Multi-target Recognition Research Articles

Underwater acoustic multi-target recognition based on channel attention mechanism

The recognition of ship-radiated noise presents a critical challenge in underwater acoustic target recognition, primarily due to interference from multiple vessels in real-world settings. This interference produces complex signals that contain multiple and overlapping targets. Despite the practical relevance of multi-target recognition, most existing research in underwater acoustic target recognition has concentrated on single-target recognition. To address the multi-target recognition problem, this paper proposes a deep learning (DL) framework that combines residual neural network (ResNet) architecture with channel attention modules. These modules excel in selectively filtering channel information within feature maps, amplifying informative features while mitigating noise interference. Thus, it enables accurate recognize both the quantity and types of targets within single-channel acoustic signals. In addition, this paper explores the effects of signal duration and energy ratios between different targets in mixed signals on recognition performance. Experimental results reveal that shorter signal durations hinder the extraction of discriminative features, reducing recognition accuracy. Notably, for signal durations of 5 s, the proposed model achieves a recognition accuracy of 97.16% on the dataset with energy ratios between −5 dB and 5 dB, closely approaching the accuracy of 98.09% obtained at a dataset with energy ratio of 0 dB.

DCS-YOLOv5s: A Lightweight Algorithm for Multi-Target Recognition of Potato Seed Potatoes Based on YOLOv5s

The quality inspection of potato seed tubers is pivotal for their effective segregation and a critical step in the cultivation process of potatoes. Given the dearth of research on intelligent tuber-cutting machinery in China, particularly concerning the identification of bud eyes and defect detection, this study has developed a multi-target recognition approach for potato seed tubers utilizing deep learning techniques. By refining the YOLOv5s algorithm, a novel, lightweight model termed DCS-YOLOv5s has been introduced for the simultaneous identification of tuber buds and defects. This study initiates with data augmentation of the seed tuber images obtained via the image acquisition system, employing strategies such as translation, noise injection, luminance modulation, cropping, mirroring, and the Cutout technique to amplify the dataset and fortify the model’s resilience. Subsequently, the original YOLOv5s model undergoes a series of enhancements, including the substitution of the conventional convolutional modules in the backbone network with the depth-wise separable convolution DP_Conv module to curtail the model’s parameter count and computational load; the replacement of the original C3 module’s Bottleneck with the GhostBottleneck to render the model more compact; and the integration of the SimAM attention mechanism module to augment the model’s proficiency in capturing features of potato tuber buds and defects, culminating in the DCS-YOLOv5s lightweight model. The research findings indicate that the DCS-YOLOv5s model outperforms the YOLOv5s model in detection precision and velocity, exhibiting superior detection efficacy and model compactness. The model’s detection metrics, including Precision, Recall, and mean Average Precision at Intersection over Union thresholds of 0.5 (mAP1) and 0.75 (mAP2), have improved to 95.8%, 93.2%, 97.1%, and 66.2%, respectively, signifying increments of 4.2%, 5.7%, 5.4%, and 9.8%. The detection velocity has also been augmented by 12.07%, achieving a rate of 65 FPS. The DCS-YOLOv5s target detection model, by attaining model compactness, has substantially heightened the detection precision, presenting a beneficial reference for dynamic sample target detection in the context of potato-cutting machinery.

Multi-target recognition and DNAzyme signal amplification integrated functional nucleic acid framework for lncRNA in situ live cell imaging

Accumulating evidence suggests that long non-coding RNAs (lncRNAs) intricately regulate tumor initiation and progression. LncRNAs hold great promise as novel biomarkers and therapeutic targets for neoplastic diseases. Consequently, quantifying the expression levels of lncRNAs can serve as a robust foundation for tumor diagnosis and treatment. In this research, we have developed a multifunctional nucleic acid framework that integrates cell-specific targeting, target recognition, and multiple signal amplification for in situ imaging of lncRNAs in tumor cells. The nucleic acid framework comprises aptamers that specifically target nucleolin in tumor cells and three blocked DNAzymes that selectively recognize lncRNAs. The nucleic acid framework exhibits excellent programmability, stability, targeting ability, and biocompatibility, thereby enabling enhanced tumor cell targeting and internalization of the multifunctional nucleic acid framework. By utilizing the elongated chain properties of lncRNA, a small number of lncRNAs can activate multiple DNAzymes for achieving signal amplification in the presence of targets. The proposed method exhibits a high sensitivity for detecting extracellular lncRNA HULC and enables the visualization of lncRNA HULC in tumor cells. It facilitates in situ imaging of lncRNA HULC, thereby aiding in the identification of alterations in its expression levels within tumor cells. This assay presents a novel approach to investigate the expression profiles of lncRNAs across diverse tumor cell types and unravel potential mechanisms underlying tumorigenesis and progression.

