Target Image Research Articles

Improved algorithm for fracture-dissolution pore detection in resistivity imaging logging based on dung beetle optimization

Abstract Resistivity imaging logging has become a direct and precise method for visualizing the structural complexities of reservoir fractures and dissolution pores. The current use of Otsu's thresholding for segmentation results in poor segmentation quality and significant noise. Accurate segmentation of sub-images containing fracture and dissolution pore targets is essential for automated structure identification and subsequent parameter calculation. This study leverages the rapid convergence and robust global optimization capabilities of the Dung Beetle Optimizer to develop enhanced image segmentation approaches. Specifically, it introduces a refined K-Means algorithm for multi-category image segmentation and an Otsu algorithm for multi-threshold image segmentation, both optimized by the Dung Beetle Optimizer. Compared to conventional binary segmentation algorithms, this new algorithm effectively isolates noise and extracts multi-category information. Using the segmented sub-images, this paper integrates mathematical morphology techniques to compute parameters such as area, perimeter, tortuosity length, and pore shape factor for identified targets. Additionally, Principal Component Analysis is used to derive recognition factors for fractures and dissolution pores. Applications show that this factor can identify matrix, fracture, and dissolution pore targets in complex background images. By combining parameter information of the target area, the method effectively removes false information in resistivity imaging and segments sub-images of fractures and dissolution pores, calculating fracture area ratio, dissolution pore area ratio, and total area ratio.

Medical image segmentation with UNet-based multi-scale context fusion

Histopathological examination holds a crucial role in cancer grading and serves as a significant reference for devising individualized patient treatment plans in clinical practice. Nevertheless, the distinctive features of numerous histopathological image targets frequently contribute to suboptimal segmentation performance. In this paper, we propose a UNet-based multi-scale context fusion algorithm for medical image segmentation, which extracts rich contextual information by extracting semantic information at different encoding stages and assigns different weights to the semantic information at different scales through TBSFF module to improve the learning ability of the network for features. Through multi-scale context fusion and feature selection networks, richer semantic features and detailed information are extracted. The target can be more accurately segmented without significantly increasing the extra overhead. The results demonstrate that our algorithm achieves superior Dice and IoU scores with a relatively small parameter count. Specifically, on the GlaS dataset, the Dice score is 90.56, and IoU is 83.47. For the MoNuSeg dataset, the Dice score is 79.07, and IoU is 65.98.

Polymersomes as Novel Drug Delivery Alternative to Conventional Liposomes

The goal of medical research across the world is to improve the health of patients. Nanotechnology is an emerging field that is now heavily concentrated in the realm of medicine continuous research in the sector has resulted in the emergence of a new discipline known as "nanomedicine," which attempts to provide new treatment options while also improving the therapeutic efficacy of existing medications. polymersomes have gotten a lot of attention in recent research all around the world, and it's led to the creation of novel medical therapies. Solubilization, cancer therapy targeting, and usage as diagnostic tool are some of these techniques. Polymersomes, which are artificial amphiphilic vesicles made up of a variety of chemical polymers, are presently being investigated for delivering different probes for imaging target tissues/ organs, as well as cytotoxic medicines to tumor cells for gene therapy. Thorough analysis has been confirmed that polymersomes will surely compete in the future in the rapidly developing field of nanotechnology. Polymersomes have great stability, ease of flexibility, and capacity to encapsulate a variety of different drugs will ensure that they play a significant role in the development of sophisticated drug delivery systems.

Continuous transcranial ultrasound in large vessel stroke: Image guidance for high-intensity focused sonothrombolysis.

