Search

Early detection of lung nodules is essential for lung cancer screening and improving patient survival rates. Traditional object detection networks such as YOLO and Faster R-CNN have shown promising results in detecting lung nodules but often lack sufficient integration of extracted features to enhance accuracy and efficiency. Moreover, these methods typically do not retain the spatial information of lung nodules from the original CT images. To overcome these limitations, a novel lung nodule detection algorithm based on YOLOv7 is introduced. Firstly, to better preserve essential features and minimize interference from irrelevant background noise, a deformable attention module for feature fusion has been designed. Additionally, maximum intensity projection is employed to create projection images at various intensities, thereby enriching the spatial background information that is often missing in single CT slices. Thirdly, the WIoU loss function is utilized to replace the original YOLOv7 loss function, aiming to reduce the influence of low-quality samples on the gradient within the dataset. The proposed model was validated using the publicly available LUNA16 dataset and achieved a recall rate of 94.40% and an AP value of 95.39%. These results demonstrate the enhanced precision and efficiency of lung nodule detection. [ABSTRACT FROM AUTHOR]

An accurate diagnosis of a brain tumour in its early stages is required to improve the possibility of survival for cancer patients. Due to the structural complexity of the brain, it has become very difficult and tedious for neurologists and radiologists to diagnose brain tumours in the initial stages with the help of various common manual approaches to tumour diagnosis. To improve the performance of the diagnosis, some computer-aided diagnosis-based systems are developed with the concepts of artificial intelligence. In this proposed manuscript, we analyse various computer-aided design (CAD)-based approaches and design a modern approach with ideas of transfer learning over deep learning on magnetic resonance imaging (MRI). In this study, we apply a transfer learning approach with the object detection model YOLO (You Only Look Once) and analyse the MRI dataset with the various modified versions of YOLO. After the analysis, we propose an object detection model based on the modified YOLOv7 with a morphological filtering approach to reach an efficient and accurate diagnosis. To enhance the performance accuracy of this suggested model, we also analyse the various versions of YOLOv7 models and find that the proposed model having the YOLOv7-E6E object detection technique gives the optimum value of performance indicators as precision, recall, F1, and mAP@50 as 1, 0.92, 0.958333, and 0.974, respectively. The value of mAP@50 improves to 0.992 by introducing a morphological filtering approach before the object detection technique. During the complete analysis of the suggested model, we use the BraTS 2021 dataset. The BraTS 2021 dataset has brain MR images from the RSNA-MICCAI brain tumour radiogenetic competition, and the complete dataset is labelled using the online tool MakeSense AI. [ABSTRACT FROM AUTHOR]

Because of the special way an unmanned aerial vehicle (UAV) acquires aerial photography, UAV images have the characteristics of large coverage area, complex background, and a large proportion of small targets, which exacerbate the difficulty of object detection. Additionally, UAV-based aerial image detection needs to meet lightweight and real-time capabilities. To address these issues, this paper proposes a lightweight model YOLOv7-P that is based on YOLOv7 but has a stronger detection capability for small targets. First, partial convolution (PConv) is used to reduce redundant parameters and computation in YOLOv7. Second, an optimal combination of detection heads is determined that can significantly improve the detection performance of small objects. Third, a novel lightweight convolution called PConv-wide is proposed to replace RepConv in the network, thus simplifying the network without affecting detection accuracy. Finally, the normalized wasserstein distance loss is reasonably combined with the complete intersection over union loss to further improve the sensitivity of the network to small targets. The proposed YOLOv7-P model strikes a delicate balance between precision and parameter count. Compared with the baseline YOLOv7 network, it reduces parameter count by 47.1% without increasing computational complexity and boosts AP50 by 8% and mAP by 5.4% on the VisDrone dataset. [ABSTRACT FROM AUTHOR]

The diversity and complexity of the agricultural environment pose significant challenges for the collection of pest and disease data. Additionally, pest and disease datasets often suffer from uneven distribution in quantity and inconsistent annotation standards. Enhancing the accuracy of pest and disease recognition remains a challenge for existing models. We constructed a representative agricultural pest and disease dataset, FIP6Set, through a combination of field photography and web scraping. This dataset encapsulates key issues encountered in existing agricultural pest and disease datasets. Referencing existing bounding box regression (BBR) loss functions, we reconsidered their geometric features and proposed a novel bounding box similarity comparison metric, DDRIoU, suited to the characteristics of agricultural pest and disease datasets. By integrating the focal loss concept with the DDRIoU loss, we derived a new loss function, namely Focal-DDRIoU loss. Furthermore, we modified the network structure of YOLOV7 by embedding the MobileViTv3 module. Consequently, we introduced a model specifically designed for agricultural pest and disease detection in precision agriculture. We conducted performance evaluations on the FIP6Set dataset using mAP75 as the evaluation metric. Experimental results demonstrate that the Focal-DDRIoU loss achieves improvements of 1.12%, 1.24%, 1.04%, and 1.50% compared to the GIoU, DIoU, CIoU, and EIoU losses, respectively. When employing the GIoU, DIoU, CIoU, EIoU, and Focal-DDRIoU loss functions, the adjusted network structure showed enhancements of 0.68%, 0.68%, 0.78%, 0.60%, and 0.56%, respectively, compared to the original YOLOv7. Furthermore, the proposed model outperformed the mainstream YOLOv7 and YOLOv5 models by 1.86% and 1.60%, respectively. The superior performance of the proposed model in detecting agricultural pests and diseases directly contributes to reducing pesticide misuse, preventing large-scale pest and disease outbreaks, and ultimately enhancing crop yields. These outcomes strongly support the promotion of sustainable agricultural development. [ABSTRACT FROM AUTHOR]

