Sign in to use this feature.

Years

Between: -

Subjects

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Journals

remove_circle_outline
remove_circle_outline

Article Types

Countries / Regions

Search Results (312)

Search Parameters:
Keywords = ghost imaging

Order results
Result details
Results per page
Select all
Export citation of selected articles as:
22 pages, 6836 KiB  
Article
MonoSeg: An Infrared UAV Perspective Vehicle Instance Segmentation Model with Strong Adaptability and Integrity
by Peng Huang, Yan Yin, Kaifeng Hu and Weidong Yang
Sensors 2025, 25(1), 225; https://doi.org/10.3390/s25010225 - 3 Jan 2025
Viewed by 347
Abstract
Despite rapid progress in UAV-based infrared vehicle detection, achieving reliable target recognition remains challenging due to dynamic viewpoint variations and platform instability. The inherent limitations of infrared imaging, particularly low contrast ratios and thermal crossover effects, significantly compromise detection accuracy. Moreover, the computational [...] Read more.
Despite rapid progress in UAV-based infrared vehicle detection, achieving reliable target recognition remains challenging due to dynamic viewpoint variations and platform instability. The inherent limitations of infrared imaging, particularly low contrast ratios and thermal crossover effects, significantly compromise detection accuracy. Moreover, the computational constraints of edge computing platforms pose a fundamental challenge in balancing real-time processing requirements with detection performance. Here, we present MonoSeg, a novel instance segmentation framework optimized for UAV perspective infrared vehicle detection. Our approach introduces three key innovations: (1) the Ghost Feature Bottle Cross module (GFBC), which enhances backbone feature extraction efficiency while significantly reducing computational over-head; (2) the Scale Feature Recombination module (SFR), which optimizes feature selection in the Neck stage through adaptive multi-scale fusion; and (3) Comprehensive Loss function that enforces precise instance boundary delineation. Extensive experimental evaluation on bench-mark datasets demonstrates that MonoSeg achieves state-of-the-art performance across standard metrics, including Box mAP and Mask mAP, while maintaining substantially lower computational requirements compared to existing methods. Full article
(This article belongs to the Section Sensing and Imaging)
Show Figures

Figure 1

29 pages, 15216 KiB  
Article
CBGS-YOLO: A Lightweight Network for Detecting Small Targets in Remote Sensing Images Based on a Double Attention Mechanism
by Zhenyuan Wu, Di Wu, Ning Li, Wanru Chen, Jie Yuan, Xiangyue Yu and Yongqiang Guo
Remote Sens. 2025, 17(1), 109; https://doi.org/10.3390/rs17010109 - 31 Dec 2024
Viewed by 400
Abstract
With the continuous progress of remote sensing technology, the demand for means of detecting small targets in remote sensing images is escalating. The significance of detecting small targets in remote sensing images lies in enhancing the ability to identify small and elusive targets [...] Read more.
With the continuous progress of remote sensing technology, the demand for means of detecting small targets in remote sensing images is escalating. The significance of detecting small targets in remote sensing images lies in enhancing the ability to identify small and elusive targets and the detection accuracy against complex backgrounds, holding significant application value in military reconnaissance, environmental monitoring, and disaster early-warning systems. Firstly, the minuteness of certain targets in relation to the entire image in which they occur, particularly when the camera is situated at a higher altitude, renders them difficult to detect. Secondly, the varying background and lighting conditions in remote sensing images further complicate the detection task. Conventional target detection methods are frequently incapable of addressing these complexities, resulting in a reduction in detection accuracy and an increase in false alarms. Hence, in this paper, we propose a lightweight remote-sensing image target detection network model, CBGS-YOLO, created by introducing the Ghost module to decrease the model parameters, applying the SPD-Conv module to optimize downsampling, and integrating the convolutional block attention module to enhance detection accuracy. The experimental outcomes demonstrate that CBGS-YOLO outperforms other models when applied to the DB_Licenta and USOD datasets, significantly enhancing detection performance for small targets. Compared with YOLOv9, this model can reduce the number of parameters from 7.10 M to 5.12 M, and the average precision (mAP) is effectively improved. The model strengthens the ability to identify small targets against complex backgrounds while maintaining lightweight properties and possesses remarkable application prospects and practical value. Full article
Show Figures