Sonothrombolysis is a potential adjunctive therapy for large vessel occlusion (LVO) stroke. Bedside ultrasound image-guided high-intensity focused ultrasound (HIFU) therapy could deliver higher energy therapeutic ultrasound to the thrombus with higher precision than what was previously accomplished in human trials. The aim is to test the feasibility of diagnostic transcranial contrast-enhanced ultrasound (CEUS) to image the occlusion site and continuously maintain the guidance image on-target for a sufficient exposure time for HIFU to be effective during LVO stroke evaluation and treatment. This prospective, single center, observational cohort study included adult patients, presenting within 6 hours of stroke symptom onset, with LVO identified on computed tomography angiography (CTA). A hand-held CEUS imaging study was initiated following CTA and lasted up to 30 minutes. The primary outcome is the proportion of patients where a guidance CEUS image of the occlusion was achieved. A CEUS image of the occluded artery was obtained in 32/35 of the included patients. The median total imaging time was 23 minutes (interquartile range 15-30). Patients undergoing thrombectomy had a lower total imaging time (17 vs. 29.5 minutes, p=.002). When imaging was successful, on-target image was maintained for only 58% (standard deviation 23.8%) of total imaging time. No complications related to CEUS were observed. This feasibility study explored the use of diagnostic transcranial CEUS for continuous imaging of occlusion sites in LVO strokes. Challenges in maintaining target image during HIFU were identified, highlighting the need for technical advances for clinical application.

3D coherent single shot lidar imaging beyond coherence length

Advancements in remote sensing and autonomous vehicle technologies made lidars equally important for unmanned objects alongside cameras. Therefore, precise 3D lidar imaging and point cloud generation have become important subjects. Although existing coherent lidar technologies provide precise imaging results, the spectral linewidth of the laser sources becomes a key limitation over long distances as it defines the maximum detection range. Here, we present long-distance 3D lidar imaging which removes the coherence length limitations and therefore the necessity of high-coherence laser sources. Mainly, we generate optical sidebands, by modulating a continuous wave (CW) laser source with multiple radio-frequency (RF) tones. Then, using our own post-processing and triangulation methods, we use the relative phase changes between the sidebands which are free from laser phase noise to determine the target distance. We prove that the multi-tone coherent Lidar technique can perform precise 3D imaging and point cloud generation of various targets at sub-10pW optical power reception and distances up to ∼12× beyond the coherence length of the CW laser employed in the lidar architecture. Overall, it is demonstrated that coherence length restriction is removed by the suggested method, which makes precise long-distance 3D lidar imaging possible, particularly for applications such as spacecraft and aerial coherent lidars.

A mitochondria-targeted nitric oxide probe with large Stokes shift for real-time imaging and evaluation of inflammatory bowel disease in situ

BackgroundInflammatory bowel disease (IBD) is a prevalent inflammatory disorder, and the abnormal expression of nitric oxide (NO) produced by biocatalysis of iNOS enzyme in mitochondria is directly associated with the occurrence and progression of IBD. Activatable fluorescent probes offer promising tools for early diagnosis of IBD, however, inadequate biodistribution and limited targeting properties of these probes in vivo severely impede accurate diagnosis of IBD and real-time evaluation of inflammatory levels in situ. Therefore, it is necessary to designed a highly efficient fluorescent probe towards NO to overcome inadequate biodistribution and achieve accurate diagnosis and evaluation of IBD in situ. ResultsWe designed a highly efficient mitochondria-targeted “turn-on” NIR fluorescent probe Cy-OMe which has excellent targeting properties and imaging ability. The response mechanism is probe Cy-OMe rapidly undergoes N-nitrosation reaction resulting in turn-on NIR fluorescence signal when exposed to NO. Cy-OMe exhibits high sensitivity and specificity in detecting NO content in vitro, owing to its large Stokes shift. Furthermore, the probe Cy-OMe not only efficiently targets mitochondria but also enables precise assessment of fluctuations in endogenous NO concertation across various cell types. Importantly, by virtue of large Stokes shift and excellent mitochondrial targeting ability, Cy-OMe has the capability to specifically evaluate dynamic fluctuations of NO in lipopolysaccharide (LPS)‐stimulated IBD mouse models in situ and Cy-OMe was achieved high-contrast imaging and precision diagnosis of intestinal inflammation diseases. SignificanceCy-OMe can accurately assess fluctuations in NO levels and show high signal fidelity in the diseased intestine region, which has prospects in the non-invasive diagnosis of intestinal inflammation in vivo. At the same time, it is expected to serve as a potential diagnose platform for investigating the physiological processes underlying NO-related inflammatory diseases and promoting understanding of the pathological functions of NO across diverse inflammatory diseases.