Accurate fruit detection is crucial for automated fruit picking. However, real-world scenarios, influenced by complex environmental factors such as illumination variations, occlusion, and overlap, pose significant challenges to accurate fruit detection. These challenges subsequently impact the commercialization of fruit harvesting robots. A tomato detection model named YOLO-SwinTF, based on YOLOv7, is proposed to address these challenges. Integrating Swin Transformer (ST) blocks into the backbone network enables the model to capture global information by modeling long-range visual dependencies. Trident Pyramid Networks (TPN) are introduced to overcome the limitations of PANet's focus on communication-based processing. TPN incorporates multiple self-processing (SP) modules within existing top-down and bottom-up architectures, allowing feature maps to generate new findings for communication. In addition, Focaler-IoU is introduced to reconstruct the original intersection-over-union (IoU) loss to allow the loss function to adjust its focus based on the distribution of difficult and easy samples. The proposed model is evaluated on a tomato dataset, and the experimental results demonstrated that the proposed model's detection recall, precision, F1 score, and AP reach 96.27%, 96.17%, 96.22%, and 98.67%, respectively. These represent improvements of 1.64%, 0.92%, 1.28%, and 0.88% compared to the original YOLOv7 model. When compared to other state-of-the-art detection methods, this approach achieves superior performance in terms of accuracy while maintaining comparable detection speed. In addition, the proposed model exhibits strong robustness under various lighting and occlusion conditions, demonstrating its significant potential in tomato detection. [ABSTRACT FROM AUTHOR]

To address the difficulties in manual counting for the uneven distribution and severe occlusion of watermelons in natural environments, this study utilizes drones and smartphones to collect videos and images, combined with manual annotation to establish a dataset for Sanbai melons and Ningxia selenium sand melons. A watermelon video automatic counting method based on the YOLOv7-GCSF model and an improved DeepSORT algorithm is proposed. The lightweight YOLOv7 model with GhostConv is enhanced with GBS modules, G-ELAN modules, and G-SPPCSPC modules to increase the model’s detection speed. Some ELAN modules are replaced with the C2f module from YOLOv8 to reduce redundant information. The SimAM attention mechanism is introduced into the MP module of the feature fusion layer to construct the MP-SimAM module, which is used to enhance the model's feature extraction capability. The CIoU loss function is replaced with the fasterconverging, lower-loss Focal EIoU loss function to increase the model's convergence speed. In video tracking and counting, a mask collision line mechanism is proposed for more accurate counting of Sanbai melons and Ningxia selenium sand melons. The results show that in terms of object detection: the four improvements to the YOLOv7-GCSF model have all enhanced the model’s performance to some extent. Specifically, compared to the YOLOv7 model, the construction of the MP-SimAM module increased accuracy by 1.5 percentage points, indicating a greater focus on Sanbai melons and Ningxia selenium sand melons. The addition of GhostConv reduced the model size by 28.1MB, demonstrating that the construction of GBS, G-ELAN, and G-SPPCSPC modules effectively reduced the model size and improved detection speed. The incorporation of the C2f module reduced the model's floating-point operations (FLOPs) by 77.5 billion, indicating that the model has eliminated most of the redundant information. The addition of the Focal EIoU loss function significantly increased the model’s convergence speed, indicating further enhancement of the model's learning ability. The improved YOLOv7-GCSF model achieved an accuracy (P) of 94.2% and a mean average precision (mAP0.5) of 98.2%, which is 5.0, 2.3, 21.9, and 14.9 percentage points higher in accuracy and 3.7, 0.3, 4.6, and 9.3 percentage points higher in mean average precision compared to YOLOv5, YOLOv7, Faster RCNN, and SSD, respectively. In terms of model lightweighting, the YOLOv7-GCSF model has seen a decrease of 1.18M and 0.11M in the number of parameters compared to the YOLOv4-Ghostnet and YOLOv7-Slimneck models, respectively. Compared to the original YOLOv7, the YOLOv7-GCSF model has reduced the parameter count and model size by 0.57M and 18.88MB, respectively. In terms of object tracking: the improved DeepSORT multi-object tracking accuracy is 91.2%, and the multi-object tracking precision is 89.6%, which is 5.0 and 13.7 percentage points higher in tracking accuracy and 3.7 and 13.1 percentage points higher in tracking precision compared to Tracktor and SORT, respectively. Comparing the improved model with manual counting results, the determination coefficient for the counting results of Sanbai melons and Ningxia selenium sand melons is 0.93, the average counting accuracy is 96.3%, and the average absolute error is 0.77, indicating that the error between the improved model and manual counting is small. This approach, by enabling effective counting of watermelons in agricultural fields, provides a technical methodology for the forecasting of watermelon yields. [ABSTRACT FROM AUTHOR]

To strengthen the safety monitoring of foggy road traffic and maintain the safety of vehicle driving on foggy roads, image dehazing algorithms are used to improve the clarity of road images detected in foggy environments, thereby improving the detection ability and monitoring efficiency of intelligent transportation systems for vehicle targets. Due to the low accuracy of vehicle detection and serious problem of missed detections in haze environments, this paper proposes an improved All-in-One Dehazing Network (AOD-Net) algorithm for detecting foggy vehicles, which adds batch normalization (BN) layers after each layer of convolution in AOD-Net, accelerating the convergence of the model and controlling overfitting. To enhance image detail information, an effective pyramid-shaped PSA attention module is embedded to extract richer feature information, enrich model representation, and improve the loss function to a multi-scale structural similarity (MS-SSIM) + L1 mixed loss function, thereby improving the quality, brightness, and contrast of dehazing images. Compared with current image dehazing algorithms, the dehazing quality of our algorithm is superior to other dehazing algorithms, such as dark channel prior (DCP), Dehaze-Net, and Fusion Feature Attention Network (FFA-Net). Compared with AOD-Net, the improved algorithm has increased the peak signal-to-noise ratio by 3.23 dB. At the same time, after the improved AOD-Net image dehazing processing, YOLOv7 object detection was performed and experimentally validated on a real foggy dataset. The results showed that compared with the previous method, it had better recognition performance in foggy detection and recognition, and higher detection accuracy for vehicles. [ABSTRACT FROM AUTHOR]