Figure 1

15 pages, 2815 KiB  
Article
High Field MRI in Parotid Gland Tumors: A Diagnostic Algorithm
by Chiara Gaudino, Andrea Cassoni, Martina Lucia Pisciotti, Resi Pucci, Chiara Veneroso, Cira Rosaria Tiziana Di Gioia, Francesca De Felice, Patrizia Pantano and Valentino Valentini
Viewed by 353
Abstract
Backgrounds: Imaging of parotid tumors is crucial for surgery planning, but it cannot distinguish malignant from benign lesions with absolute reliability. The aim of the study was to establish a diagnostic MRI algorithm to differentiate parotid tumors. Methods: A retrospective study was conducted [...] Read more.
Backgrounds: Imaging of parotid tumors is crucial for surgery planning, but it cannot distinguish malignant from benign lesions with absolute reliability. The aim of the study was to establish a diagnostic MRI algorithm to differentiate parotid tumors. Methods: A retrospective study was conducted including all patients with parotid tumors, who underwent 3T-MRI and surgery. Morphological characteristics and normalized T2 and late postcontrast T1 signal intensities (SI) were assessed. “Ghosting sign” on late postcontrast T1 sequence was defined as indistinguishability of the tumor except for a thin peripheral enhancement. Patients were divided according to histology and imaging data were compared. A diagnostic MRI algorithm was established. Results: Thirty-six patients were included. The combination of normalized late T1 postcontrast SI, normalized T2 SI and “ghosting sign” allowed for the distinguishing of malignant from benign parotid tumors with high sensitivity (100%), specificity (93%), positive predictive value (80%), negative predictive value, (100%) and accuracy (94%). Moreover, pleomorphic adenomas often showed a homogeneous T2 signal and a complete capsule (p < 0.01), Warthin tumors protein-rich cysts and calcifications (p < 0.005 and p < 0.05), and malignant tumors an inhomogeneous contrast enhancement (p < 0.01). Conclusions: High field MRI represents a promising tool in parotid tumors, allowing for an accurate differentiation of malignant and benign lesions. Full article
(This article belongs to the Special Issue Advances in Radiotherapy for Head and Neck Cancer)
Show Figures

Figure 1

13 pages, 5367 KiB  
Article
Lightweight Neural Network Optimization for Rubber Ring Defect Detection
by Weihan Gao, Ziyi Huang and Haijun Hu
Appl. Sci. 2024, 14(24), 11953; https://doi.org/10.3390/app142411953 - 20 Dec 2024
Viewed by 372
Abstract
Surface defect detection based on machine vision and convolutional neural networks (CNNs) is an important and necessary process that enables rubber ring manufacturers to improve production quality and efficiency. However, such automatic detection always consumes substantial computer resources to guarantee detection accuracy. To [...] Read more.
Surface defect detection based on machine vision and convolutional neural networks (CNNs) is an important and necessary process that enables rubber ring manufacturers to improve production quality and efficiency. However, such automatic detection always consumes substantial computer resources to guarantee detection accuracy. To solve this problem, in this paper, a CNN optimization algorithm based on the Ghost module is presented. First, the convolutional layer is replaced with the Ghost module in CNNs so that feature maps can be generated using cheaper linear operations. Second, an optimization method is used to obtain the best replacement of the Ghost module to balance computer resource consumption and detection accuracy. Finally, an image preprocessing method that includes inverting colors is applied. This algorithm is integrated into YOLOv5, trained on a dataset of rubber ring surface defects. Compared to the original network, the network size decreases by 30.5% and the computational cost decreases by 23.1%, whereas the average precision only decreases by 1.8%. Additionally, the network’s training time decreases by 16.1% as a result of preprocessing. These results show that the proposed approach greatly helps practical rubber ring surface defect detection. Full article
Show Figures

