Search

Accurate detection of foreign objects during industrial coal preparation is crucial to ensuring the safety of equipment and personnel, as well as maintaining the green utilization of the coal product. The complexity of industrial coal preparation environments presents challenges for vision-based foreign object detection. This work introduces the SHA-DH-YOLOX algorithm, designed to enhance detection accuracy. The proposed algorithm boosts three notable improvements. First, the Shuffle Attention mechanism (SHA) is integrated into the YOLOX backbone to strengthen the feature extraction of essential information from input images. Second, the Dynamic head (Dyhead) is introduced into the feature fusion to enhance the detector’s representation capability, improving scale-, spatial-, and task-awareness. Third, the original Intersection over Union (IoU) loss function is replaced with SCYLLA-IoU (SIoU) to achieve more accurate bounding boxes and enhanced training stability. These improvements work collaboratively with YOLOX-M, resulting in it outperforming state-of-the-art baseline models, including YOLOv5, YOLOv6, YOLOv7, YOLOv8, and original YOLOX. The developed SHA-DH-YOLOX algorithm improves AP50 by 1.87 to 7.97% compared to baseline models of equivalent size. Robustness tests further affirm the stability of the SHA-DH-YOLOX model when facing diverse and challenging scenarios. This pioneering work provides valuable tools for achieving safe and reliable coal preparation practices. [ABSTRACT FROM AUTHOR]

Traffic sign assisted recognition technology is becoming more and more important in the automatic driving system. Due to the different bearing capacity of different hardware equipment, it has become one of the research directions of various units and enterprises to make the model lighter while the performance is unchanged or better. In order to make the model lighter and improve the model recognition effect and detection speed, a lightweight traffic sign detection method based on SWimAM (a simple, parameter-free attention module add weight part for convolutional neural networks) designed YOLOv5 (you only look once version 5) was proposed. This method added iterable learning weights based on SimAM mechanism and changes the calculation method of internal weights. SWimAM module was proposed and C3 layer of YOLOv5 backbone structure was replaced with this module. The head part was fused with SE (squeeze-and-excitation networks) attention mechanism and the loss function was replaced by SIoU (soft intersection over union) to enhance the detection accuracy of the model and reduce the instability of the gradient. A data enhancement method of filtering Mosaic images was proposed to solve the non-uniformity of partial labels. On the final TT100K traffic sign data set, the recognition mean average precision of the improved YOLOv5s network increase by 2. 5%, calculation speed increased by 7. 33%, computational complexity decreased by 3. 07%, and the number of references decreased by 9. 27% . The mean average precision of Chinese traffic sign detection data set CCTSDB and German traffic sign detection data set GTSDB reached 94. 9% and 94. 7%, respectively, which verified that the model has good generalization. [ABSTRACT FROM AUTHOR]

Pest infestations in tea gardens are one of the common issues encountered during tea cultivation. This study introduces an improved YOLOv8 network model for the detection of tea pests to facilitate the rapid and accurate identification of early-stage micro-pests, addressing challenges such as small datasets and the difficulty of extracting phenotypic features of target pests in tea pest detection. Based on the original YOLOv8 network framework, this study adopts the SIoU optimized loss function to enhance the model's learning ability for pest samples. AKConv is introduced to replace certain network structures, enhancing feature extraction capabilities and reducing the number of model parameters. Vision Transformer with Bi-Level Routing Attention is embedded to provide the model with a more flexible computation allocation and improve its ability to capture target position information. Experimental results show that the improved YOLOv8 network achieves a detection accuracy of 98.16% for tea pest detection, which is a 2.62% improvement over the original YOLOv8 network. Compared with the YOLOv10, YOLOv9, YOLOv7, Faster RCNN, and SSD models, the improved YOLOv8 network has increased the mAP value by 3.12%, 4.34%, 5.44%, 16.54%, and 11.29%, respectively, enabling fast and accurate identification of early-stage micro pests in tea gardens. This study proposes an improved YOLOv8 network model based on deep learning for the detection of micro-pests in tea, providing a viable research method and significant reference for addressing the identification of micro-pests in tea. It offers an effective pathway for the high-quality development of Yunnan's ecological tea industry and ensures the healthy growth of the tea industry. [ABSTRACT FROM AUTHOR]

ObjectiveIt is vital to detect and track ships during coastal monitoring and ship navigation over long distances in complex circumstances. However, due to their small size and unclear features, they can be readily confused with shorelines, noise, and rocks, making them sometimes difficult to spot immediately. To address this issue, a novel ship detection method called ShipDet is proposed which significantly improves performance through the design of a dedicated backbone network, improved feature extraction process, and constrained microscopic detection heads. MethodFirst, this method constructs a feature fusion and extraction network that is highly sensitive to small objects by integrating the Swin Transformer module (STR) with the classic CSPDarknet53 network. This enhances the correlation between small target features and the environment, establishing associations between ships and waterways, ships and other ships, and ships and coastlines, while suppressing irrelevant information. Subsequently, considering the uneven distribution and minor scale variations of ship targets in the dataset, two detection layers are retained to reduce model parameters and further enhance model performance. Moreover, the method employs the SCYLLA-IoU (SIoU) loss function to constrain the detection heads, thereby reducing regression freedom and improving detection accuracy and robustness. ResultsTo validate the proposed method, a dataset called 2023ships is established which consists of up to 9 000 samples covering various scenarios such as inland rivers, coastal areas, daytime, nighttime, and foggy weather. During testing, the proposed method demonstrates superior overall ship detection performance compared to other algorithms, with a mAP of 92.9%, a precision rate of 92.1%, and a parameter size of 35 366 310. ConclusionThe proposed method can greatly benefit the fields of maritime monitoring and intelligent navigation.

This study proposes FLSTrack, an end-to-end multi-object tracking algorithm that integrates Focused Linear Attention with dual decoders. The algorithm aims to address the limitations of current multi-object tracking methods, including poor performance in complex scenarios, inadequate data association, and high computational complexity. Initially, the SwinTransformer is paired with a Focused Linear Attention module to enhance the network’s ability to extract both local and global information, thereby reducing computational costs. Subsequently, a dual-branch decoder based on window attention is developed, with one branch dedicated to tracking and the other to detecting targets in image frames. To further enhance the algorithm’s speed, the complex feature re-identification (ReID) network is replaced with the BYTE data association method. To compensate for the loss of feature appearance resulting from omitting the ReID network, the SIoU loss function is introduced, significantly improving target localization accuracy. The experimental results of FLSTrack on the MOT17, MOT20, DanceTrack, and KITTI datasets show superior performance. Moreover, with an inference speed nearing 30 FPS, the algorithm achieves an optimal balance between tracking accuracy and real-time performance. [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.)