TransImg: A Translation Algorithm of Visible-to-Infrared Image Based on Generative Adversarial Network

Infrared images of sensitive targets are difficult to obtain and cannot meet the design and training needs of target detection and tracking algorithms for mobile platforms such as aircraft. This paper proposes an image translation algorithm TransImg, which can achieve visible light image translation to the infrared domain to enrich the dataset. First, the algorithm designed a generator structure consisting of a deep residual connected encoder and a region perception feature fusion module to enhance feature learning, thereby avoiding issues such as generating infrared images with insufficient details in the transfer task. Afterward, a multi-scale discriminator and a composite loss function were designed to further improve the transfer effect. Finally, an automatic mixed-precision training strategy was designed for the overall migration algorithm architecture to accelerate the training and generation of infrared images. Experiments have shown that the image translation algorithm TransImg has good algorithm accuracy, and the infrared image generated by visible light image translation has richer texture details, faster generation speed, and lower video memory consumption, and the performance exceeds the mainstream traditional algorithm, and the generated images can meet the requirements of target detection and tracking algorithms design and training for mobile platforms such as aircraft.

Research on X-ray security contraband identification technology based on lightweight YOLOv8

Aiming at the difficulty of identification and localization in the detection of contraband targets in X-ray images, as well as the demand for upgrading and deployment of security equipment during the peak flow stage, a lightweight X-ray security contraband detection algorithm is proposed and optimized for YOLOv8. Firstly, the number of channels in the original network is reduced according to a predetermined ratio, which effectively reduces model parameters and computational complexity and achieves better results than the current mainstream lightweight methods, such as model pruning and detection backbone optimization. Secondly, due to the presence of objects of various scales and sizes in X-ray security inspection images, we introduced the BiFPN feature extraction strategy in the neck. We designed a simplified version of BiFPN based on the YOLOv8 network structure to effectively integrate feature information from different levels and scales. Finally, we incorporated the idea of Focal Loss to address the issue of imbalance between positive and negative samples and proposed a new regression loss function, Focal-GIoU Loss, which combines GIoU Loss. This increases the loss weight for important but difficult-to-detect samples, such as small targets and overlapping targets, making the model more focused on these critical samples. Results show that our proposed YOLO-CBF improves mAP by 1.5%, 0.9%, and 0.5% on three datasets with different levels of occlusion in PIDray, while reducing the parameter count and computational cost from the original 3.0M and 8.1G to 2.1M and 6.3G.Moreover, it performs well in comparative experiments between different models and in generalization experiments across different datasets.

Tunable Imaging Distance Focusing Module Directly Driven by a Thin‐plate Piezoelectric Actuator

AbstractWith the advancement of imaging technology, the performance of optical focusing modules becomes crucial for determining imaging quality. Conventional focusing modules frequently face challenges of excessive bulk and weight, complicating the integrated design and limiting application fields. Herein, this study presents a piezo‐actuated optical focusing module (POFM) and the construction strategy to alleviate these issues. A novel radial‐bending resonant‐type piezoelectric actuator (RB‐RPA) is developed to directly drive the POFM. The RB‐RPA, which features a hollow structure (27 × 27 × 7 mm3), utilizes both radial and bending vibration modes of a thin metal plate. It achieves a speed of 122.93 mm s−1, a thrust force of 0.14 N, and a displacement resolution of 0.52 µm. Employing the proposed construction strategy, RB‐RPA is integrated with imaging components to fabricate a POFM prototype. Furthermore, the micrometer‐level displacement resolution of POFM facilitates optical focusing on imaging targets, allowing the acquisition of sharp images within 70 ms. It achieves an image resolution of 119.57 lp mm−1 within a 42 mm segment of the captured image. Finally, a QT‐based interface for the POFM, enables real‐time image capture and sharpness evaluation, thereby enhancing imaging efficiency and integration. This work provides a potential candidate for next‐generation imaging devices.