Terahertz spoof plasmonic neural network for diffractive information recognition and processing

All-optical diffractive neural networks, as analog artificial intelligence accelerators, leverage parallelism and analog computation for complex data processing. However, their low space transmission efficiency or large spatial dimensions hinder miniaturization and broader application. Here, we propose a terahertz spoof plasmonic neural network on a planar diffractive platform for direct multi-target recognition. Our approach employs a spoof surface plasmon polariton coupler array to construct a diffractive network layer, resulting in a compact, efficient, and easily integrable architecture. We designed three schemes: basis vector classification, multi-user recognition, and MNIST handwritten digit classification. Experimental results reveal that the terahertz spoof plasmonic neural network successfully classifies basis vectors, recognizes multi-user orientation information, and directly processes handwritten digits using a designed input framework comprising a metal grating array, transmitters, and receivers. This work broadens the application of terahertz plasmonic metamaterials, paving the way for terahertz on-chip integration, intelligent communication, and advanced computing systems.

Multi-Target Recognition of Substation Infrared Image Based on Improved Faster RCNN

Abstract This study presents a multi-target recognition approach for substation infrared images based on enhanced Faster RCNN, which addresses the challenge of identifying several high-voltage electrical equipment in substation infrared images simultaneously. This method uses VGG16 to extract image features of a variety of electrical equipment in infrared images. Generate regional suggestions through the regional suggestion network and adjust the regional suggestions through border regression. ROI Pooling maps regional suggestions of different scales to fixed-size output vectors and sends them to Softmax for classification, and corrects the incorrectly identified parts categories according to the inclusion relationship of the regional suggestions. In the experiment, 27586 infrared photos are chosen to create an infrared data set in the voc207 format. Then, statistical analysis is performed on the recognition outcomes of 5517 infrared images in the test set. Based on the testing data, the upgraded rapid RCNN has a 92.8% recognition accuracy, which is 9.7% higher than that before, and has higher engineering practical value.

Design and Simulation of Multi Unmanned Boat Cooperative Obstacle Avoidance System Based on 5G Edge Computing

Background:: Compared to single unmanned boat, multi unmanned boats have more flexible mobility and efficient task completion capabilities, which can effectively expand the types of tasks. However, the traditional independent path planning and obstacle avoidance methods of unmanned boats are difficult to meet the requirements of collaborative operation among multiple unmanned boats due to the lack of information exchange. Objective:: According to the actual demand of multi unmanned boats' cooperative operation, a method of multi unmanned boats cooperative obstacle avoidance based on 5G edge computing is proposed to realize the unified planning and scheduling of multi unmanned boats. Methods:: Firstly, 5G technology and Kubeedge edge computing tools are used to build a multi unmanned boat collaborative obstacle avoidance system based on cloud, edge and end collaboration, and the Kubeedge edge computing platform was optimized by optimizing communication strategies, building a highly available Kubeedge cluster, building a Harbor image center, and using Web management interfaces further to improve the reliability and stability of the system. Secondly, the YOLOR-Deepport multi-target recognition and tracking algorithm based on cloud, edge and end collaborative network is used to complete the recognition and tracking tasks of obstacle targets, and a set of EECBS path planning methods based on the Kubedge centralized control platform is designed to plan collision-free and efficient paths for each unmanned boat in realtime. Finally, the effectiveness of the system was verified through simulation experiments. Results:: The experimental results show that compared to the traditional autonomous planning obstacle avoidance method for unmanned boats, the collaborative planning obstacle avoidance method proposed in this paper can exhibit excellent performance in dense and narrow scenarios, with a more reasonable navigation path, a range reduction of 20% - 50%, and higher safety. Conclusion:: The results show that the cooperative obstacle avoidance system based on 5G edge computing designed in the paper is feasible, and it can effectively realize the cooperative path planning and obstacle avoidance of multi unmanned boats.

A Comprehensive Survey on Wi-Fi Sensing for Human Identity Recognition

In recent years, Wi-Fi sensing technology has become an emerging research direction of human–computer interaction due to its advantages of low cost, contactless, illumination insensitivity, and privacy preservation. At present, Wi-Fi sensing research has been expanded from target location to action recognition and identity recognition, among others. This paper summarizes and analyzes the research of Wi-Fi sensing technology in human identity recognition. Firstly, we overview the history of Wi-Fi sensing technology, compare it with traditional identity-recognition technologies and other wireless sensing technologies, and highlight its advantages for identity recognition. Secondly, we introduce the steps of the Wi-Fi sensing process in detail, including data acquisition, data pre-processing, feature extraction, and identity classification. After that, we review state-of-the-art approaches using Wi-Fi sensing for single- and multi-target identity recognition. In particular, three kinds of approaches (pattern-based, model-based, and deep learning-based) for single-target identity recognition and two kinds of approaches (direct recognition and separated recognition) for multi-target identity recognition are introduced and analyzed. Finally, future research directions are discussed, which include transfer learning, improved multi-target recognition, and unified dataset construction.