The civil aviation transportation has sustained rapid growth, which poses significant challenges in ensuring airport safety and efficiency of use. Persons and vehicles are tiny targets in airport surveillance. Existing detection methods are difficult to detect accurately. Enhancing small target detection by only the method of adding enhancement modules inevitably leads to increased network parameters. To address the above issues, this article proposes a lightweight airport surveillance detection based on YOLOv7 named LAS-YOLO. Firstly, we design the lightweight basic module, which significantly reduces network parameters while retaining certain local features. Secondly, we replace the SPPCSPC module with the spatial pyramid pooling-fast module with fewer parameters, further reducing the quantity of network parameters. Finally, the attention mechanism and small object detection layer are introduced to enhance small object detection accuracy. The efficient channel attention module is selected among three attention methods by experiments. We simulate the application process of object detection methods in airport surveillance, training on high-performance computers and testing on lower-performance computer. This article verifies the performance of the proposed method on the public ASS dataset consisting of the airport surface surveillance dataset (ASS1) and panoramic surveillance dataset (ASS2). The experiment shows that the parameters of LAS-YOLO are 12.5 M, which is 34.2 % of the original model. The mean average precision is 89.8 % on the ASS1. This proposed method enhances the average precision for airplane and vehicle detection by 14.5 % and 22.7 % compared to YOLOv7 on the ASS2. In order to reflect the robustness of the model in airport surveillance, we conduct another experiment using airplane data from the ROSD. The experiment demonstrates the superiority of the proposed method over other models in airport surveillance. Code is available at https://zenodo.org/records/10969930. [ABSTRACT FROM AUTHOR]

Pigs play vital roles in the food supply, economic development, agricultural recycling, bioenergy, and social culture. Pork serves as a primary meat source and holds extensive applications in various dietary cultures, making pigs indispensable to human dietary structures. Manual pig counting, a crucial aspect of pig farming, suffers from high costs and time-consuming processes. In this paper, we propose the PDC-YOLO network to address these challenges, dedicated to detecting pigs in complex farming environments for counting purposes. Built upon YOLOv7, our model incorporates the SPD-Conv structure into the YOLOv7 backbone to enhance detection under varying lighting conditions and for small-scale pigs. Additionally, we replace the neck of YOLOv7 with AFPN to efficiently fuse features of different scales. Furthermore, the model utilizes rotated bounding boxes for improved accuracy. Achieving a mAP of 91.97%, precision of 95.11%, and recall of 89.94% on our collected pig dataset, our model outperforms others. Regarding technical performance, PDC-YOLO exhibits an error rate of 0.002 and surpasses manual counting significantly in speed. [ABSTRACT FROM AUTHOR]

Copyright of Cotton Textile Technology is the property of Cotton Textile Technology Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Forest fires have a serious impact on people's living environment. Currently, drones enable rapid detection of forest fires. Due to the limited processing capabilities of onboard drones, the accuracy of smoke detection algorithms is low, and the processing speed is slow. This paper proposes an early wildfire smoke detection system designed for unmanned aerial vehicle (UAV) images, leveraging a modified YOLOv7 model, termed YOLOv7-MS(Modified Smoke). A dataset of more than 4,000 wildfire images was curated using existing UAV imagery. Our approach introduces several advancements. First, we propose a novel 3FIoU loss function to enhance stability and expedite convergence during training. Second, we optimize the backbone network by employing the FasterNet technique to reduce the number of parameters and increase the detection speed. Third, we address information loss and quality degradation problems by implementing the Asymptotic Feature Pyramid Network (AFPN) to counter indirect interactions between non-adjacent layers. Finally, we integrate a three-dimensional attention mechanism into the network to enhance focus on the target. Experimental findings showcase the efficacy of our YOLOv7-MS method, achieving a mean Average Precision (mAP) of 79.3% while maintaining a frame rate of 175 fps, outperforming other one-stage object detectors when evaluated on customized image datasets and public datasets. [ABSTRACT FROM AUTHOR]

The technology for object detection in remote sensing images finds extensive applications in production and people's lives, and improving the accuracy of image detection is a pressing need. With that goal, this paper proposes a range of improvements, rooted in the widely used YOLOv7 algorithm, after analyzing the requirements and difficulties in the detection of remote sensing images. Specifically, we strategically remove some standard convolution and pooling modules from the bottom of the network, adopting stride-free convolution to minimize the loss of information for small objects in the transmission. Simultaneously, we introduce a new, more efficient attention mechanism module for feature extraction, significantly enhancing the network's semantic extraction capabilities. Furthermore, by adding multiple cross-layer connections in the network, we more effectively utilize the feature information of each layer in the backbone network, thereby enhancing the network's overall feature extraction capability. During the training phase, we introduce an auxiliary network to intensify the training of the underlying network and adopt a new activation function and a more efficient loss function to ensure more effective gradient feedback, thereby elevating the network performance. In the experimental results, our improved network achieves impressive mAP scores of 91.2% and 80.8% on the DIOR and DOTA version 1.0 remote sensing datasets, respectively. These represent notable improvements of 4.5% and 7.0% over the original YOLOv7 network, significantly enhancing the efficiency of detecting small objects in particular. [ABSTRACT FROM AUTHOR]