Research on Target Image Classification in Low-Light Night Vision.

In extremely dark conditions, low-light imaging may offer spectators a rich visual experience, which is important for both military and civic applications. However, the images taken in ultra-micro light environments usually have inherent defects such as extremely low brightness and contrast, a high noise level, and serious loss of scene details and colors, which leads to great challenges in the research of low-light image and object detection and classification. The low-light night vision image used as the study object in this work has an excessively dim overall picture and very little information about the screen's features. Three algorithms, HE, AHE, and CLAHE, were used to enhance and highlight the image. The effectiveness of these image enhancement methods is evaluated using metrics such as the peak signal-to-noise ratio and mean square error, and CLAHE was selected after comparison. The target image includes vehicles, people, license plates, and objects. The gray-level co-occurrence matrix (GLCM) was used to extract the texture features of the enhanced images, and the extracted image texture features were used as input to construct a backpropagation (BP) neural network classification model. Then, low-light image classification models were developed based on VGG16 and ResNet50 convolutional neural networks combined with low-light image enhancement algorithms. The experimental results show that the overall classification accuracy of the VGG16 convolutional neural network model is 92.1%. Compared with the BP and ResNet50 neural network models, the classification accuracy was increased by 4.5% and 2.3%, respectively, demonstrating its effectiveness in classifying low-light night vision targets.

Multi-Modal Object Detection Method Based on Dual-Branch Asymmetric Attention Backbone and Feature Fusion Pyramid Network

With the simultaneous acquisition of the infrared and optical remote sensing images of the same target becoming increasingly easy, using multi-modal data for high-performance object detection has become a research focus. In remote sensing multi-modal data, infrared images lack color information, it is hard to detect difficult targets with low contrast, and optical images are easily affected by illuminance. One of the most effective ways to solve this problem is to integrate multi-modal images for high-performance object detection. The challenge of fusion object detection lies in how to fully integrate multi-modal image features with significant modal differences and avoid introducing interference information while taking advantage of complementary advantages. To solve these problems, a new multi-modal fusion object detection method is proposed. In this paper, the method is improved in terms of two aspects: firstly, a new dual-branch asymmetric attention backbone network (DAAB) is designed, which uses a semantic information supplement module (SISM) and a detail information supplement module (DISM) to supplement and enhance infrared and RGB image information, respectively. Secondly, we propose a feature fusion pyramid network (FFPN), which uses a Transformer-like strategy to carry out multi-modal feature fusion and suppress features that are not conducive to fusion during the fusion process. This method is a state-of-the-art process for both FLIR-aligned and DroneVehicle datasets. Experiments show that this method has strong competitiveness and generalization performance.

Reduced Non-Specific Binding of Super-Resolution DNA-PAINT Markers by Shielded DNA-PAINT Labeling Protocols.

The DNA-based single molecule super-resolution imaging approach, DNA-PAINT, can achieve nanometer resolution of single targets. However, the approach can suffer from significant non-specific background signals originating from non-specifically bound DNA-conjugated DNA-PAINT secondary antibodies as shown here. Using dye-modified oligonucleotides the location of DNA-PAINT secondary antibody probes can easily be observed with widefield imaging prior to beginning a super-resolution measurement. This reveals that a substantial proportion of DNA probes can accumulate, non-specifically, within the nucleus, as well as across the cytoplasm, of cells. Here, Shielded DNA-PAINT labeling is introduced, a method using partially or fully double-stranded docking strand sequences, prior to labeling, in buffers with increased ionic strength to greatly reduce non-specific interactions in the nucleus as well as the cytoplasm. This new labeling approach is evaluated against various conditions and it is shown that applying Shielded DNA-PAINT can reduce non-specific events approximately five-fold within the nucleus. This marked reduction in non-specific binding of probes during the labeling procedure is comparable to results obtained with unnatural left-handed DNA albeit at a fraction of the cost. Shielded DNA-PAINT is a straightforward adaption of current DNA-PAINT protocols and enables nanometer precision imaging of nuclear targets with low non-specific backgrounds.