To address the issues of decreased detection accuracy, false detections, and missed detections caused by scale differences between near and distant targets and environmental factors (such as lighting and water waves) in surface target detection tasks for uncrewed vessels, the YOLOv8-MSS algorithm is proposed to be used to optimize the detection of water surface targets. By adding a small target detection head, the model becomes more sensitive and accurate in recognizing small targets. To reduce noise interference caused by complex water surface environments during the downsampling process in the backbone network, C2f_MLCA is used to enhance the robustness and stability of the model. The lightweight model SENetV2 is employed in the neck component to improve the model's performance in detecting small targets and its anti-interference capability. The SIoU loss function enhances detection accuracy and bounding box regression precision through shape awareness and geometric information integration. Experiments on the publicly available dataset FloW-Img show that the improved algorithm achieves an mAP@0.5 of 87.9% and an mAP@0.5:0.95 of 47.6%, which are improvements of 5% and 2.6%, respectively, compared to the original model. [ABSTRACT FROM AUTHOR]

In response to the problems of complex model networks, low detection accuracy, and the detection of small targets prone to false detections and omissions in pedestrian detection, this paper proposes FedsNet, a pedestrian detection network based on RT-DETR. By constructing a new lightweight backbone network, ResFastNet, the number of parameters and computation of the model are reduced to accelerate the detection speed of pedestrian detection. Integrating the Efficient Multi-scale Attention(EMA) mechanism with the backbone network creates a new ResBlock module for improved detection of small targets. The more effective DySample has been adopted as the upsampling operator to improve the accuracy and robustness of pedestrian detection. SIoU is used as the loss function to improve the accuracy of pedestrian recognition and speed up model convergence. Experimental evaluations conducted on a self-built pedestrian detection dataset demonstrate that the average accuracy value of the FedsNet model is 91 % , which is a 1.7 % improvement over the RT-DETR model. The parameters and model volume are reduced by 15.1 % and 14.5 % , respectively. When tested on the public dataset WiderPerson, FedsNet achieved the average accuracy value of 71.3 % , an improvement of 1.1 % over the original model. In addition, the detection speed of the FedsNet network reaches 109.5 FPS and 100.3 FPS, respectively, meeting the real-time requirements of pedestrian detection. [ABSTRACT FROM AUTHOR]

An improved forest fire detection algorithm based on the You Only Look Once v7 (YOLOv7) is proposed in this paper to address the poor accuracy and speed of traditional forest fire detection. In order to guide this model to better focus on the features of forest smoke and fire, this paper introduces the Convolutional Block Attention Module (CBAM) channel attention mechanism and spatial attention mechanism in the backbone network and the head of the YOLOv7 model. It uses the SCYLLA-IoU (SIoU) loss function to replace the Complete-IoU (CIoU) loss function in order to improve the regression accuracy and convergence speed. Experiments show that the improved YOLOv7 algorithm achieves 78.8%, 65.4%, and 70.8% accuracy, recall, and average accuracy, respectively. Compared with the original algorithm, the accuracy, recall, and average accuracy are improved by 4.7%, 1.6% and 5.3%. The algorithm reduces missed detections, improves the accuracy and practicality of forest fire detection, and has good robustness in different complex scenarios. [ABSTRACT FROM AUTHOR]

In aerial image detection, difficulties in feature extraction and low detection accuracy arise due to background interference, occlusion, and the presence of multiple small objects. This paper proposes a DM-YOLOX aerial object target detection method with intensive attention mechanism. Firstly, the proposed approach incorporates coordinate attention (CA) and a dense connection method into the backbone network architecture, enabling adaptive channel weighting throughout the feature extraction process. This facilitates the enhancement of significant features while suppressing less relevant ones, thereby augmenting the network's capacity to represent object features and ensuring retention and reinforcement of key features. Secondly, the multibranch extraction module (MBE) is incorporated into the feature fusion network to enhance the network's ability in extracting multi-scale feature information from images with extensive coverage, thereby enhancing the detection accuracy and efficiency of small- and medium-sized objects in complex scenes. Finally, the utilization of SIoU instead of IoU as the bounding box loss function effectively addresses the issue of mismatch between real and predicted boxes, leading to accelerated network convergence and improved performance during model training. After training and testing on the VisDrone 2019 dataset, this method effectively detects small objects in complex environments. The DM-YOLOX model shows a significant improvement of 2.7% in mAP compared to the baseline network, while achieving an 8% increase in frames per second (FPS). [ABSTRACT FROM AUTHOR]

Target detection, as a core issue in the field of computer vision, is widely applied in many key areas such as face recognition, license plate recognition, security protection, and driverless driving. Although its detection speed and accuracy continue to break records, there are still many challenges and difficulties in target detection of remote sensing images, which require further in-depth research and exploration. Remote sensing images can be regarded as a "three-dimensional data cube", with more complex background information, dense and small object targets, and more severe weather interference factors. These factors lead to large positioning errors and low detection accuracy in the target detection process of remote sensing images. An improved YOLOv7 object detection model is proposed to address the problem of high false negative rate for dense and small objects in remote sensing images. Firstly, the GAM attention mechanism is introduced, and a global scheduling mechanism is proposed to improve the performance of deep neural networks by reducing information reduction and expanding global interaction representations, thus enhancing the network's sensitivity to targets. Secondly, the loss function CIoU in the original Yolov7 network model is replaced by SIoU, aiming to optimize the loss function, reduce losses, and improve the generalization of the network. Finally, the model is tested on the public available RSOD remote sensing dataset, and its generalization is verified on the Okahublot FloW-Img sub-dataset. The results showed that the accuracy (MAP@0.5) of detecting objects improved by 1.7 percentage points and 1.5 percentage points respectively for the improved Yolov7 network model compared to the original model, effectively improves the accuracy of detecting small targets in remote sensing images and solves the problem of leakage detection of small targets in remote sensing images. [ABSTRACT FROM AUTHOR]