Precision agriculture-based orchard management relies heavily on the accurate delineation of tree canopies, especially for high-value crops like mangoes. Traditional GIS and remote sensing methods, such as Object-Based Imagery Analysis (OBIA), often face challenges due to overlapping canopies, complex tree structures, and varied light conditions. This study aims to enhance the accuracy of mango orchard mapping by developing a novel deep-learning approach that combines fine-tuned object detection and segmentation techniques. UAV imagery was collected over a 65-acre mango orchard in Multan, Pakistan, and processed into an RGB orthomosaic with a 3 cm ground sampling distance. The You Only Look Once (YOLOv7) framework was trained on an annotated dataset to detect individual mango trees. The resultant bounding boxes were used as prompts for the segment anything model (SAM) for precise delineation of canopy boundaries. Validation against ground truth data of 175 manually digitized trees showed a strong correlation ( R 2 = 0.97), indicating high accuracy and minimal bias. The proposed method achieved a mean absolute percentage error (MAPE) of 4.94% and root mean square error (RMSE) of 80.23 sq ft against manually digitized tree canopies with an average size of 1290.14 sq ft. The proposed approach effectively addresses common issues such as inaccurate bounding boxes and over- or under-segmentation of tree canopies. The enhanced accuracy can substantially assist in various downstream tasks such as tree location mapping, canopy volume estimation, health monitoring, and crop yield estimation. [ABSTRACT FROM AUTHOR]

The real-time instance segmentation task based on deep learning aims to accurately identify and distinguish all instance objects from images or videos. However, due to the existence of problems such as mutual occlusion between instances, limitations in model receptive fields, etc., achieving accurate and real-time segmentation continues to pose a formidable challenge. To alleviate the aforementioned issues, this paper proposes a real-time instance segmentation method based on a dual-branch structure, called GHA-Inst. Specifically, we made improvements to the feature fusion module (Neck) and output end (Head) of the YOLOv7-seg real-time instance segmentation framework to mitigate the accuracy reduction caused by feature loss and reduce the interference of background noise on the model. Secondly, we introduced a Global Hybrid-Domain Attention (GHA) module to improve the model's focus on significant information while retaining more original spatial features, alleviate incomplete segmentation caused by instance occlusion, and improve the quality of generated masks. Finally, our method achieved competitive results on multiple metrics of the MS COCO 2017 and KINS open-source datasets. Compared with the YOLOv7-seg baseline model, GHA-Inst improved the average precision (AP) by 3.4% and 2.6% on the two datasets, respectively. [ABSTRACT FROM AUTHOR]

The detection algorithms of small objects in remote sensing images is often challenging due to the complex background and limited pixels. This can lead to reduced accuracy in detection and an increased number of missed small objects. So this paper introduces YOLOFNC, an enhanced network based on YOLOv7. To improve the model's ability to capture features of small objects, an enhanced C3-Faster module based on the C3 module is designed and integrated into the YOLOv7 network. This module helps extract more features related to small objects. Additionally, we employ Normalized Wasserstein Distance (NWD) fusion GIoU as a novel loss function to refine the accuracy of network optimization weights and the small object regression framework. Furthermore, a coordinated attention (CA) mechanism is incorporated at strategic locations in the model to reduce redundant information in the feature layer and prevent the loss of important small object features. we conduct comparison experiments between YOLO-FNC and other commonly used object detection algorithms on DIOR, AITOD, and VisDrone datasets. The experimental results show that YOLO-FNC achieves 84.4% mAP on the DIOR dataset, 35.9% mAP on the AI-TOD dataset, and 52.6% mAP on the VisDrone dataset. Compared to YOLOv7 and other remote sensing object detection models, YOLO-FNC demonstrates better performance in object detection. [ABSTRACT FROM AUTHOR]

Copyright of Computer Measurement & Control is the property of Magazine Agency of Computer Measurement & Control and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Computer Measurement & Control is the property of Magazine Agency of Computer Measurement & Control and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Computer Measurement & Control is the property of Magazine Agency of Computer Measurement & Control and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Railway Science & Engineering is the property of Journal of Railway Science & Engineering Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Advanced Textile Technology is the property of Zhejiang Sci-Tech University Magazines and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

This study aims to address the problem in tracking technology in which targeted cruising ships or submarines sailing near the water surface are tracked at low frame rates or with some frames missing in the video image, so that the tracked targets have a large gap between frames, leading to a decrease in tracking accuracy and inefficiency. Thus, in this study, we proposed a water surface dynamic multi-target tracking algorithm based on the fusion of YOLOv7 and DeepSORT. The algorithm first introduces the super-resolution reconstruction network. The network can eliminate the interference of clouds and waves in images to improve the quality of tracking target images and clarify the target characteristics in the image. Then, the shuffle attention module is introduced into YOLOv7 to enhance the feature extraction ability of the target features in the recognition network. Finally, Euclidean distance matching is introduced into the cascade matching of the DeepSORT algorithm to replace the distance matching of IOU to improve the target tracking accuracy. Simulation results showed that the algorithm proposed in this study has a good tracking effect, with an improvement of 9.4% in the improved YOLOv7 model relative to the mAP50-95 value and an improvement of 13.1% in the tracking accuracy in the DeepSORT tracking network compared with the SORT tracking accuracy. [ABSTRACT FROM AUTHOR]