Imaging error reduction in radial cine-MRI with deep learning-based intra-frame motion compensation.

Radial cine-MRI allows for sliding window reconstruction at nearly arbitrary frame rate, promising high-speed imaging for intra-fractional motion monitoring in MRgRT. However, motion within the reconstruction window may determine the location of the reconstructed target to deviate from the true real-time position (target positioning errors), particularly in cases of fast breathing or for anatomical structures affected by the heartbeat. In this work, we present a proof-of-concept study aiming to enhance radial cine-MR imaging by implementing deep-learning-based intra-frame motion compensation techniques.
Approach: A novel network (TransSin-UNet) was proposed to continuously estimate the final-position image of the target, corresponding to end of the frame acquisition. Within the radial k-space reconstruction window, the spatial-temporal dependencies among the sinogram representation of the spokes were modeled by a transformer encoder subnetwork, followed by a UNet subnetwork operating in the spatial domain for pixel-level fine-tuning. By simulating motion-dependent radial sampling with (tiny) golden angles, we generated datasets from 25 4D digital anthropomorphic lung cancer phantoms. The network was then trained and extensively evaluated across datasets characterized by varying azimuthal radial profile increments.
Main Results: The method required additional 4.8ms per frame over the conventional approach involving direct image reconstruction with motion-corrupted spokes. TransSin-UNet outperformed architectures relying solely on transformer encoders or UNets across all the comparative evaluations, leading to a noticeable enhancement in image quality and target positioning accuracy. The normalized root mean-squared error (NRMSE) decreased by 50% from the initial value of 0.188 on average, whereas the mean Dice similarity coefficient (DSC) of the gross tumor volume (GTV) increased from 85.1% to 96.2% in the investigated cases. Furthermore, the final-positions of anatomical structures undergoing substantial intra-frame deformations were precisely derived.
Significance: The proposed approach enables an effective intra-frame motion compensation, offering an opportunity to reduce errors in radial cine-MR imaging for real-time motion management.&#xD.

Endothelium-targeted NF-κB siRNA nanogel for magnetic resonance imaging and visualized-anti-inflammation treatment of atherosclerosis

Atherosclerosis-induced lethal cardiovascular disease remains a severe healthcare threat due to the limited drug efficiency and untimely prediction of high-risk events caused by inadequate target specificity of medications, incapable recognition of insensitive patients, and variable morphology of vulnerable plaques. Therefore, it is necessary to develop efficient strategies to improve the diagnosis accuracy and achieve visualized treatment of atherosclerosis. Herein, we establish an inflamed endothelium-targeted three-in-one nucleic acid nanogel system that can reverse the inflammatory state of endothelial cells (ECs) in plaques and simultaneously achieve real-time monitoring of the therapy process for efficient atherosclerosis diagnosis and treatment. For this purpose, contrast agent (Gd-DOTA) and VCAM-1-targeted peptide (VP) are first covalently conjugated onto DNA strands by click reaction respectively, which could self-assemble into Y-shaped structures (Gd-Y1 and VP-Y2 motifs) with magnetic resonance (MR) imaging and endothelium targeting capacities. Thereafter, NF-κB subunit p65-targeting siRNA (siNF-κB) is crosslinked with Gd-Y1 and VP-Y2 motifs to construct the endothelium-targeting nanogel platform. With contrast agents inside, the nanogel enables MR-based diagnosis and visualized therapy of atherosclerosis, providing accurate prognostic analysis and indications for treatment results, which ensures timely disclosure of insensitive individuals and avoids acute lethal events. By delivering siNF-κB to inflammatory endothelium, the nanogel significantly regresses plaques in both the aorta and carotid artery with reduced inflammation cytokines, collagens, macrophages, and apoptotic cells, providing a potential anti-inflammation strategy to treat atherosclerosis and avoid acute cardiovascular disease.