Rose tea is a type of flower tea in China's reprocessed tea category, which is divided into seven grades, including super flower, primary flower, flower bud, flower heart, yellow flower, scattered flower, and waste flower. Grading rose tea into distinct quality levels is a practice that is essential to boosting their competitive advantage. Manual grading is inefficient. We provide a lightweight model to advance rose tea grading automation. Firstly, four kinds of attention mechanisms were introduced into the backbone and compared. According to the experimental results, the Convolutional Block Attention Module (CBAM) was chosen in the end due to its ultimate capacity to enhance the overall detection performance of the model. Second, the lightweight module C2fGhost was utilized to change the original C2f module in the neck to lighten the network while maintaining detection performance. Finally, we used the SIoU loss in place of the CIoU loss to improve the boundary regression performance of the model. The results showed that the mAP, precision (P), recall (R), FPS, GFLOPs, and Params values of the proposed model were 86.16%, 89.77%, 83.01%, 166.58, 7.978, and 2.746 M, respectively. Compared with the original model, the mAP, P, and R values increased by 0.67%, 0.73%, and 0.64%, the GFLOPs and Params decreased by 0.88 and 0.411 M, respectively, and the speed was comparable. The model proposed in this study also performed better than other advanced detection models. It provides theoretical research and technical support for the intelligent grading of roses. [ABSTRACT FROM AUTHOR]

Surface defect inspection of metal components plays a critical role in ensuring product quality, enhancing production efficiency, and reducing costs, with particular emphasis on the detection of small-sized surface defects to ensure the safety and reliability of metal components during their usage. Existing detection methods for small size defects on the surfaces of metal components have some shortcomings, such as low precision and poor real-time performance. To solve these two problems, this paper proposes a real-time defect detection method based on improved YOLO. Firstly, the LSandGlass (LSG) module is used to replace the residual module in the backbone network, which reduces information loss, eliminates the low-resolution feature layer, and minimizes semantic loss. The network then uses a lightweight Ghost convolution at the neck to extract the network features. In addition, the convolutional block attention mechanism (CBAM) module is added to improve the detection precision of small-size defects. Finally, soft intersection over union (SIoU) is used to further enhance target detection capability. The experiment was carried out a self-made hexagonal bolt data set of typical commonly used metal components. The experimental results show that compared to the original YOLOv5, the mAP (0.5) is improved by 5.7% to 95.50%, and the reasoning FPS is improved by 21 fps to 95 fps. These results indicate that the proposed LCG-YOLO improves the real-time detection performance of metal component surface defects.

Pest infestations in tea gardens are one of the common issues encountered during tea cultivation. This study introduces an improved YOLOv8 network model for the detection of tea pests to facilitate the rapid and accurate identification of early-stage micro-pests, addressing challenges such as small datasets and the difficulty of extracting phenotypic features of target pests in tea pest detection. Based on the original YOLOv8 network framework, this study adopts the SIoU optimized loss function to enhance the model’s learning ability for pest samples. AKConv is introduced to replace certain network structures, enhancing feature extraction capabilities and reducing the number of model parameters. Vision Transformer with Bi-Level Routing Attention is embedded to provide the model with a more flexible computation allocation and improve its ability to capture target position information. Experimental results show that the improved YOLOv8 network achieves a detection accuracy of 98.16% for tea pest detection, which is a 2.62% improvement over the original YOLOv8 network. Compared with the YOLOv10, YOLOv9, YOLOv7, Faster RCNN, and SSD models, the improved YOLOv8 network has increased the mAP value by 3.12%, 4.34%, 5.44%, 16.54%, and 11.29%, respectively, enabling fast and accurate identification of early-stage micro pests in tea gardens. This study proposes an improved YOLOv8 network model based on deep learning for the detection of micro-pests in tea, providing a viable research method and significant reference for addressing the identification of micro-pests in tea. It offers an effective pathway for the high-quality development of Yunnan’s ecological tea industry and ensures the healthy growth of the tea industry.

An algorithm model based on computer vision is one of the critical technologies that are imperative for agriculture and forestry planting. In this paper, a vision algorithm model based on StyleGAN and improved YOLOv5s is proposed to detect sandalwood trees from unmanned aerial vehicle remote sensing data, and this model has excellent adaptability to complex environments. To enhance feature expression ability, a CA (coordinate attention) module with dimensional information is introduced, which can both capture target channel information and keep correlation information between long-range pixels. To improve the training speed and test accuracy, SIOU (structural similarity intersection over union) is proposed to replace the traditional loss function, whose direction matching degree between the prediction box and the real box is fully considered. To achieve the generalization ability of the model, StyleGAN is introduced to augment the remote sensing data of sandalwood trees and to improve the sample balance of different flight heights. The experimental results show that the average accuracy of sandalwood tree detection increased from 93% to 95.2% through YOLOv5s model improvement; then, on that basis, the accuracy increased by another 0.4% via data generation from the StyleGAN algorithm model, finally reaching 95.6%. Compared with the mainstream lightweight models YOLOv5-mobilenet, YOLOv5-ghost, YOLOXs, and YOLOv4-tiny, the accuracy of this method is 2.3%, 2.9%, 3.6%, and 6.6% higher, respectively. The size of the training sandalwood tree model is 14.5 Mb, and the detection time is 17.6 ms. Thus, the algorithm demonstrates the advantages of having high detection accuracy, a compact model size, and a rapid processing speed, making it suitable for integration into edge computing devices for on-site real-time monitoring. [ABSTRACT FROM AUTHOR]

In view of the problems such as missing detection and false detection in the reading detection of the pointer water meter with uneven illumination and atomized water meter dial, a reading detection method of the pointer water meter based on the improved YOLOv5s was proposed. Firstly, data augmentation methods such as Mosaic and Mixup were used to improve the generalization ability of the model. Secondly, the introduction of the bilateral feature pyramid network (BiFPN) module enabled higher-level feature fusion, enabling the full fusion of deep and shallow feature maps of water meter images, thereby improving the network's expressive power. Then, the convolutional block attention module (CBAM) was embedded to enhance the sub dial indication features of the pointer water meter in both channel and spatial dimensions. Finally, the complete intersection over union loss (CIoU Loss) function was replace with SIoU_ Loss (scylla intersection over union loss) to improve the regression accuracy of bounding boxes. Improved algorithm mAP@ 0. 5 reached 97. 8%, an improvement of 3. 2% compared to the YOLOv5s original network. The experimental results show that this algorithm can effectively improve the reading detection accuracy of pointer water meters. [ABSTRACT FROM AUTHOR]