One-stage algorithm can be effectively used in normal conditions, showing excellent performance on unmanned aerial vehicle (UAV) detection. However, when facing inclement weathers, such as foggy environment, it cannot give a satisfactory outcome we crave for. At the same time, UAV, a tiny object, only contains a few pixels in images and is hided in the fog, causing object obscurity. Concerned about these premises, an improved YOLOv7 is proposed to focus on UAV detection in foggy situation. We adopt BiFormer, a novel dynamic sparse attention through bi-level routing to achieve a flexible distribution of calculation with content awareness, and CL, combined loss function for replacing original IoU metric, to overcome these challenges. At last, Content-Aware ReAssembly of Features (CARAFE) is integrated to the network, aggregating contextual information within a large receptive field. According to this task, we built a new dataset for fog detection (UAV-FG) in which objects are covered by fog, and amount of experiments on UAV-FG datasets verify the effectiveness of our design. Compared with YOLOv7, our method shows consistent and substantial gains (23.21%, 14.35% improvement in mAP@0.5 and mAP@0.5:0.95, respectively) with negligible computational overhead and also satisfies the requirement of real-time detection. [ABSTRACT FROM AUTHOR]

Forest fire is an ecological catastrophe with great damage and rapid spread, which inflicts significant damage upon the ecological balance of the forests and poses a threat to human well-being. Given the current problems of low forest fire recognition accuracy and weak local detection, an improved forest fire detection algorithm Catch Fire YOLO-based neural networks (CF-YOLO) based on YOLOv7 model is studied. In global information processing, the plug-and-play coordinate attention mechanism is introduced into the YOLOv7 model, which enhances the visual depiction of the receptive field, while aggregate features along different spatial directions to improve the depiction of the focal interest. We present the three parallel max-pooling operations in the SPPCSPC module of the Neck to a serial mode, where the output of each pooling is used as the next pooling input. In local information processing, we prepare a feature fusion module to replace the partial high-efficiency layer aggregation network (ELAN), so that the network further improves the detection accuracy while speeding up the calculation. The proposed model was trained and verified on a forest fire dataset, the experimental results demonstrate an improved detection capability, especially for small targets, and can meet the requirements of edge deployment in forest fire scenarios. [ABSTRACT FROM AUTHOR]

Wearing safety helmets at construction sites is a major measure to prevent safety accidents, so it is essential to supervise and ensure that workers wear safety helmets. This requires a high degree of real-time performance. We improved the network structure based on YOLOv7. To enhance real-time performance, we introduced GhostModule after comparing various modules to create a new efficient structure that generates more feature mappings with fewer linear operations. SE blocks were introduced after comparing several attention mechanisms to highlight important information in the image. The EIOU loss function was introduced to speed up the convergence of the model. Eventually, we constructed the efficient model EGS-YOLO. EGS-YOLO achieves a mAP of 91.1%, 0.2% higher than YOLOv7, and the inference time is 13.3% faster than YOLOv7 at 3.9 ms (RTX 3090). The parameters and computational complexity are reduced by 37.3% and 33.8%, respectively. The enhanced real-time performance while maintaining the original high precision can meet actual detection requirements. [ABSTRACT FROM AUTHOR]

Detecting small and densely packed objects in images remains a significant challenge in computer vision. Existing object detection methods often exhibit low accuracy and frequently miss detection when identifying dense small objects and require larger model parameters. This study introduces a novel detection framework designed to address these limitations by integrating advanced feature fusion and optimization techniques. Our approach focuses on enhancing both detection accuracy and parameter efficiency. The approach was evaluated on the open-source VisDrone2019 data set and compared with mainstream algorithms. Experimental results demonstrate a 70.2% reduction in network parameters and a 6.3% improvement in mAP@0.5 over the original YOLOv7 algorithm. These results demonstrate that the enhanced model surpasses existing algorithms in detecting small objects. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Xi'an Jiaotong University is the property of Editorial Office of Journal of Xi'an Jiaotong University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Surface defect detection on wafers is crucial for quality control in semiconductor manufacturing. However, the complexity of defect spatial features, including mixed defect types, large scale differences, and overlapping, results in low detection accuracy. In this paper, we propose a CC-De-YOLO model, which is based on the YOLOv7 backbone network. Firstly, the coordinate attention is inserted into the main feature extraction network. Coordinate attention decomposes channel attention into two one-dimensional feature coding processes, which are aggregated along both horizontal and vertical spatial directions to enhance the network’s sensitivity to orientation and position. Then, the nearest neighbor interpolation in the upsampling part is replaced by the CAR-EVC module, which predicts the upsampling kernel from the previous feature map and integrates semantic information into the feature map. Two residual structures are used to capture long-range semantic dependencies and improve feature representation capability. Finally, an efficient decoupled detection head is used to separate classification and regression tasks for better defect classification. To evaluate our model’s performance, we established a wafer surface defect dataset containing six typical defect categories. The experimental results show that the CCDe-YOLO model achieves 91.0% mAP@0.5 and 46.2% mAP@0.5:0.95, with precision of 89.5% and recall of 83.2%. Compared with the original YOLOv7 model and other object detection models, CC-De-YOLO performs better. Therefore, our proposed method meets the accuracy requirements for wafer surface defect detection and has broad application prospects. The dataset containing surface defect data on wafers is currently publicly available on GitHub (https://github.com/ztao3243/Wafer-Datas.git).