Figure 1

13 pages, 5286 KiB  
Article
Eye-Inspired Single-Pixel Imaging with Lateral Inhibition and Variable Resolution for Special Unmanned Vehicle Applications in Tunnel Inspection
by Bin Han, Quanchao Zhao, Moudan Shi, Kexin Wang, Yunan Shen, Jie Cao and Qun Hao
Biomimetics 2024, 9(12), 768; https://doi.org/10.3390/biomimetics9120768 - 18 Dec 2024
Viewed by 606
Abstract
This study presents a cutting-edge imaging technique for special unmanned vehicles (UAVs) designed to enhance tunnel inspection capabilities. This technique integrates ghost imaging inspired by the human visual system with lateral inhibition and variable resolution to improve environmental perception in challenging conditions, such [...] Read more.
This study presents a cutting-edge imaging technique for special unmanned vehicles (UAVs) designed to enhance tunnel inspection capabilities. This technique integrates ghost imaging inspired by the human visual system with lateral inhibition and variable resolution to improve environmental perception in challenging conditions, such as poor lighting and dust. By emulating the high-resolution foveal vision of the human eye, this method significantly enhances the efficiency and quality of image reconstruction for fine targets within the region of interest (ROI). This method utilizes non-uniform speckle patterns coupled with lateral inhibition to augment optical nonlinearity, leading to superior image quality and contrast. Lateral inhibition effectively suppresses background noise, thereby improving the imaging efficiency and substantially increasing the signal-to-noise ratio (SNR) in noisy environments. Extensive indoor experiments and field tests in actual tunnel settings validated the performance of this method. Variable-resolution sampling reduced the number of samples required by 50%, enhancing the reconstruction efficiency without compromising image quality. Field tests demonstrated the system’s ability to successfully image fine targets, such as cables, under dim and dusty conditions, achieving SNRs from 13.5 dB at 10% sampling to 27.7 dB at full sampling. The results underscore the potential of this technique for enhancing environmental perception in special unmanned vehicles, especially in GPS-denied environments with poor lighting and dust. Full article
(This article belongs to the Special Issue Advanced Biologically Inspired Vision and Its Application)
Show Figures

Figure 1

12 pages, 7416 KiB  
Article
A Dual-Path Computational Ghost Imaging Method Based on Convolutional Neural Networks
by Hexiao Wang, Jianan Wu, Mingcong Wang and Yu Xia
Sensors 2024, 24(23), 7869; https://doi.org/10.3390/s24237869 - 9 Dec 2024
Viewed by 599
Abstract
Ghost imaging is a technique for indirectly reconstructing images by utilizing the second-order or higher-order correlation properties of the light field, which exhibits a robust ability to resist interference. On the premise of ensuring the quality of the image, effectively broadening the imaging [...] Read more.
Ghost imaging is a technique for indirectly reconstructing images by utilizing the second-order or higher-order correlation properties of the light field, which exhibits a robust ability to resist interference. On the premise of ensuring the quality of the image, effectively broadening the imaging range can improve the practicality of the technology. In this paper, a dual-path computational ghost imaging method based on convolutional neural networks is proposed. By using the dual-path detection structure, a wider range of target image information can be obtained, and the imaging range can be expanded. In this paper, for the first time, we try to use the two-channel probe as the input of the convolutional neural network and successfully reconstruct the target image. In addition, the network model incorporates a self-attention mechanism, which can dynamically adjust the network focus and further improve the reconstruction efficiency. Simulation results show that the method is effective. The method in this paper can effectively broaden the imaging range and provide a new idea for the practical application of ghost imaging technology. Full article
(This article belongs to the Section Sensing and Imaging)
Show Figures