Computer vision methods for non-contact detection of herd pigs could help detect early disease and reduce mortality rates by analyzing pig behavior. Due to the limitation of breeding space and cost, the unit breeding area is relatively dense, making it difficult to detect all pigs for a long time without interruption. In order to improve the detection performance, this paper proposes an end-to-end efficient and accurate herd pig detection framework based on YOLOv7 target detection model, which is named Ghost-YOLOv7-SIoU. In this framework, the feature extraction backbone network consists of a series of directly connected efficient layer aggregation networks (ELAN) and downsampling modules. The neck network contains a feature pyramid network and path aggregation network. Ghost convolution is adopted to replace the 3 × 3 standard convolution of the ELAN module in backbone network and the scaled-up ELAN module in neck network to obtain rich features while reducing the parameter number and computational effort. Furthermore, to speed up the model convergence and improve the model robustness and accuracy, SIoU loss is used for bounding box regression in the training stage. On the VOC2012 dataset, the number of parameters and floating-point operations decreased by 13.4% and 15.7% compared to YOLOv7, with comparable detection accuracy. Additionally, the number of parameters and floating-point operations decreased by 13.7% and 16.1% on our pig dataset. Ghost-YOLOv7-SIoU is superior to YOLOV4-CSP and YOLOR-CSP in accuracy. Experimental results demonstrate the effectiveness of the proposed method in improving the efficiency of model detection while ensuring detection accuracy. [ABSTRACT FROM AUTHOR]

This paper proposes a YOLO fire detection algorithm based on an attention-enhanced ghost mode, mixed convolutional pyramids, and flame-centre detection (AEGG-FD). Specifically, the enhanced ghost bottleneck is stacked to reduce redundant feature mapping operations in the process for achieving lightweight reconfiguration of the backbone, while attention is added to compensate for accuracy loss. Furthermore, a feature pyramid built using mixed convolution is introduced to accelerate network inference speed. Finally, the local information is extracted by the designed flame-centre detection (FD) module for furnishing auxiliary information in effective firefighting. Experimental results on both the benchmark fire dataset and the video dataset show that the AEGG-FD performs better than the classical YOLO-based models such as YOLOv5, YOLOv7 and YOLOv8. Specifically, both the mean accuracy (mAP0.5, reaching 84.7%) and the inferred speed (FPS) are improved by 6.5 and 8.4 respectively, and both the number of model parameters and model size are compressed to 72.4% and 44.6% those of YOLOv5, respectively. Therefore, AEGG-FD achieves an effective balance between model weight, detection speed, and accuracy in firefighting. [ABSTRACT FROM AUTHOR]

With the rapid advancement of artificial intelligence technologies, drone aerial photography has gradually become the mainstream method for defect detection of transmission line insulators. To address the issues of slow recognition speed and low accuracy in existing detection methods, this paper proposes an insulator defect detection algorithm based on an improved YOLOv8s model. Initially, a multi-scale large-kernel attention (MLKA) module is introduced to enhance the model’s focus on features of different scales as well as low-level feature maps. In addition, by employing lightweight GSConv convolution and constructing the GSC_C2f module, the computational process is simplified and memory burden is reduced, thereby effectively improving the performance of insulator defect detection. Finally, an improved loss function using SIoU is adopted to optimize the model’s detection performance and enhance its feature extraction capability for insulator defects. Experimental results demonstrate that the improved model exhibits excellent performance in drone aerial photography for insulator defect detection, achieving an mAP of 99.22% and an FPS of 55.73 frames per second. Compared to the original YOLOv8s and YOLOv5s, the improved model’s mAP increased by 2.18% and 2.91%, respectively, and the model size is only 30.18 MB, meeting the requirements for real-time operation and accuracy. [ABSTRACT FROM AUTHOR]

Accurate identification of ship targets is the key technology of intelligent inland waterway navigation. Given the complicated navigation environment of inland waterway ships and model detection's low accuracy and efficiency, this paper proposes an enhanced detection algorithm MGS-YOLO based on YOLOv5s. Firstly, the original backbone network is replaced by the MobileNetv3 algorithm, and the improved network parameter is only 7.54 MB. Secondly, the Gated Convolution (GnConv) structure is introduced into the original feature fusion module, which effectively improves the spatial interaction ability of feature information at different levels and further reduced the computational complexity of the model. Finally, to further improve the training speed and reasoning accuracy of the model, the SCYLLA-IoU (SIoU) is introduced into MGS-YOLO to effectively solve the problem of mismatching in the direction between the real box and the regression box. The final results show that the mean Average Precision (mAP), F1, and Average Frames Per Second (AVGFPS) of MGS-YOLO reach 0.977, 0.95, and 95.24 on the established ship dataset. It means that MGS-YOLO does not lose prediction accuracy when reducing network parameters and it has certain real-time performance. Comparing with the current representative lightweight learning models YOLOv5s, YOLOv3-tiny, YOLOv4-tiny, and YOLOv7 with good performance, the MGS-YOLO model has higher detection accuracy and efficiency and provides certain technical support for the safety detection and management of inland ships. [ABSTRACT FROM AUTHOR]

Apple leaf diseases significantly threaten the yield and quality of apples. In order to detect apple leaf diseases in a timely and accurate manner, this study proposed a detection method for apple leaf diseases based on an improved YOLOv7 model. The method integrated a Similarity-based Attention Mechanism (SimAM) into the traditional YOLOv7 model. Additionally, the regression loss function is modified from Complete Intersection over Union (CIoU) to Structured Intersection over Union (SIoU). Experimental results demonstrates that the improved model exhibits an overall recognition precision of 92%, a recall rate of 99%, and a mean average precision (mAP) of 96.1%. These metrics show a respective improvement of 14.4%, 38.85%, and 18.69% compared to the pre-improved YOLOv7. When compared with seven other target detection models in comparative experiments, the improved YOLOv7 model achieves higher accuracy, lower rates of missed and false detections in disease target detection. The model excels in detecting disease categories in complex environments and identifying small targets at early disease stages. It can provide technical support for effective detection of apple leaf diseases. [ABSTRACT FROM AUTHOR]

By detecting the position of maintenance components in real-time, maintenance guidance information can be superimposed and important operational guidance can be provided for maintenance personnel. The YOLOv5- OBB-CR real-time detection algorithm is proposed for maintenance component with orientation bounding box based on improved YOLOv5-OBB. The C3 module in the original network is improved to CReToNeXt, which can more effectively enhance the network's ability to learn image features. Considering that the network learning is the labeled rotation box information, the original Loss function CIoU is improved to SIoU with angle loss information, and the improved Loss function can more effectively describe the regression of the target box. The demonstration shows that the mAP@.5 0.95 of YOLOv5-OBB-CR-s (SIoU) is 85.6%, which is 6.7% higher than the original YOLOv5 OBB algorithm. [ABSTRACT FROM AUTHOR]