Recent Reviews on Dynamic Target Detection Based on Vision

Background: Vision-based dynamic target detection is an important research topic in computer vision, which is the basis for intelligent behavior analysis and event detection. Further research on dynamic target detection methods can help improve target detection and tracking mechanisms while also driving the development of other related fields. Hence, conducting a review on vision-based dynamic target detection is very significant. Objective: There are many methods for dynamic target detection. This paper introduces their classification, characteristics, advantages, disadvantages and development trends. Method: This paper reviews recent patents and representative articles on dynamic target detection in simple visual and complex contexts. The crucial methods of these references are introduced from the aspects of algorithm, innovation, and principle. Results: This paper analyzes and compares the existing dynamic target detection methods, summarizes their characteristics, main applications, and advantages and disadvantages in the current development stage, and discusses the future development and potential problems of dynamic target tracking methods. Conclusion: Vision-based dynamic target detection can accurately extract moving targets from the scene. Due to its inherent complexity, each detection method has its advantages and disadvantages in specific scenes. Currently, the research mainly focuses on the real-time robustness and accuracy of the algorithm, which needs to be further improved in the aspects of algorithm innovation, multialgorithm fusion, multi-target recognition, and algorithm adaptability. Therefore, relevant research patents and documents should be put forward, initiating the future development trend.

An Effective Method for Underwater Biological Multi-Target Detection Using Mask Region-Based Convolutional Neural Network

Underwater creatures play a vital role in maintaining the delicate balance of the ocean ecosystem. In recent years, machine learning methods have been developed to identify underwater biologicals in the complex underwater environment. However, the scarcity and poor quality of underwater biological images present significant challenges to the recognition of underwater biological targets, especially multi-target recognition. To solve these problems, this paper proposed an ensemble method for underwater biological multi-target recognition. First, the CutMix method was improved for underwater biological image augmentation. Second, the white balance, multiscale retinal, and dark channel prior algorithms were combined to enhance the underwater biological image quality, which could largely improve the performance of underwater biological target recognition. Finally, an improved model was proposed for underwater biological multi-target recognition by using a mask region-based convolutional neural network (Mask-RCNN), which was optimized by the soft non-maximum suppression and attention-guided context feature pyramid network algorithms. We achieved 4.97 FPS, the mAP was 0.828, and the proposed methods could adapt well to underwater biological multi-target recognition. The recognition effectiveness of the proposed method was verified on the URPC2018 dataset by comparing it with current state-of-the-art recognition methods including you-only-look-once version 5 (YOLOv5) and the original Mask-RCNN model, where the mAP of the YOLOv5 model was lower. Compared with the original Mask-RCNN model, the mAP of the improved model increased by 3.2% to 82.8% when the FPS was reduced by only 0.38.

Direction of Arrival Estimation and Highlighting Characteristics of Testing Wideband Echoes from Multiple Autonomous Underwater Vehicles.

Multiple autonomous underwater vehicles (AUVs) have gradually become the trend in underwater operations. Identifying and detecting these new underwater multi-targets is difficult when studying underwater moving targets. A 28-element transducer is used to test the echo of multiple AUVs with different layouts in a lake. The characteristics of the wideband echo signals are studied. Under the condition that the direction of arrival (DOA) is not known, an autofocus coherent signal subspace (ACCSM) method is proposed. The focusing matrix is constructed based on the received data. The spatial spectrum of the array signal of multiple AUVs at different attitudes is calculated. The algorithm estimates the DOA of the echo signals to overcome the shortcomings of traditional wideband DOA estimation and improve its accuracy. The results show that the highlights are not only related to the number of AUVs, but are also modified by scale and attitude. The contribution of the microstructure of the target in the overall echo cannot be ignored. Different parts of the target affect the number of highlights, thus resulting in varying numbers of highlights at different attitude angle intervals. The results have significant implications for underwater multi-target recognition.

Microwave Absolute Distance Measurement Method with Ten-Micron-Level Accuracy and Meter-Level Range Based on Frequency Domain Interferometry.