Figure 1

20 pages, 12422 KiB  
Article
LHSDNet: A Lightweight and High-Accuracy SAR Ship Object Detection Algorithm
by Dahai Dai, Hao Wu, Yue Wang and Penghui Ji
Remote Sens. 2024, 16(23), 4527; https://doi.org/10.3390/rs16234527 - 3 Dec 2024
Viewed by 573
Abstract
At present, the majority of deep learning-based ship object detection algorithms concentrate predominantly on enhancing recognition accuracy, often overlooking the complexity of the algorithm. These complex algorithms demand significant computational resources, making them unsuitable for deployment on resource-constrained edge devices, such as airborne [...] Read more.
At present, the majority of deep learning-based ship object detection algorithms concentrate predominantly on enhancing recognition accuracy, often overlooking the complexity of the algorithm. These complex algorithms demand significant computational resources, making them unsuitable for deployment on resource-constrained edge devices, such as airborne and spaceborne platforms, thereby limiting their practicality. With the purpose of alleviating this problem, a lightweight and high-accuracy synthetic aperture radar (SAR) ship image detection network (LHSDNet) is proposed. Initially, GhostHGNetV2 was utilized as the feature extraction network, and the calculation amount of the network was reduced by GhostConv. Next, a lightweight feature fusion network was designed to combine shallow and deep features through lightweight convolutions, effectively preserving more information while minimizing computational requirements. Lastly, the feature extraction module was integrated through parameter sharing, and the detection head was lightweight to save computing resources further. The results from our experiments demonstrate that the proposed LHSDNet model increases mAP50 by 0.7% in comparison to the baseline model. Additionally, it illustrates a pronounced decrease in parameter count, computational demand, and model file size by 48.33%, 51.85%, and 41.26%, respectively, when contrasted with the baseline model. LHSDNet achieves a balance between precision and computing resources, rendering it more appropriate for edge device implementation. Full article
Show Figures

Figure 1

21 pages, 3849 KiB  
Article
CCW-YOLO: A Modified YOLOv5s Network for Pedestrian Detection in Complex Traffic Scenes
by Zhaodi Wang, Shuqiang Yang, Huafeng Qin, Yike Liu and Jinyan Ding
Information 2024, 15(12), 762; https://doi.org/10.3390/info15120762 - 1 Dec 2024
Viewed by 908
Abstract
In traffic scenes, pedestrian target detection faces significant issues of misdetection and omission due to factors such as crowd density and obstacle occlusion. To address these challenges and enhance detection accuracy, we propose an improved CCW-YOLO algorithm. The algorithm first introduces a lightweight [...] Read more.
In traffic scenes, pedestrian target detection faces significant issues of misdetection and omission due to factors such as crowd density and obstacle occlusion. To address these challenges and enhance detection accuracy, we propose an improved CCW-YOLO algorithm. The algorithm first introduces a lightweight convolutional layer using GhostConv and incorporates an enhanced C2f module to improve the network’s detection performance. Additionally, it integrates the Coordinate Attention module to better capture key points of the targets. Next, the bounding box loss function CIoU loss at the output of YOLOv5 is replaced with WiseIoU loss to enhance adaptability to various detection scenarios, thereby further improving accuracy. Finally, we develop a pedestrian count detection system using PyQt5 to enhance human–computer interaction. Experimental results on the INRIA public dataset showed that our algorithm achieved a detection accuracy of 98.4%, representing a 10.1% improvement over the original YOLOv5s algorithm. This advancement significantly enhances the detection of small objects in images and effectively addresses misdetection and omission issues in complex environments. These findings have important practical implications for ensuring traffic safety and optimizing traffic flow. Full article
Show Figures