Human pose estimation aims to locate and predict the key points of the human body in images or videos. Due to the challenges of capturing complex spatial relationships and handling different body scales, accurate estimation of human pose remains challenging. Our work proposes a real-time human pose estimation method based on the anchor-assisted YOLOv7 framework, named MDA-YOLO Person. In this study, we propose the Keypoint Augmentation Strategies (KAS) to overcome the challenges faced in human pose estimation and improve the model's ability to accurately predict keypoints. Furthermore, we introduce the Anchor Adjustment Module (AAM) as a replacement for the original YOLOv7's detection head. By adjusting the parameters associated with the detector's anchors, we achieve an increased recall rate and enhance the completeness of the pose estimation. Additionally, we incorporate the Multi-Scale Dual-Head Attention (MDA) module, which effectively models the weights of both channel and spatial dimensions at multiple scales, enabling the model to focus on more salient feature information. As a result, our approach outperforms other methods, as demonstrated by the promising results obtained on two large-scale public datasets. MDA-YOLO Person outperforms the baseline model YOLOv7-pose on both MS COCO 2017 and CrowdPose datasets, with improvements of 2.2% and 3.7% in precision and recall on MS COCO 2017, and 1.9% and 3.5% on CrowdPose, respectively. [ABSTRACT FROM AUTHOR]

To enhance the cleanliness of creek environments, quadruped robots can be utilized to detect for creek waste. The continuous changes in the water environment significantly reduce the accuracy of image detection when using quadruped robots for image acquisition. In order to improve the accuracy of quadruped robots in waste detection, this article proposed a detection model called YOLOv7-GCM model for creek waste. The model integrated a global attention mechanism (GAM) into the YOLOv7 model, which achieved accurate waste detection in ever-changing backgrounds and underwater conditions. A content-aware reassembly of features (CARAFE) replaced a up-sampling of the YOLOv7 model to achieve more accurate and efficient feature reconstruction. A minimum point distance intersection over union (MPDIOU) loss function replaced the CIOU loss function of the YOLOv7 model to more accurately measure the similarity between target boxes and predictive boxes. After the aforementioned improvements, the YOLOv7-GCM model was obtained. A quadruped robot to patrol the creek and collect images of creek waste. Finally, the YOLOv7-GCM model was trained on the creek waste dataset. The outcomes of the experiment show that the precision rate of the YOLOv7-GCM model has increased by 4.2% and the mean average precision (mAP@0.5) has accumulated by 2.1%. The YOLOv7-GCM model provides a new method for identifying creek waste, which may help promote efficient waste management. [ABSTRACT FROM AUTHOR]

Traffic sign detection is a crucial aspect of advanced driver assistance systems (ADAS) for academic research and the automotive industry. seeing that accurate and timely detection of traffic signs (TS) is essential for ensuring the safety of driving. However, TS detection methods encounter challenges like slow detection speed and a lack of robustness in complex environments. This paper suggests addressing these limitations by proposing the use of the you only look one version 7 (YOLOv7) network to detect and recognize TS in road scenes. Furthermore, the k-means++ algorithm is used to acquire anchor boxes. Additionally, a tiny version of YOLOv7 is used to take advantage of its real-time and low model size, which are required for real-time hardware implementation. So, we conducted an experiment using our proprietary Morocco dataset. According to the experimental results, YOLOv7 achieves 85% in terms of mean average precision (mAP) at 0.5 for all classes. And YOLOv7-tiny obtains 90% in the same term. Afterward, a recognition system for the prohibitive class using the convolutional neural network (CNN) is trained and integrated inside the YOLOv7 algorithm; its model achieves an accuracy of 99%, which leads to a good specification of the prohibitive sign meaning. [ABSTRACT FROM AUTHOR]

To solve the problems of low accuracy, slow detection speed, and difficulty in deploying model parameters in surface defect detection of continuous casting production process, a lightweight surface defect detection algorithm YOLOv7-TSCR that integrates heavy parameterization and attention mechanism was proposed. Firstly, based on the Mish and SiLU activation functions and the SimAM attention mechanism, an improved high-efficiency layer aggregation module ELAN-S was constructed to effectively enhance the extraction of multi-scale defect features. Secondly, the C2f_RG module was designed to improve the feature fusion network, reducing the number of parameters while obtaining richer gradient flow information and enhancing feature fusion capabilities. Finally, based on the collected defect images from actual production, a dataset of casting defects was constructed and validated. The results show that YOLOv7-TSCR has significantly improved detection performance compared to other network models；With a reduced number of model parameters, the accuracy reaches 93.5%, the average accuracy increasesby 2.8%, and the detection speed reaches 120 FPS; The generalization comparison experiment on the NEU-DET public dataset proves that the algorithm has strong generalization. On the basis of ensuring high detection accuracy, the improved algorithm has a fast detection speed and a small number of parameters, which provides a technical reference for the efficient detection of surface defects in casting billets.

Abstract Aiming at the problems of error detection and missing detection in night target detection, this paper proposes a night target detection algorithm based on YOLOv7(You Only Look Once v7). The algorithm proposed in this paper preprocesses images by means of square equalization and Gamma transform. The GSConv(Group Separable Convolution) module is introduced to reduce the number of parameters and the amount of calculation to improve the detection effect. ShuffleNetv2_×1.5 is introduced as the feature extraction Network to reduce the number of Network parameters while maintaining high tracking accuracy. The hard-swish activation function is adopted to greatly reduce the delay cost. At last, Scylla Intersection over Union function is used instead of Efficient Intersection over Union function to optimize the loss function and improve the robustness. Experimental results demonstrate that the average detection accuracy of the proposed improved YOLOv7 model is 88.1%. It can effectively improve the detection accuracy and accuracy of night target detection.

During the packaging process, it is essential to detect the steel stamping characters inside the box to identify any missing or repeated characters. Currently, manual detection suffers from low efficiency and a high false detection rate. To address these challenges, a steel stamping character recognition and analysis system based on machine vision has been developed. The enhanced YOLOv7 detection method was employed for character identification, complemented by a statistical analysis approach to achieve automated judgment and detection. To address the issue of size disparity between large and small characters, a small size anchor box and a larger detection head were integrated. Furthermore, modifications were made to the output structure of the YOLOv7 prediction network to enhance multi-scale detection capabilities. The inclusion of the location attention convolution module bolstered global feature extraction, thereby enhancing the detection accuracy of similar characters. Moreover, the utilization of a hash table was used to improve the efficiency of mapping steel stamping character recognition sequences. The experimental results demonstrate that the enhanced model achieves an accuracy of 99.83%, with a processing efficiency of 10.5 ms per single frame. These findings align with the performance criteria for automatic recognition and analysis of steel stamping characters.