68Ga-Labeled TRAP-Based Glycoside Trimers for Imaging of the Functional Liver Reserve.

The exclusive asialoglycoprotein receptor (ASGR) expression on hepatocytes makes it an attractive target for imaging of the functional liver reserve. Here, we present a set of TRAP-based glycoside trimers and evaluate their imaging properties compared to the gold standard [99mTc]Tc-GSA. The click-chemistry-based synthesis approach provided easy access to trimeric low-molecular-weight compounds. Labeling with 68Ga was carried out in high radiochemical yields (>99%). Complexes showed high stability and hydrophilicity. Protein binding ranged between 10 and 25%. Highest binding affinity (IC50) and best liver accumulation were found for [68Ga]Ga-T3N3, followed by [68Ga]Ga-T3G3 and [68Ga]Ga-T0G3. Rapid elimination from the rest of the body resulted in excellent target-to-background ratios. Our studies confirmed that high ASGR uptake depends on the correct spacer design and that N-acetylgalactosamine improves targeting properties in vivo. Thus, [68Ga]Ga-T3N3 represents a new low-molecular-weight radiopharmaceutical with pharmacokinetics similar to those of [99mTc]Tc-GSA.

Enhancing diffusion-weighted prostate MRI through self-supervised denoising and evaluation

Diffusion-weighted imaging (DWI) is a magnetic resonance imaging (MRI) technique that provides information about the Brownian motion of water molecules within biological tissues. DWI plays a crucial role in stroke imaging and oncology, but its diagnostic value can be compromised by the inherently low signal-to-noise ratio (SNR). Conventional supervised deep learning-based denoising techniques encounter challenges in this domain as they necessitate noise-free target images for training. This work presents a novel approach for denoising and evaluating DWI scans in a self-supervised manner, eliminating the need for ground-truth data. By leveraging an adapted version of Stein’s unbiased risk estimator (SURE) and exploiting a phase-corrected combination of repeated acquisitions, we outperform both state-of-the-art self-supervised denoising methods and conventional non-learning-based approaches. Additionally, we demonstrate the applicability of our proposed approach in accelerating DWI scans by acquiring fewer image repetitions. To evaluate denoising performance, we introduce a self-supervised methodology that relies on analyzing the characteristics of the residual signal removed by the denoising approaches.

X-Ray Emission of Nearby Low-mass and Sunlike Stars with Directly Imageable Habitable Zones

Stellar X-ray and UV radiation can significantly affect the survival, composition, and long-term evolution of the atmospheres of planets in or near their host star’s habitable zone (HZ). Especially interesting are planetary systems in the solar neighborhood that may host temperate and potentially habitable surface conditions, which may be analyzed by future ground- and space-based direct-imaging surveys for signatures of habitability and life. To advance our understanding of the radiation environment in these systems, we leverage ∼3 Ms of XMM-Newton and Chandra observations in order to measure three fundamental stellar properties at X-ray energies for 57 nearby FGKM stellar systems: the shape of the stellar X-ray spectrum, the luminosity, and the timescales over which the stars vary (e.g., due to flares). These systems possess HZs that will be directly imageable to next-generation telescopes such as the Habitable Worlds Observatory and ground-based Extremely Large Telescopes. We identify 29 stellar systems with L X/L bol ratios similar to (or less than) that of the Sun; any potential planets in the HZs of these stars therefore reside in present-day X-ray radiation environments similar to (or less hostile than) modern Earth, though a broader set of these targets could host habitable planets. An additional 19 stellar systems have been observed with the Swift X-ray Telescope; in total, only ∼30% of potential direct imaging target stars has been observed with XMM-Newton, Chandra, or Swift. The data products from this work (X-ray light curves and spectra) are available via a public Zenodo repository (doi:10.5281/zenodo.11490574).