Graphical abstract

14 pages, 3626 KiB  
Article
A Lightweight Deep Learning Network with an Optimized Attention Module for Aluminum Surface Defect Detection
by Yizhe Li, Yidong Xie and Hu He
Sensors 2024, 24(23), 7691; https://doi.org/10.3390/s24237691 - 30 Nov 2024
Viewed by 781
Abstract
Aluminum is extensively utilized in the aerospace, aviation, automotive, and other industries. The presence of surface defects on aluminum has a significant impact on product quality. However, traditional detection methods fail to meet the efficiency and accuracy requirements of industrial practices. In this [...] Read more.
Aluminum is extensively utilized in the aerospace, aviation, automotive, and other industries. The presence of surface defects on aluminum has a significant impact on product quality. However, traditional detection methods fail to meet the efficiency and accuracy requirements of industrial practices. In this study, we propose an innovative aluminum surface defect detection method based on an optimized two-stage Faster R-CNN network. A 2D camera serves as the image sensor, capturing high-resolution images in real time. Optimized lighting and focus ensure that defect features are clearly visible. After preprocessing, the images are fed into a deep learning network incorporated with a multi-scale feature pyramid structure, which effectively enhances defect recognition accuracy by integrating high-level semantic information with location details. Additionally, we introduced an optimized Convolutional Block Attention Module (CBAM) to further enhance network efficiency. Furthermore, we employed the genetic K-means algorithm to optimize prior region selection, and a lightweight Ghost model to reduce network complexity by 14.3%, demonstrating the superior performance of the Ghost model in terms of loss function optimization during training and validation as well as in terms of detection accuracy, speed, and stability. The network was trained on a dataset of 3200 images captured by the image sensor, split in an 8:1:1 ratio for training, validation, and testing, respectively. The experimental results show a mean Average Precision (mAP) of 94.25%, with individual Average Precision (AP) values exceeding 80%, meeting industrial standards for defect detection. Full article
(This article belongs to the Special Issue Sensing and Imaging for Defect Detection: 2nd Edition)
Show Figures

Figure 1

21 pages, 8183 KiB  
Article
ARSOD-YOLO: Enhancing Small Target Detection for Remote Sensing Images
by Yijuan Qiu, Xiangyue Zheng, Xuying Hao, Gang Zhang, Tao Lei and Ping Jiang
Sensors 2024, 24(23), 7472; https://doi.org/10.3390/s24237472 - 23 Nov 2024
Viewed by 769
Abstract
Remote sensing images play a vital role in domains including environmental monitoring, agriculture, and autonomous driving. However, the detection of targets in remote sensing images remains a challenging task. This study introduces innovative methods to enhance feature extraction, feature fusion, and model optimization. [...] Read more.
Remote sensing images play a vital role in domains including environmental monitoring, agriculture, and autonomous driving. However, the detection of targets in remote sensing images remains a challenging task. This study introduces innovative methods to enhance feature extraction, feature fusion, and model optimization. The Adaptive Selective Feature Enhancement Module (AFEM) dynamically adjusts feature weights using GhostModule and sigmoid functions, thereby enhancing the accuracy of small target detection. Moreover, the Adaptive Multi-scale Convolution Kernel Feature Fusion Module (AKSFFM) enhances feature fusion through multi-scale convolution operations and attention weight learning mechanisms. Moreover, our proposed ARSOD-YOLO optimized the network architecture, component modules, and loss functions based on YOLOv8, enhancing outstanding small target detection capabilities while preserving model efficiency. We conducted experiments on the VEDAI and AI-TOD datasets, showcasing the excellent performance of ARSOD-YOLO. Our algorithm achieved an mAP50 of 74.3% on the VEDAI dataset, surpassing the YOLOv8 baseline by 3.1%. Similarly, on the AI-TOD dataset, the mAP50 reached 47.8%, exceeding the baseline network by 6.1%. Full article
(This article belongs to the Section Sensing and Imaging)
Show Figures