The gangue recognition technology is one of the key technologies in the intelligent construction of mines. To address the problem of low accuracy of the gangue recognition model caused by low illumination and high dust environment at the working face and the difficulty of recognizing small target gangue, a coal gangue image recognition model based on CSPNet-YOLOv7 target detection algorithm is proposed. Cross Stage Partial Network (CSPNet) is used to improve the backbone feature extraction network of YOLOv7 model, optimize the gradient information to reduce the network parameters, while Recursive Feature Pyramid (RFP) and Switchable Auto Convolution (SAC) to replace the simple up and down sampling and normal convolution modules in the neck feature extraction network, and to enhance the generalization ability of the network by using three migration training for feature learning of different widths and depths. The experimental results show that the CSPNet-YOLOv7 model has an average accuracy mean of 97.53%, an accuracy rate of 92.24%, a recall rate of 97.91%, an F1 score of 0.95, a model parametric number of 30.85×106, a floating point operation count of 42.15×109, and a frame rate of 24.37 f/s transmitted per second, Compared to the YOLOv7 model, the average mean accuracy is improved by 7.46%, and the number of parameters and floating point operations are reduced by 17.23% and 60.41%, respectively, compared to the FasterRCNN-Resnet50, YOLOv3, YOLOv4, MobileNet V2 -YOLOv4, YOLOv4-VGG, YOLOv5s models. The CSPNet-YOLOv7 model has the highest average accuracy mean for coal gangue identification, while the number of parameters and floating point operations is small, which has a good balance between identification accuracy and speed. Finally, the CSPNet-YOLOv7 model is validated through downhole field tests, providing an effective technical means for accurate coal gangue identification.

Abstract The precise identification of surface imperfections in steel strips is crucial for ensuring steel product quality. To address the challenges posed by the substantial model size and computational complexity in current algorithms for detecting surface defects in steel strips, this paper introduces SS-YOLO (YOLOv7 for Steel Strip), an enhanced lightweight YOLOv7 model. This method replaces the CBS module in the backbone network with a lightweight MobileNetv3 network, reducing the model size and accelerating the inference time. The D-SimSPPF module, which integrates depth separable convolution and a parameter-free attention mechanism, was specifically designed to replace the original SPPCSPC module within the YOLOv7 network, expanding the receptive field and reducing the number of network parameters. The parameter-free attention mechanism SimAM is incorporated into both the neck network and the prediction output section, enhancing the ability of the model to extract essential features of strip surface defects and improving detection accuracy. The experimental results on the NEU-DET dataset show that SS-YOLO achieves a 97% mAP50 accuracy, which is a 4.5% improvement over that of YOLOv7. Additionally, there was a 79.3% reduction in FLOPs(G) and a 20.7% decrease in params. Thus, SS-YOLO demonstrates an effective balance between detection accuracy and speed while maintaining a lightweight profile.

To address the challenges of multi-scale objects, dense distributions, occlusions, and numerous small targets in UAV image detection, we present CMS-YOLOv7, a real-time target detection method based on an enhanced YOLOv7 model. Firstly, the detection layer P2 for small targets was added to YOLOv7 to enhance the detection ability of small and medium-sized targets, and the deep detection head P5 was taken out to mitigate the influence of excessive downsampling on small target images. The anchor frame was calculated by the K-means++ method. Using the concept of Inner-IoU, the Inner-MPDIoU loss function was constructed to control the range of the auxiliary border and improve detection performance. Furthermore, the CARAFE module was introduced to replace traditional upsampling methods, offering improved integration of semantic information during the image upsampling process and enhancing feature mapping accuracy. Simultaneously, during the feature extraction stage, a non-strided convolutional SPD-Conv module was constructed using space-to-depth techniques. This module replaced certain convolutional operations to minimize the loss of fine-grained information and improve the model's ability to extract features from small targets. Experiments on the UAV aerial photo dataset VisDrone2019 demonstrated that compared with the baseline YOLOv7 object detection algorithm, CMS-YOLOv7 achieved an improvement of 3.5% mAP@0.5, 3.0% mAP@0.5:0.95, and the number of parameters decreased by 18.54 M. The ability of small target detection was significantly enhanced. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Traffic mark detection and identification play a key character in the development of driverless and intelligent transportation systems, offering significant assistance in ensuring the safety of people's daily travels. However, the detection effect of traffic signs is affected by many target categories, small targets, and low recognition accuracy, making traffic sign detection more challenging than target detection in general scenarios. In this paper, an improved YOLOv7 network (YOLOv7-COORD) is entered. Foremost, increase CBAM attention module at the connection between backbone and neck network of YOLOv7 to enhance the expression ability of neural networks through the attention mechanism, emphasizing important features and ignoring minor features to enhance the efficiency and precision of the network. Secondly, By adding CoordConv before the upsampling of the neck and before the detection head output, the network can better feel the location message in the characteristic map. Finally, a detection head generated by the low-level, high-resolution characteristic map is added to enhance the recognition accuracy of small target object. The abundance of experimental data demonstrates that the impression of the improved YOLOv7-COORD model is superior to that of the original YOLOv7 model, and the average accuracy of (mAP@0.5) on TT100K datasets is 3.2% higher than that of YOLOv7, reaching 85.4%. In summary, the improved YOLOv7-COORD model can better detect targets in traffic sign images. [ABSTRACT FROM AUTHOR]