A microwave absolute distance measurement method with ten-micron-level accuracy and meter-level range based on frequency domain interferometry is proposed and experimentally demonstrated for the first time. Theoretical analysis indicates that an interference phenomenon occurs instantaneously in the frequency domain when combining two homologous broad-spectrum microwave beams with different paths, and the absolute value of the distance difference between the two paths is only inversely proportional to the period of frequency domain interference fringes. The proof-of-principle experiments were performed to prove that the proposed method can achieve absolute distance measurement in the X-band with standard deviations of 15 μm, 17 μm, and 26 μm and within ranges of 1.69 m, 2.69 m, and 3.75 m. Additionally, a displacement resolution of 100 microns was realized. The multi-target recognition performance was also verified in principle. Furthermore, at the expense of a slight decrease in ranging accuracy, a fast distance measurement with the single measurement time of 20 μs was achieved by using a digitizer combined with a Fourier transform analyzer. Compared with the current microwave precision ranging technologies, the proposed method not only has the advantages of high precision, large range, and rapid measurement capability, but the required components are also easily obtainable commercial devices. The proposed method also has better complex engineering applicability, because the ten-micron-level ranging accuracy is achievable only by using a simple Fourier transform without any phase estimation algorithm, which greatly reduces the requirement for signal-to-noise ratio.

Improved Lightweight Multi-Target Recognition Model for Live Streaming Scenes

Nowadays, the commercial potential of live e-commerce is being continuously explored, and machine vision algorithms are gradually attracting the attention of marketers and researchers. During live streaming, the visuals can be effectively captured by algorithms, thereby providing additional data support. This paper aims to consider the diversity of live streaming devices and proposes an extremely lightweight and high-precision model to meet different requirements in live streaming scenarios. Building upon yolov5s, we incorporate the MobileNetV3 module and the CA attention mechanism to optimize the model. Furthermore, we construct a multi-object dataset specific to live streaming scenarios, including anchor facial expressions and commodities. A series of experiments have demonstrated that our model realized a 0.4% improvement in accuracy compared to the original model, while reducing its weight to 10.52%.

Based on YOLO v3 Target Recognition Algorithm as Vehicle Tracking Algorithm Analysis

Traditional traffic information acquisition and acquisition are mainly implemented by sensors, and these traditional acquisition and acquisition systems have some great drawbacks. However, with the popularity of traffic monitoring, computer vision technology gradually has a platform foundation that can be applied to identify and track traffic conditions. In this paper, through the research of traditional and Deep learning-based multi-target recognition algorithms and two common multi-target tracking algorithms, a solution of YOLO v3 network combined with deep-sort algorithm is proposed. In this paper, a video of traffic information of urban roads is directly collected for areas with relatively large traffic flow. Interval frames are extracted from the video data set to make relevant data sets for training and verification of YOLO v3 neural networks. Combined with the test results, an open source vehicle depth model dataset is used to train the vehicle depth feature weight file, and Deep-SORT algorithm is used to achieve the target tracking, which can realize the real-time and more accurate multi-target recognition and tracking of moving vehicles.

Multi-Target Recognition Utilizing Micro-Doppler Signatures with Limited Supervision

Multi-Target Recognition Utilizing Micro-Doppler Signatures with Limited Supervision

A Miniature Meta-Optical System for Reconfigurable Wide-Angle Imaging and Polarization-Spectral Detection

Wide-angle imaging and spectral detection play vital roles in tasks such as target tracking, object classification, and anti-camouflage. However, limited by their intrinsically different architectures, as determined by frequency dispersion requirements, their simultaneous implementation in a shared-aperture system is difficult. Here, we propose a novel concept to realize reconfigurable dual-mode detection based on electrical-control tunable metasurfaces. As a proof-of-concept demonstration, the simultaneous implementation of wide-angle imaging and polarization-spectral detection in a miniature shared-aperture meta-optical system is realized for the first time via the electrical control of cascaded catenary-like metasurfaces. The proposed system supports the imaging (spectral) resolution of approximately 27.8 line-pairs per millimeter (lp·mm−1; ∼80 nm) for an imaging (spectral) mode from 8 to 14 μm. This system also bears a large field of view of about 70°, enabling multi-target recognition in both modes. This work may promote the miniaturization of multifunctional optical systems, including spectrometers and polarization imagers, and illustrates the potential industrial applications of meta-optics in biomedicine, security, space exploration, and more.