Figure 1

26 pages, 14487 KiB  
Article
Accelerating Die Bond Quality Detection Using Lightweight Architecture DSGβSI-Yolov7-Tiny
by Bao Rong Chang, Hsiu-Fen Tsai and Wei-Shun Chang
Electronics 2024, 13(22), 4573; https://doi.org/10.3390/electronics13224573 - 20 Nov 2024
Viewed by 496
Abstract
The die bonding process is one of the most critical steps in the front-end semiconductor packaging process, as it significantly affects the yield of the entire IC packaging process. This research aims to find an efficient, intelligent vision detection model to identify whether [...] Read more.
The die bonding process is one of the most critical steps in the front-end semiconductor packaging process, as it significantly affects the yield of the entire IC packaging process. This research aims to find an efficient, intelligent vision detection model to identify whether each chip correctly adheres to the IC substrate; by utilizing the detection model to classify the type of defects occurring in the die bond images, the engineers can analyze the leading causes, enabling timely adjustments to key machine parameters in real-time, improving the yield of the die bond process, and significantly reducing manufacturing cost losses. This study proposes the lightweight Yolov7-tiny model using Depthwise-Separable and Ghost Convolutions and Sigmoid Linear Unit with β parameter (DSGβSI-Yolov7-tiny), which we can apply for real-time and efficient detection and prediction of die bond quality. The model achieves a maximum FPS of 192.3, a precision of 99.1%, and an F1-score of 0.97. Therefore, the performance of the proposed DSGβSI-Yolov7-tiny model outperforms other methods. Full article
(This article belongs to the Special Issue Novel Methods for Object Detection and Segmentation)
Show Figures

Figure 1

23 pages, 10156 KiB  
Article
GFS-YOLO11: A Maturity Detection Model for Multi-Variety Tomato
by Jinfan Wei, Lingyun Ni, Lan Luo, Mengchao Chen, Minghui You, Yu Sun and Tianli Hu
Agronomy 2024, 14(11), 2644; https://doi.org/10.3390/agronomy14112644 - 9 Nov 2024
Viewed by 1902
Abstract
In order to solve the problems that existing tomato maturity detection methods struggle to take into account both common tomato and cherry tomato varieties in complex field environments (such as light change, occlusion, and fruit overlap) and the model size being too large, [...] Read more.
In order to solve the problems that existing tomato maturity detection methods struggle to take into account both common tomato and cherry tomato varieties in complex field environments (such as light change, occlusion, and fruit overlap) and the model size being too large, this paper proposes a lightweight tomato maturity detection model based on improved YOLO11, named GFS-YOLO11. In order to achieve a lightweight network, we propose the C3k2_Ghost module to replace the C3K2 module in the original network, which can ensure a feature extraction capability and reduce model computation. In order to compensate for the potential feature loss caused by the light weight, this paper proposes a feature-refining module (FRM). After embedding each feature extraction module in the trunk network, it improves the feature expression ability of common tomato and cherry tomato in complex field environments by means of depth-separable convolution, multi-scale pooling, and channel attention and spatial attention mechanisms. In addition, in order to further improve the detection ability of the model for tomatoes of different sizes, the SPPFELAN module is also proposed in this paper. In combining the advantages of SPPF and ELAN, multiple parallel SPPF branches are used to extract features of different levels and perform splicing and fusion. To verify the validity of the method, this study constructed a dataset of 1061 images of common and cherry tomatoes, covering tomatoes in six ripened categories. The experimental results show that the performance of the GFS-YOLO11 model is significantly improved compared with the original model; the P, R, mAP50, and MAP50-95 increased by 5.8%, 4.9%, 6.2%, and 5.5%, respectively, and the number of parameters and calculation amount were reduced by 35.9% and 22.5%, respectively. The GFS-YOLO11 model is lightweight while maintaining high precision, can effectively cope with complex field environments, and more conveniently meet the needs of real-time maturity detection of common tomatoes and cherry tomatoes. Full article
(This article belongs to the Section Precision and Digital Agriculture)
Show Figures

Figure 1

20 pages, 8544 KiB  
Article
DCS-YOLOv5s: A Lightweight Algorithm for Multi-Target Recognition of Potato Seed Potatoes Based on YOLOv5s
by Zhaomei Qiu, Weili Wang, Xin Jin, Fei Wang, Zhitao He, Jiangtao Ji and Shanshan Jin
Agronomy 2024, 14(11), 2558; https://doi.org/10.3390/agronomy14112558 - 31 Oct 2024
Cited by 1 | Viewed by 668
Abstract
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 [...] Read more.
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. Full article
(This article belongs to the Special Issue Advances in Data, Models, and Their Applications in Agriculture)
Show Figures