Visual tracking algorithm based on template updating and dual feature enhancement

Aiming at the problem of tracking failure due to target deformation, flipping and occlusion in visual tracking, a template updating algorithm based on image structural similarity is proposed by dynamically updating the template to adapt to the changes of the target during tracking, specifically, a queue is used to save the recent N -frame tracking results, and a decision is made on whether to update the template or not based on the structural similarity score between the current tracking results and the template image, and if updated, the template is matched from the historical N -frame tracking results as the new template. If updated, the optimal target image is matched from the historical N -frame tracking results as a new template for subsequent tracking. The tracking feature enhancement module and segmentation feature enhancement module are also designed based on SiamMask network. The tracking feature enhancement module consists of non-local operations and convolutional downsampling, which is used to establish contextual correlation, enhance the target features, suppress the background interference, improve the tracking robustness, and solve the feature attenuation problem due to the occlusion of the target. The segmentation feature enhancement module introduces the convolutional block attention module and deformable convolution to improve the network's ability to capture channel and spatial features, adaptively learn the shape and contour information of the target, and enhance the network's segmentation accuracy of the tracked target. , which in turn improves the tracking accuracy. Experiments show that the proposed algorithm performs well and stably in solving the above problems, improving the expected average overlap rate by 5.2%, 5.3%, and 2.5%, and the robustness by 6%, 7.9%, and 15.6%on the VOT2016, VOT2018, and VOT2019 datasets , respectively, and achieving a real-time speed of 91 frames per second, when compared to the baseline SiamMask.

Improving rail transit security with enhanced YOLOv5 obstacle detection

Abstract As the economy advances and rail transit technology progresses, rail transit plays an important role in alleviating urban traffic pressure and promoting regional economic development. However, railway safety faces potential hazards such as foreign object intrusion in the trackside environment, seriously threatening the safety of trains and passengers. Therefore, to achieve high-performance recognition of obstacle target images in rail transit, a small sample object detection algorithm YOLOv5-RTO, which using EVC (Explicit Visual Center) attention mechanism and lightweight up-sampling operator CARAFE (Content-Aware ReAssembly of FEatures) to improve YOLOv5, has been proposed. Based on the self-collected image data of rail transit obstacles, a dense and time-varying dataset was created within the rail transit system, and data augmentation methods were used to reduce the impact of small sample datasets on the detection performance of subsequent algorithm. Using this dataset, target detection tests were conducted on rail transit obstacle images to analyze the actual performance of the training model. The experiment results indicate that the enhanced YOLOv5-RTO algorithm integrates the advantages of EVC and CARAFE while preserving the lightweight and accurate characteristics of YOLOv5. The improved algorithm scheme has an average inference time of 1.3 ms per frame in the field of rail transit images, achieving an overall mAP of 96.5%, an increase of 1.8% compared to the original algorithm. It has a certain engineering application value and provides reference for further optimizing the safety system of urban rail transit.

Research on Radar Target Detection Based on the Electromagnetic Scattering Imaging Algorithm and the YOLO Network

In this paper, the radar imaging technology based on the time-domain (TD) electromagnetic scattering algorithm is used to generate image datasets quickly and apply them to target detection research. Considering that radar images are different from optical images, this paper proposes an improved strategy for the traditional You Only Look Once (YOLO)v3 network to improve target detection accuracy on radar images. The speckle noise in radar images can cover the real information of a target image and increase the difficulty of target detection. The attention mechanisms are added to the traditional YOLOv3 network to strengthen the weight of the target region. By comparing the target detection accuracy under different attention mechanisms, an attention module with higher detection accuracy is obtained. The validity of the proposed detection network is verified on a simulation dataset, a measured real dataset, and a mixed dataset. This paper is about an interdisciplinary study of computational electromagnetics, remote sensing, and artificial intelligence. Experiments verify that the proposed composite network has better detection performance.