Accurate ship object detection ensures navigation safety and effective maritime traffic management. Existing ship target detection models often have the problem of missed detection in complex marine environments, and it is hard to achieve high accuracy and real-time performance simultaneously. To address these issues, this paper proposes a lightweight ship object detection model called YOLOv7-Ship to perform end-to-end ship detection in complex marine environments. At first, we insert the improved "coordinate attention mechanism" (CA-M) in the backbone of the YOLOv7-Tiny model at the appropriate location. Then, the feature extraction capability of the convolution module is enhanced by embedding omnidimensional dynamic convolution (ODconv) into the efficient layer aggregation network (ELAN). Furthermore, content-aware feature reorganization (CARAFE) and SIoU are introduced into the model to improve its convergence speed and detection precision for small targets. Finally, to handle the scarcity of ship data in complex marine environments, we build the ship dataset, which contains 5100 real ship images. Experimental results show that, compared with the baseline YOLOv7-Tiny model, YOLOv7-Ship improves the mean average precision (mAP) by 2.2% on the self-built dataset. The model also has a lightweight feature with a detection speed of 75 frames per second, which can meet the need for real-time detection in complex marine environments to a certain extent, highlighting its advantages for the safety of maritime navigation. [ABSTRACT FROM AUTHOR]

Copyright of Cyber Security & Data Governance is the property of Editorial Office of Information Technology & Network Security 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 Guangxi Normal University - Natural Science Edition is the property of Gai Kan Bian Wei Hui 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.)

Due to complex environmental factors such as uneven illumination and high noise, unmanned electric locomotives in coal mines have low accuracy in multi object detection and difficulty in recognizing small objects. In order to solve the above problems, a multi object detection model for underground unmanned electric locomotives in coal mines based on SD-YOLOv5s-4L is proposed. On the basis of YOLOv5s, the following improvements are made to construct the SD-YOLOv5s-4L network model. The model introduces the SIoU loss function to solve the problem of mismatch between the direction of the real box and the predicted box, so that the model can better learn the position information of the object. The model introduces decoupled heads at the head of YOLOv5s to enhance the feature fusion and positioning accuracy of the network model. It enables the model to quickly capture multi-scale features of the object. The model introduces a small object detection layer to increase the original three scale detection layer to four scale. It enhances the model's feature extraction capability and detection precision for small objects. The experiment is conducted on a multi object detection dataset of the mine electric locomotives. The results show the following points. The mean average precision (mAP) of the SD-YOLOv5s-4L network model for various types of objects is 97.9%, and the average precision (AP) for small objects is 98.9%. Compared with the YOLOv5s network model, it improves by 5.2% and 9.8%, respectively. Compared with other network models such as YOLOv7 and YOLOv8, the SD-YOLOv5s-4L network model has the best comprehensive detection performance and can provide technical support for achieving unmanned driving of the mine electric locomotives.

To address the issues of decreased detection accuracy, false detections, and missed detections caused by scale differences between near and distant targets and environmental factors (such as lighting and water waves) in surface target detection tasks for uncrewed vessels, the YOLOv8-MSS algorithm is proposed to be used to optimize the detection of water surface targets. By adding a small target detection head, the model becomes more sensitive and accurate in recognizing small targets. To reduce noise interference caused by complex water surface environments during the downsampling process in the backbone network, C2f_MLCA is used to enhance the robustness and stability of the model. The lightweight model SENetV2 is employed in the neck component to improve the model’s performance in detecting small targets and its anti-interference capability. The SIoU loss function enhances detection accuracy and bounding box regression precision through shape awareness and geometric information integration. Experiments on the publicly available dataset FloW-Img show that the improved algorithm achieves an mAP@0.5 of 87.9% and an mAP@0.5:0.95 of 47.6%, which are improvements of 5% and 2.6%, respectively, compared to the original model.

In tobacco production, cigarettes with appearance defects are inevitable and dramatically impact the quality of tobacco products. Currently, available methods do not balance the tension between detection accuracy and speed. To achieve accurate detection on a cigarette production line with the rate of 200 cigarettes per second, we propose a defect detection model for cigarette appearance based on YOLOv5n (You Only Look Once Version 5 Nano), called CJS-YOLOv5n (YOLOv5n with C2F (Cross Stage Partial (CSP) Bottleneck with 2 convolutions-fast), Jump Concat, and SCYLLA-IoU (SIoU)). This model incorporates the C2F module proposed in the state-of-the-art object detection network YOLOv8 (You Only Look Once Version 8). This module optimizes the network by parallelizing additional gradient flow branches, enhancing the model's feature extraction capability and obtaining richer gradient information. Furthermore, this model uses Jump Concat to preserve minor defect feature information during the fusion process in the feature fusion pyramid's P4 layer. Additionally, this model integrates the SIoU localization loss function to improve localization accuracy and detection precision. Experimental results demonstrate that our proposed CJS-YOLOv5n model achieves superior overall performance. It maintains a detection speed of over 500 FPS (frames per second) while increasing the recall rate by 2.3% and mAP (mean average precision)@0.5 by 1.7%. The proposed model is suitable for application in high-speed cigarette production lines.

Introduction: Object detection methods for team ball games players often struggle due to their reliance on dataset scale statistics, resulting in missed detections for players with smaller bounding boxes and reduced accuracy for larger bounding boxes. Methods: This study introduces a two-fold approach to address these challenges. Firstly, a novel multi-scale attention mechanism is proposed, aiming to reduce reliance on scale statistics by utilizing a specially created SIoU (Similar to Intersection over Union) label that explicitly represents multi-scale features. This label guides the training of multi-scale attention network modules at two granularity levels. Secondly, an integrated scale equalization algorithmwithin SIoU labels enhances the detection ability of multi-scale targets in imbalanced samples. Results and discussion: Comparative experiments conducted on basketball, volleyball, and ice hockey datasets validate the proposed method. The relative optimal approach demonstrated improvements in the detection accuracy of players with smaller and larger scale bounding boxes by 11%, 7%, 15%, 8%, 9%, and 4%, respectively. [ABSTRACT FROM AUTHOR]