Combinatorial detection of ship and its wake via skeleton theory based on joint feature knowledge association

Ship detection has a wide range of applications in maritime surveillance, including civilian and military fields. Compared with the hull, ship wakes are more obvious and easier to capture. So, it is widely used in ship inspection. Previous work regarded wakes as clutter with a specific spatial distribution. In this paper, the ship wake is modeled as an extended target with irregular but certain characteristics. In the presence of wakes, the task of realizing ship recognition becomes a special multi-target recognition task, in which the ship is a point target and the wake is its extended target. A skeleton theory based multiple model joint feature knowledge association (ST-MM-JFKA) method is proposed to estimate the ship state and wake state at the same time. The Dot model and the Curve model are established, one can be applied to most point targets, and the other can be modeled for ship detection. Combining two models, this method can effectively improve the detection effect. In addition, the proposed method can also use the estimated wake angle to infer the ship length, which is conducive to ship classification. The simulation results show the effectiveness of the proposed method.

HIDR: A Hierarchical Independent Detection and Recognition strategy for underwater acoustic multi-target recognition

This paper proposed HIDR (Hierarchical Independent Detection and Recognition), a novel strategy for underwater acoustic multi-target recognition. HIDR adopts a hierarchical architecture instead of the single-step traditional target recognition task, which is a relatively challenging task especially for the multi-target recognition. HIDR would firstly distinguish target signals from non-target signals as a detection stage, then pinpoint the specific target from all possible types of target signals as a recognition stage. This hierarchical architecture cannot only sharply reduce the difficulty of feature extraction, but also benefit for the higher recognition accuracy. A universal feature extraction strategy is utilized to extract two independent feature sets for the two stages respectively, which include auditory parameters especially adaptive to detection/recognition stages, as well as other common time/frequency domain features. Experiments with real sea trial data are conducted to compare HIDR with existing high-quality multi-target recognition schemes. Experimental results show that the proposed strategy can reach up to 88.71% of recognition accuracy in four-class recognition task, which is more than 5.25% higher than that of mainstream methods.

RETRACTED ARTICLE: Evaluation of image segmentation and multi class object recognition algorithm based on machine learning

This paper mainly updates the image segmentation and multi-target recognition algorithm through the support vector machine algorithm in ML, and verifies the reliability of the new proposed algorithm through simulation experiments, and determines that the ML-based image segmentation and multi-target recognition algorithm can have stronger processing capability in image recognition and processing. Finally, the performance of traditional image segmentation and multi class object recognition algorithms and the image segmentation and multi class object recognition algorithms proposed in this paper were compared through experiments. The results showed that the performance of the ML based image segmentation and multi class object recognition algorithms proposed in this paper has increased by 29.1% on average in all aspects.

Sensing and Navigation of Wearable Assistance Cognitive Systems for the Visually Impaired

This article develops a wearable vision-based assistance system to provide situational awareness for blind and visually impaired (BVI) people in indoor scenarios. The system is built upon nonintrusive wearable devices, including an RGB-D camera, an embedded computer, and haptic modules. First, the depth map and color images of the scene are obtained from an RGB-D camera, which provides 3-D environmental information. The modular work modes are then designed for different tasks, such as navigation and multitarget recognition. Then, the cognition results are summarized and presented to the user through verbal or haptic feedback. Our system is evaluated by a pilot test to validate its effectiveness of improving the navigation capabilities and multitarget recognition capabilities for the BVI in indoor environments. We present study results with different tasks, including navigation, object localization, face recognition, and text reading. The experiments prove that the system can meet the needs of the BVI in daily use.

Identification of new benzimidazole-triazole hybrids as anticancer agents: multi-target recognition, in vitro and in silico studies

Multi-target inhibitors represent useful anticancer agents with superior therapeutic attributes. Here in, two novel series of benzimidazole-triazole hybrids were designed, synthesised as multi-target EGFR, VEGFR-2 and Topo II inhibitors, and evaluated for anticancer activity. Compounds 5a and 6g were the most potent analogues against four cancer cell lines, HepG-2, HCT-116, MCF-7 and HeLa, and were further evaluated for EGFR, VEGFR-2, and Topo II inhibition. Compound 5a was especially good inhibitor for EGFR (IC50 = 0.086 µM) compared to Gefitinib (IC50 = 0.052 µM), moderate VEGFR-2 inhibitor (IC50 = 0.107 µM) compared to Sorafenib (IC50 = 0.0482 µM), and stronger Topo II inhibitor (IC50 = 2.52 µM) than Doxorubicin (IC50 = 3.62 µM). Compound 6g exhibited moderate EGFR and VEGFR-2 inhibition and weaker Topo II inhibition. DNA binding assay, cell cycle analysis, apoptotic induction, molecular docking, and physicochemical studies were additionally implemented to explore the plausible mechanism of the active compounds.