Subsequently, inner-branch and cross-branch merging were investigated to promote feature sharing from the classification branch. Finally, cascaded distribution-guided result alignment is advanced and verified to predict accurate localization quality. After integrating our proposed adaptation, merging, and alignment, we created AMA-Det with an enhanced shared head, which impressively reaches 43.9 mAP with ResNet50 as the backbone. AMA-Det also achieves a 54.5 mAP by multi-scale testing on MSCOCO test-dev and outperforms all existing CNN-based one-stage counterparts.

Deep Learning-based SNR Estimation for Multistage Spectrum Sensing in Cognitive Radio Networks

Vacant frequency bands are used in cognitive radio (CR) by incorporating the spectrum sensing (SS) technique. Spectrum sharing plays a central role in ensuring the effectiveness of CR applications. Therefore, a new multi-stage detector for robust signal and spectrum sensing applications is introduced here. Initially, the sampled signal is subjected to SNR estimation by using a convolutional neural network (CNN). Next, the detection strategy is selected in accordance with the predicted SNR levels of the received signal. Energy detector (ED) and singular value-based detector (SVD) are the solutions utilized in the event of high SNR, whilst refined non-negative matrix factorization (MNMF) is employed in the case of low SNR. CNN weights are chosen via the Levy updated sea lion optimization (LU-SLNO) algorithm inspired by the traditional sea lion optimization (SLNO) approach. Finally, the outcomes of the selected detectors are added, offering a precise decision on spectrum tenancy and existence of the signal.

Equivalent Circuit Model of the RF Characteristics of Multi-Stage Infrared Photodetectors

Multi-stage infrared photodetectors such as quantum cascade detectors (QCDs) and interband cascade infrared photodetectors (ICIP) have been demonstrated with high detectivity and high-frequency operation. In the previous work published by Rui. Q. Yang [Applied Physics Letters 2021, 119 (14), 141107], an equivalent circuit model is used to derive the relation among quantum efficiency, collection efficiency, and particle conversion efficiency. The ultimate detectivities in multi-stage infrared photodetectors were discussed based on that model. However, the RF performance of multi-stage infrared photodetectors was rarely studied theoretically so far. In this work, a generalized equivalent circuit model is proposed with the AC term included. The detailed calculations and relevant discussion are provided to show how the normalized frequency response function of each stage impacts the overall 3 dB performance of the device. In the limit of weak absorption, such as QCDs or ICIP with very weak and identical absorption in each stage, the multi-stage infrared photodetectors show significant improvement in RF performance. Moreover, how the current mismatching issue between stages impacts 3 dB bandwidth performance quantitatively is derived and discussed for identical absorption stages architecture. The result and insights gained from this work can be beneficial for the understanding and optimization of high-speed multi-stage detectors.

A more compact object detector head network with feature enhancement and relational reasoning

• We exposed the flaws of the two-stage object detection method. • A novel two stage object detection paradigm is presented. • An ablation study illustrates the effect of different elements of the framework. • State-of-the-art methods are outperformed in both accuracy and parameters. Modeling feature interaction patterns is of significant importance to object detection tasks. However, reasoning about the relationship between instance features is challenging in two-stage detectors due to the overuse of hand-crafted components. To tackle this problem, we analyze three different levels of feature interaction relationships, namely, the dependency relationship between the cropped local features and global features, the feature autocorrelation within the instance, and the cross-correlation relationship between the instances. To this end, we propose a more c ompact o bject d etector h ead network ( CODH ), which can not only preserve global context information and condense the information density, but also allows instance-wise feature enhancement and relational reasoning in a larger matrix space. Without bells and whistles, our method can effectively improve the detection performance while significantly reducing the parameters of the model, e.g. , with our method, the parameters of the head network is 0.6 × smaller than the state-of-the-art Cascade R-CNN. Yet, the performance boost is 1.3% on COCO test-dev. Without losing generality, we can also build a lighter head network for other multi-stage detectors by assembling our method, including Faster R-CNN, Libra R-CNN, and Double Head R-CNN.

High Quality Object Detection for Multiresolution Remote Sensing Imagery Using Cascaded Multi-Stage Detectors

Deep-learning-based object detectors have substantially improved state-of-the-art object detection in remote sensing images in terms of precision and degree of automation. Nevertheless, the large variation of the object scales makes it difficult to achieve high-quality detection across multiresolution remote sensing images, where the quality is defined by the Intersection over Union (IoU) threshold used in training. In addition, the imbalance between the positive and negative samples across multiresolution images worsens the detection precision. Recently, it was found that a Cascade region-based convolutional neural network (R-CNN) can potentially achieve a higher quality of detection by introducing a cascaded three-stage structure using progressively improved IoU thresholds. However, the performance of Cascade R-CNN degraded when the fourth stage was added. We investigated the cause and found that the mismatch between the ROI features and the classifier could be responsible for the degradation of performance. Herein, we propose a Cascade R-CNN++ structure to address this issue and extend the three-stage architecture to multiple stages for general use. Specifically, for cascaded classification, we propose a new ensemble strategy for the classifier and region of interest (RoI) features to improve classification accuracy at inference. In localization, we modified the loss function of the bounding box regressor to obtain higher sensitivity around zero. Experiments on the DOTA dataset demonstrated that Cascade R-CNN++ outperforms Cascade R-CNN in terms of precision and detection quality. We conducted further analysis on multiresolution remote sensing images to verify model transferability across different object scales.

A Feature Pyramid Based Multi-stage Framework for Object Detection in Low-altitude UAV Images

This paper proposes a high-performance framework for accurate multi-stage object detection in low-altitude based UAV images. The proposed system employs a cascade style architecture with increasing thresholds for achieving accurate detection. The framework makes use of highly efficient Feature Pyramid Networks (FPNs) to detect objects of small sizes, and various scales which are the main challenge in low-altitude aerial images. FPNs aim to resolve scale variation problems in object detection by combining features of multiple levels. The experiments have been performed on a complex low-altitude aerial dataset VisDrone which has multiple categories of classes. The FPN-Cascade detector has been supported by slicing the data horizontally and vertically that resulted in an advancement of 8% mAP when compared with the base detector. The experiments compare the FPN-Cascade performance on the standard as well as augmented VisDrone dataset. A concrete methodology about the training process, hyperparameter tuning, and performance evaluation methods for Cascade RCNN on the VisDrone dataset is highlighted. The proposed framework achieves state of the art 30.04% mAP value on the VisDrone dataset.

AT-BOD: An Adversarial Attack on Fool DNN-Based Blackbox Object Detection Models

Object recognition is a fundamental concept in computer vision. Object detection models have recently played a vital role in various applications, including real-time and safety-critical systems such as camera surveillance and self-driving cars. Scientific research has proven that object detection models are prone to adversarial attacks. Although several proposed methods exist throughout the literature, they either target white-box models or specific-task black-box models and do not generalize on other detectors. In this paper, we proposed a new adversarial attack against Blackbox-based object detectors called AT-BOD. The proposed AT-BOD model can fool the single-stage and multi-stage detectors, where we used an optimization algorithm to generate adversarial examples depending only on the detector predictions. AT-BOD model works in two diverse ways, reducing the confidence score and misleading the model to make the wrong decision or hide the object detection models. Our solution achieved a fooling rate of 97% and a false negative increase of 99% on the YOLOv3 detector, and a fooling rate of 61% false-negative increase of 57% on the Faster R-CNN detector. The detection accuracy of YOLOv3 and Faster R-CNN under AT-BOD was dramatically reduced and reached ≤1% and ≤3%, respectively.