Traditional methods for detecting surface defects on ceramic tiles result in misdetection and missed detection, which makes it difficult to guarantee product stability and consistency within the same batch. Therefore, this article proposes an improved YOLOv5 algorithm for detecting surface defects on ceramic tiles. Firstly, the Res2Net module is combined with self-attention to fully utilize local and global information and improve the feature extraction effect of defects. Secondly, the GS-BiFPN neck network is designed to enhance the fusion capability of shallow detail and deep semantic information and alleviate ambiguity and redundancy on the feature map. Then, a lightweight attention module is introduced to improve the detection capability of difficult-to-recognize defects and anti-background interference. Finally, the SIoU loss function improves the model's convergence speed and accuracy. Experimental results demonstrate that the improved algorithm's mean average precision (mAP) reaches 73.3%, 6.3% higher than the baseline model. Even when compared with YOLOv7-tiny, the mAP of the improved algorithm has increased by 8.7%. Additionally, the detection speed of the model can reach 92 frames per second, which can meet the requirements of ceramic tile surface defect detection in industrial scenarios. [ABSTRACT FROM AUTHOR]

Object detector performance gains often occur with deeper networks and heavier computational overhead, yet scenarios with constrained calculation and storage demand real-time performance while consuming fewer resources. Existing methods tend to be caught in a tough decision between parameters, computation, speed and accuracy. We propose a lightweight real-time object detector Lite-YOLOv3 from the optimization of YOLOv3. Firstly, sparse pruning of the trained model significantly decreases the parameters and calculations while boosting the speed. Secondly, a channel-wise convolution attention (CWA) mechanism is proposed to enhance the feature extraction capability of the backbone with essentially no extra computational burden. Furthermore, a multi-scale slice depthwise convolution with efficient channel attention (MSD-ECA) is proposed to enhance the receptive field and cross-scale information representation. Finally, SIoU is chosen as the localization loss function to improve the training speed and regression accuracy. For 512 × 512 input, Lite-YOLOv3 achieves 74.1 % mAP at 113 FPS on the PASCAL VOC07+12 dataset and 52.4 % mAP on the MS COCO2017 dataset. The experimental results show that compared with YOLOv3, Lite-YOLOv3 is slightly inferior in accuracy, the parameters and calculations are only 24.8 % and 30.7 % , respectively, the inference speed is 1.7 times faster, which sufficiently proves the effectiveness of the proposed method and is also comparable with other models. [ABSTRACT FROM AUTHOR]

The objects in UAV aerial images have multiple scales, dense distribution, and occlusion, posing considerable challenges for object detection. In order to address this problem, this paper proposes a real-time multi-scale object detection method based on an improved YOLOv7 model (ATS-YOLOv7) for UAV aerial images. First, this paper introduces a feature pyramid network, AF-FPN, which is composed of an adaptive attention module (AAM) and a feature enhancement module (FEM). AF-FPN reduces the loss of deep feature information due to the reduction of feature channels in the convolution process through the AAM and FEM, strengthens the feature perception ability, and improves the detection speed and accuracy for multi-scale objects. Second, we add a prediction head based on a transformer encoder block on the basis of the three-head structure of YOLOv7, improving the ability of the model to capture global information and feature expression, thus achieving efficient detection of objects with tiny scales and dense occlusion. Moreover, as the location loss function of YOLOv7, CIoU (complete intersection over union), cannot facilitate the regression of the prediction box angle to the ground truth box—resulting in a slow convergence rate during model training—this paper proposes a loss function with angle regression, SIoU (soft intersection over union), in order to accelerate the convergence rate during model training. Finally, a series of comparative experiments are carried out on the DIOR dataset. The results indicate that ATS-YOLOv7 has the best detection accuracy (mAP of 87%) and meets the real-time requirements of image processing (detection speed of 94.2 FPS). [ABSTRACT FROM AUTHOR]

The rising issue of an aging population has intensified the focus on the health concerns of the elderly. Among these concerns, falls have emerged as a predominant health threat for this demographic. The YOLOv5 family represents the forefront of techniques for human fall detection. However, this algorithm, although advanced, grapples with issues such as computational demands, challenges in hardware integration, and vulnerability to occlusions in the designated target group. To address these limitations, we introduce a pioneering lightweight approach named CGNS-YOLO for human fall detection. Our method incorporates both the GSConv module and the GDCN module to reconfigure the neck network of YOLOv5s. The objective behind this modification is to diminish the model size, curtail floating-point computations during feature channel fusion, and bolster feature extraction efficacy, thereby enhancing hardware adaptability. We also integrate a normalization-based attention module (NAM) into the framework, which concentrates on salient fall-related data and deemphasizes less pertinent information. This strategic refinement augments the algorithm's precision. By embedding the SCYLLA Intersection over Union (SIoU) loss function, our model benefits from faster convergence and heightened detection precision. We evaluated our model using the Multicam dataset and the Le2i Fall Detection dataset. Our findings indicate a 1.2% enhancement in detection accuracy compared with the conventional YOLOv5s framework. Notably, our model realized a 20.3% decrease in parameter tally and a 29.6% drop in floating-point operations. A comprehensive instance analysis and comparative assessments underscore the method's superiority and efficacy. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Mine Automation is the property of Industry & Mine Automation Editorial Department 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.)

The use of Internet of Things (IoT) technology for real-time monitoring of agricultural pests is an unavoidable trend in the future of intelligent agriculture. This paper aims to address the difficulties in deploying models at the edge of the pest monitoring visual system and the low recognition accuracy. In order to achieve that, a lightweight GCSS-YOLOv5s algorithm is proposed. Firstly, we introduce the lightweight network GhostNet, use the Ghostconv module to replace the traditional convolution, and construct the C3Ghost module based on the CSP structure, drastically reducing the number of model parameters. Secondly, during the feature fusion process, we introduce the content-aware reassembly of features (CARAFE) lightweight up-sampling operator to enhance the feature integration capability of the pests by reducing the impact of redundant features after fusion. Then, we adopt SIoU as the bounding box regression loss function, which enhances the convergence speed and detection accuracy of the model. Finally, the traditional non-maximum suppression (NMS) was improved to Soft-NMS to improve the model's ability to recognize overlapping pests. According to the experimental results, the mean average precision (mAP) of the GCSS-YOLOv5s model reaches 90.5%. This is achieved with a 44% reduction in the number of parameters and a 7.4 G reduction in computation volume compared to the original model. The method significantly reduces the model's resource requirements while maintaining accuracy, which offers a specific theoretical foundation and technological reference for the future field of intelligent monitoring. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Graphics is the property of Journal of Graphics 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.)