The humanoid robot soccer system encounters a notable challenge in object detection, primarily concentrating on identifying the ball and often neglecting crucial elements like opposing robots and goals, resulting in on-field collisions and imprecise ball shooting. This study comparatively evaluates three you only look once (YOLO) real-time object detection system variants: YOLOv8, YOLOv7, and YOLO-NAS. A dataset of 2104 annotated images, covering classes such as ball, goalpost, and robot, was curated from Roboflow and robot-captured images. The dataset was partitioned into training, validation, and testing sets, and each YOLO model underwent extensive finetuning over 100 epochs on this custom dataset, leveraging the pre-trained common objects in context (COCO) model. Evaluation metrics, including mean average precision (mAP) and inference speed, assessed performance. YOLOv8 achieved the highest accuracy with a mAP of 0.92, while YOLOv7 showed the fastest inference speed of 24 ms on the Jetson Nano platform. Balancing accuracy and speed, YOLO-NAS emerged as the optimal choice. Thus, YOLO-NAS is recommended for object detection for humanoid soccer robots, regardless of team affiliation. Future research should focus on enhancing object detection through advanced training techniques, model architectures, and sensor fusion for improved performance in dynamic environments, potentially optimizing through scenario-specific fine-tuning. [ABSTRACT FROM AUTHOR]

Aiming at the problem of low target detection accuracy due to the blurring of details in underwater optical images and the occlusion of underwater organisms, an underwater tar- get detection algorithm based on fine-grained feature perception is proposed. The algorithm is based on the YOLO (You Only Look Once) v7 network structure, which firstly proposes the ELSA (ELAN-SimAM) module to enhance the feature perception of the backbone network on the blurred details of the underwater image. Secondly, it proposes the Multi-gradient Ag- gregation Structure (MAS) to realize the efficient fusion of the feature information across multiple gradients, and embeds a lightweight Triplet Attention mechanism to enable cross-di- mensional interactive fusion of features and reduce the leakage detection problem caused by underwater biological occlusion. The experimental results show that the proposed algorithm is suitable for target detection under the underwater complex environment, and can realize target localization and detection in a short time with high detection accuracy. [ABSTRACT FROM AUTHOR]

Fire has emerged as a major danger to the Earth’s ecological equilibrium and human well-being. Fire detection and alert systems are essential. There is a scarcity of public fire datasets with examples of fire and smoke in real-world situations. Moreover, techniques for recognizing items in fire smoke are imprecise and unreliable when it comes to identifying small objects. We developed a dual dataset to evaluate the model’s ability to handle these difficulties. Introducing FS-YOLO, a new fire detection model with improved accuracy. Training YOLOv7 may lead to overfitting because of the large number of parameters and the limited fire detection object categories. YOLOv7 struggles to recognize small dense objects during feature extraction, resulting in missed detections. The Swin Transformer module has been enhanced to decrease local feature interdependence, obtain a wider range of parameters, and handle features at several levels. The improvements strengthen the model’s robustness and the network’s ability to recognize dense tiny objects. The efficient channel attention was incorporated to reduce the occurrence of false fire detections. Localizing the region of interest and extracting meaningful information aids the model in identifying pertinent areas and minimizing false detections. The proposal also considers using fire-smoke and real-fire-smoke datasets. The latter dataset simulates real-world conditions with occlusions, lens blur, and motion blur. This dataset tests the model’s robustness and adaptability in complex situations. On both datasets, the mAP of FS-YOLO is improved by 6.4 % and 5.4 % compared to YOLOv7. In the robustness check experiments, the mAP of FS-YOLO is 4.1 % and 3.1 % higher than that of today’s SOTA models YOLOv8s, DINO. [ABSTRACT FROM AUTHOR]

To enhance the quality of defect detection for Printed Circuit Board Assembly (PCBA) during electronic product manufacturing, this study primarily focuses on optimizing the YOLOv7-based method for PCBA defect detection. In this method, the Mish, a smoother function, replaces the Leaky ReLU activation function of YOLOv7, effectively expanding the network's information processing capabilities. Concurrently, a Squeeze-and-Excitation attention mechanism (SEAM) has been integrated into the head of the model, significantly augmenting the precision of small target defect detection. Additionally, considering angular loss, compared to the CIoU loss function in YOLOv7, the SIoU loss function in the paper enhances robustness and training speed and optimizes inference accuracy. In terms of data preprocessing, this study has devised a brightness adjustment data enhancement technique based on split-filtering to enrich the dataset while minimizing the impact of noise and lighting on images. The experimental results under identical training conditions demonstrate that our model exhibits a 9.9% increase in mAP value and an FPS increase to 164 compared to the YOLOv7. These indicate that the method proposed has a superior performance in PCBA defect detection and has a specific application value. [ABSTRACT FROM AUTHOR]

Enhancing security is currently a paramount concern for society, as traditional surveillance methods necessitate constant vigilance and monitoring of cameras, which can be inadequate. To address this issue, developing an automated security system capable of real-time detection of abnormal human activities and taking appropriate actions is imperative. This paper introduces a novel approach for classifying human actions in controlled environments by combining a support vector machine (SVM) with the deep learning model You Only Look Once (YOLOv7). The YOLOv7 model calculates the boundaries of detected targets, which are then input into the SVM to enhance classification accuracy. The results demonstrate superior classification performance compared to alternative models. In practical terms, the proposed method achieves a testing accuracy 94.24% in classifying human activities based on real-world data. This approach offers promise for preemptively identifying abnormal actions before they occur, paving the way for further advancements in security methods. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Hebei University of Science & Technology is the property of Hebei University of Science & Technology, Journal of Hebei University of Science & Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)