Figure 1

25 pages, 24948 KiB  
Article
RRBM-YOLO: Research on Efficient and Lightweight Convolutional Neural Networks for Underground Coal Gangue Identification
by Yutong Wang, Ziming Kou, Cong Han and Yuchen Qin
Sensors 2024, 24(21), 6943; https://doi.org/10.3390/s24216943 - 29 Oct 2024
Viewed by 741
Abstract
Coal gangue identification is the primary step in coal flow initial screening, which mainly faces problems such as low identification efficiency, complex algorithms, and high hardware requirements. In response to the above, this article proposes a new “hardware friendly” coal gangue image recognition [...] Read more.
Coal gangue identification is the primary step in coal flow initial screening, which mainly faces problems such as low identification efficiency, complex algorithms, and high hardware requirements. In response to the above, this article proposes a new “hardware friendly” coal gangue image recognition algorithm, RRBM-YOLO, which is combined with dark light enhancement. Specifically, coal gangue image samples were customized in two scenarios: normal lighting and simulated underground lighting with poor lighting conditions. The images were preprocessed using the dim light enhancement algorithm Retinexformer, with YOLOv8 as the backbone network. The lightweight module RepGhost, the repeated weighted bi-directional feature extraction module BiFPN, and the multi-dimensional attention mechanism MCA were integrated, and different datasets were replaced to enhance the adaptability of the model and improve its generalization ability. The findings from the experiment indicate that the precision of the proposed model is as high as 0.988, the [email protected](%) value and [email protected]:0.95(%) values increased by 10.49% and 36.62% compared to the original YOLOv8 model, and the inference speed reached 8.1GFLOPS. This indicates that RRBM-YOLO can attain an optimal equilibrium between detection precision and inference velocity, with excellent accuracy, robustness, and industrial application potential. Full article
(This article belongs to the Section Remote Sensors)
Show Figures

Figure 1

16 pages, 4833 KiB  
Article
BGF-YOLOv10: Small Object Detection Algorithm from Unmanned Aerial Vehicle Perspective Based on Improved YOLOv10
by Junhui Mei and Wenqiu Zhu
Sensors 2024, 24(21), 6911; https://doi.org/10.3390/s24216911 - 28 Oct 2024
Viewed by 2308
Abstract
With the rapid development of deep learning, unmanned aerial vehicles (UAVs) have acquired intelligent perception capabilities, demonstrating efficient data collection across various fields. In UAV perspective scenarios, captured images often contain small and unevenly distributed objects, and are typically high-resolution. This makes object [...] Read more.
With the rapid development of deep learning, unmanned aerial vehicles (UAVs) have acquired intelligent perception capabilities, demonstrating efficient data collection across various fields. In UAV perspective scenarios, captured images often contain small and unevenly distributed objects, and are typically high-resolution. This makes object detection in UAV imagery more challenging compared to conventional detection tasks. To address this issue, we propose a lightweight object detection algorithm, BGF-YOLOv10, specifically designed for small object detection, based on an improved version of YOLOv10n. First, we introduce a novel YOLOv10 architecture tailored for small objects, incorporating BoTNet, variants of C2f and C3 in the backbone, along with an additional small object detection head, to enhance detection performance for small objects. Second, we embed GhostConv into both the backbone and head, effectively reducing the number of parameters by nearly half. Finally, we insert a Patch Expanding Layer module in the neck to restore the feature spatial resolution. Experimental results on the VisDrone-DET2019 and UAVDT datasets demonstrate that our method significantly improves detection accuracy compared to YOLO series networks. Moreover, when compared to other state-of-the-art networks, our approach achieves a substantial reduction in the number of parameters. Full article
(This article belongs to the Section Remote Sensors)
Show Figures

Figure 1

Back to TopTop