Rose tea is a type of flower tea in China’s reprocessed tea category, which is divided into seven grades, including super flower, primary flower, flower bud, flower heart, yellow flower, scattered flower, and waste flower. Grading rose tea into distinct quality levels is a practice that is essential to boosting their competitive advantage. Manual grading is inefficient. We provide a lightweight model to advance rose tea grading automation. Firstly, four kinds of attention mechanisms were introduced into the backbone and compared. According to the experimental results, the Convolutional Block Attention Module (CBAM) was chosen in the end due to its ultimate capacity to enhance the overall detection performance of the model. Second, the lightweight module C2fGhost was utilized to change the original C2f module in the neck to lighten the network while maintaining detection performance. Finally, we used the SIoU loss in place of the CIoU loss to improve the boundary regression performance of the model. The results showed that the mAP, precision (P), recall (R), FPS, GFLOPs, and Params values of the proposed model were 86.16%, 89.77%, 83.01%, 166.58, 7.978, and 2.746 M, respectively. Compared with the original model, the mAP, P, and R values increased by 0.67%, 0.73%, and 0.64%, the GFLOPs and Params decreased by 0.88 and 0.411 M, respectively, and the speed was comparable. The model proposed in this study also performed better than other advanced detection models. It provides theoretical research and technical support for the intelligent grading of roses.

With the advancement of intelligent driving technology, researchers are paying more and more attention to the identification of traffic signs. Although a detection method of traffic signs based on color or shape can achieve recognition of large categories of signs such as prohibitions and warnings, the recognition categories are few, and the accuracy is not high. A traffic sign detection algorithm based on color or shape is small in computation and good in real-time, but the color features are greatly affected by light and weather. For the questions raised above, this paper puts forward an improved YOLOv5 method. The method uses the SIoU loss function to take the place of the loss function in the YOLOv5 model, which optimizes the training model, and the convolutional block attention model (CBAM) is fused with the CSP1_3 model in YOLOv5 to form a new CSP1_3CBAM model, which enhances YOLOv5's feature extraction ability and improves the accuracy regarding traffic signs. In addition, the ACONC is introduced as the activation function of YOLOv5, which promotes YOLOv5's generalization ability through adaptive selection of activation by linear–nonlinear switching factors. The research results on the TT100k dataset show that the improved YOLOv5 precision rate increased from 73.2% to 81.9%, an increase of 8.7%; the recall rate increased from 74.2% to 77.2%, an increase of 3.0%; and the mAP increased from 75.7% to 81.9%, an increase of 6.2%. The FPS also increased from 26.88 to 30.42 frames per second. The same training was carried out on the GTSDB traffic sign dataset, and the mAP increased from 90.2% to 92.5%, which indicates that the algorithm has good generalization ability. [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.)

Copyright of Chinese Journal of Liquid Crystal & Displays is the property of Chinese Journal of Liquid Crystal & Displays 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.)

Introduction: Accurate grading identification of tea buds is a prerequisite for automated tea-picking based on machine vision system. However, current target detection algorithms face challenges in detecting tea bud grades in complex backgrounds. In this paper, an improved YOLOv7 tea bud grading detection algorithm TBC-YOLOv7 is proposed. Methods: The TBC-YOLOv7 algorithm incorporates the transformer architecture design in the natural language processing field, integrating the transformer module based on the contextual information in the feature map into the YOLOv7 algorithm, thereby facilitating self-attention learning and enhancing the connection of global feature information. To fuse feature information at different scales, the TBC-YOLOv7 algorithm employs a bidirectional feature pyramid network. In addition, coordinate attention is embedded into the critical positions of the network to suppress useless background details while paying more attention to the prominent features of tea buds. The SIOU loss function is applied as the bounding box loss function to improve the convergence speed of the network. Result: The results of the experiments indicate that the TBC-YOLOv7 is effective in all grades of samples in the test set. Specifically, the model achieves a precision of 88.2% and 86.9%, with corresponding recall of 81% and 75.9%. The mean average precision of the model reaches 87.5%, 3.4% higher than the original YOLOv7, with average precision values of up to 90% for one bud with one leaf. Furthermore, the F1 score reaches 0.83. The model's performance outperforms the YOLOv7 model in terms of the number of parameters. Finally, the results of the model detection exhibit a high degree of correlation with the actual manual annotation results (R2 =0.89), with the root mean square error of 1.54. Discussion: The TBC-YOLOv7 model proposed in this paper exhibits superior performance in vision recognition, indicating that the improved YOLOv7 model fused with transformer-style module can achieve higher grading accuracy on densely growing tea buds, thereby enables the grade detection of tea buds in practical scenarios, providing solution and technical support for automated collection of tea buds and the judging of grades. [ABSTRACT FROM AUTHOR]

Forest fires pose significant hazards to ecological environments and economic society. The detection of forest fire smoke can provide crucial information for the suppression of early fires. Previous detection models based on deep learning have been limited in detecting small smoke and smoke with smoke-like interference. In this paper, we propose a lightweight model for forest fire smoke detection that is suitable for UAVs. Firstly, a smoke dataset is created from a combination of forest smoke photos obtained through web crawling and enhanced photos generated by using the method of synthesizing smoke. Secondly, the GSELAN and GSSPPFCSPC modules are built based on Ghost Shuffle Convolution (GSConv), which efficiently reduces the number of parameters in the model and accelerates its convergence speed. Next, to address the problem of indistinguishable feature boundaries between clouds and smoke, we integrate coordinate attention (CA) into the YOLO feature extraction network to strengthen the extraction of smoke features and attenuate the background information. Additionally, we use Content-Aware Reassembly of FEatures (CARAFE) upsampling to expand the receptive field in the feature fusion network and fully exploit the semantic information. Finally, we adopt SCYLLA-Intersection over Union (SIoU) loss as a replacement for the original loss function in the prediction phase. This substitution leads to improved convergence efficiency and faster convergence. The experimental results demonstrate that the LMDFS model proposed for smoke detection achieves an accuracy of 80.2% with a 5.9% improvement compared to the baseline and a high number of Frames Per Second (FPS)—63.4. The model also reduces the parameter count by 14% and Giga FLoating-point Operations Per second (GFLOPs) by 6%. These results suggest that the proposed model can achieve a high accuracy while requiring fewer computational resources, making it a promising approach for practical deployment in applications for detecting smoke. [ABSTRACT FROM AUTHOR]

In the process of conveying raw coal to the surface on conveyor belts, the raw coal is generally blended with foreign bodies, such as large pieces of gangue and damaged bolts, which can affect the quality of mined coal, damage the transportation equipment and even jam the coal conduit, seriously reducing the coal conveying efficiency. To handle to the existing problems of underground complex environment, low detection accuracy and poor real-time performance in coal flow foreign bodies detection, we propose an adaptive focused target feature fusion network (AFFNet) based on YOLOX. The multi-transformer parallel (MTRP) module is used to expand the receptive field and fuse the features under different receptive fields with the transformer encoder to enhance the feature extraction ability. The cross stage partial transformer (CSPTR) with transformer encoder module is designed to capture the global context information of the feature maps in the network, and improve the location prediction in the detection. In the feature fusion channel of different scales, the learnable weight parameters are added to learn the spatial weight of feature map fusion adaptively, and the feature expression ability of different scales is optimized. SCYLLA-IoU (SIoU) loss and varifocal loss are used to obtain more accurate bounding boxes and deal with the sample category imbalance problem, respectively. The experimental results show that AFFNet can achieve a detection speed of 48 frame per second (FPS) and a mean average precision (mAP50) of 95.6%, 6.7% higher than YOLOX-s on the dataset of foreign body in coal flow. It can balance both the detection speed and detection accuracy, and can be used to improve the efficiency of detecting foreign bodies in the coal flow. [ABSTRACT FROM AUTHOR]

Ship fires are one of the main factors that endanger the safety of ships; because the ship is far away from land, the fire can be difficult to extinguish and could often cause huge losses. The engine room has many pieces of equipment and is the principal place of fire; however, due to its complex internal environment, it can bring many difficulties to the task of fire detection. The traditional detection methods have their own limitations, but fire detection using deep learning technology has the characteristics of high detection speed and accuracy. In this paper, we improve the YOLOv7-tiny model to enhance its detection performance. Firstly, partial convolution (PConv) and coordinate attention (CA) mechanisms are introduced into the model to improve its detection speed and feature extraction ability. Then, SIoU is used as a loss function to accelerate the model's convergence and improve accuracy. Finally, the experimental results on the dataset of the ship engine room fire made by us shows that the mAP@0.5 of the improved model is increased by 2.6%, and the speed is increased by 10 fps, which can meet the needs of engine room fire detection. [ABSTRACT FROM AUTHOR]

Apple thinning is one of the most important steps in the apple tree management. Mechanical thinning can greatly reduce the labor costs while retaining young apples, according to the experience. Therefore, mechanical thinning instead of manual thinning can be the promising trend in modern orchard management. Target detection before thinning is often required for the automate apple thinning. However, the small baby apples are closely grouped with the background-like hue and texture, leading to the blur imaging under the other apples or leaves in bunches. In this study, an improved YOLOv7 of deep learning network was designed to integrate the Swin Transformer Block suitable for the close-range color small target detection. Firstly, Swin Transformer Block was added into the small target detection layer of YOLOv7 model, in order to retain more small-scale target feature information with the network's accuracy of small targets. Secondly, the loss function CIoU in YOLOv7 was replaced by SIoU to consider the difference between the direction of the prediction box and the real box during training, particularly for the high accuracy of model detection. Finally, the heat map of target detection was produced using the GradCAM approach. Effective feature visualization was also carried out to determine the model's zone of interest. There were two shooting methods (long- and close-range), in terms of image data set production. The image data sets were then divided into the close- and long-range one after labeling. The test results showed that the improved YOLOv7 model was achieved in the mean average precision (mAP) on the close-range dataset of 96.1%, which was 0.7 percentage points greater than that of YOLOv7. The mAP on the long-range image dataset was 93.6%, which was 3.5 percentage points higher than that of YOLOv7. Furthermore, the mAP of improved YOLOv7 was 95.2% on the whole data set, where the detection accuracy was 92.7%, the recall rate was 91.0%, and the memory occupied by the model was 81 MB. The mAP, accuracy, and recall rate were improved by 2.3, 0.9, and 1.3 percentage points, respectively, compared with the YOLOv7 model. The detection heat map of improved YOLOv7 shared the higher thermal value in the apple area, indicating the more effective features after extraction. At the same time, the contribution of Swin Transformer Block's to each target detection layer was evaluated to compare the effects of three detection layers on the ability to detect young apples. Therefore, the addition of the Swin-Transformer Block into the small target detection layer was considerably enhanced the detection performance of improved model. A total of 1.9, 0.3, and 1.6 percentage points were achieved in the mAP, precision, and recall rate, respectively. There was no significantly different performance of the improved model, when the Swin Transformer Block was added into the large, medium, and small detection layers. Once the Swin-Transformer module was just introduced to the small target detection layer, the model memory use increased by 25 MB. In summary, the improved YOLOv7 network can performed the better detection and stronger robustness for apples in the thinning period. The finding can provide the necessary technical support for apple growth monitoring, and mechanical thinning. [ABSTRACT FROM AUTHOR]

Safety helmets are essential in various indoor and outdoor workplaces, such as metallurgical high-temperature operations and high-rise building construction, to avoid injuries and ensure safety in production. However, manual supervision is costly and prone to lack of enforcement and interference from other human factors. Moreover, small target object detection frequently lacks precision. Improving safety helmets based on the helmet detection algorithm can address these issues and is a promising approach. In this study, we proposed a modified version of the YOLOv5s network, a lightweight deep learning-based object identification network model. The proposed model extends the YOLOv5s network model and enhances its performance by recalculating the prediction frames, utilizing the IoU metric for clustering, and modifying the anchor frames with the K-means++ method. The global attention mechanism (GAM) and the convolutional block attention module (CBAM) were added to the YOLOv5s network to improve its backbone and neck networks. By minimizing information feature loss and enhancing the representation of global interactions, these attention processes enhance deep learning neural networks' capacity for feature extraction. Furthermore, the CBAM is integrated into the CSP module to improve target feature extraction while minimizing computation for model operation. In order to significantly increase the efficiency and precision of the prediction box regression, the proposed model additionally makes use of the most recent SIoU (SCYLLA-IoU LOSS) as the bounding box loss function. Based on the improved YOLOv5s model, knowledge distillation technology is leveraged to realize the light weight of the network model, thereby reducing the computational workload of the model and improving the detection speed to meet the needs of real-time monitoring. The experimental results demonstrate that the proposed model outperforms the original YOLOv5s network model in terms of accuracy (Precision), recall rate (Recall), and mean average precision (mAP). The proposed model may more effectively identify helmet use in low-light situations and at a variety of distances. [ABSTRACT FROM AUTHOR]