A vehicle recognition model based on improved yolov5. Nov 1, 2022 · The model recognized nine different types of diseases and pests with an mAP value of 85. Traffic sign recognition and detection is a key technology in automatic vehicle driving and driver assistance systems. An improved algorithm based on YOLOv5-OBB is proposed to reduce the computational effort of the model and increase the speed of model detection. Apr 18, 2023 · The YOLOv5 model has four parts: input, backbone, neck, and prediction. Dec 14, 2023 · Pavement defect detection technology stands as a pivotal component within intelligent driving systems, demanding heightened precision and rapid detection rates. It helps to avoid traffic violations on the road. 5% and 3. Fig. Therefore, this paper Jul 30, 2023 · Step 1 Get the UAV’s bounding boxes. 18 proposed a lightweight YOLOv5 model by introducing the C3Ghost and Ghost modules in its The rapid development of the automobile industry has made life easier for people, but traffic accidents have increased in frequency in recent years, making vehicle safety particularly important. 4% respectively, and the overall number of parameters and computational cost of the model are reduced by 14. Yolov5 Vehicle Detection Model in Fog Based on Channel. In view of the current practical requirements for the recognition accuracy and real-time performance of license plate recognition system in complex scenes, the existing target detection methods and license plate recognition methods are studied, and a car license plate recognition method based on Feb 19, 2023 · When compared to the original YOLOv5 network, the FLOPs in this network model rose by 18. 2% to 77. These algorithms have made substantial contributions to object identification; however, there is one little issue. 0%; and the mAP increased from 75. 2%, an increase of 3. Through extensive model training on the datasets and comparative experiments, significant improvements are achieved in precision (P), recall (R), and mean average precision (mAP). 7% to 81. However, existing traffic sign recognition algorithms suffer from problems such as large model size, complex computation, high computational cost, which make it difficult to achieve an effective balance between detection speed and detection accuracy. The algorithm is based on the YOLOv5 object detection network. In response to this problem, we propose an improved model SN-YOLO based on YOLOv5. The network structure is divided into four parts: Input, Backbone, Neck, and Prediction. In this study, a tomato maturity recognition model, YOLOv5s-tomato, is proposed based on improved YOLOv5 to recognize the four types of different tomato maturity stages: mature green, breaker, pink, and red. 9% Oct 20, 2023 · A YOLO-based deep learning method for pedestrian and vehicle recognition was proposed, where image preprocessing and data enhancement are applied to improve the generalization ability of the model; then the network structure were changed, as well as the multi-scale feature detection map and the PANet structure were applied to improved the recognition ability of different scale targets. These factors Feb 6, 2023 · Consequently, forest fire detection remains a challenging research area. Aug 20, 2022 · The forest fire detection model proposed in this paper is based on YOLOv5s in version 6. The structure of the YOLOv5 model in version 6. Extracted buildings are classified based on their elevation and size. Compared with other mainstream one-stage detection algorithms YOLOv4 and YOLOv7, the improved YOLOv5 model has an average precision higher by 1. Experimental results show that the miss detection rate of the proposed improved model is lower in comparison with the original YOLOv5, and detection precision has been improved. Jul 17, 2023 · Segmented roads are classified based on their width and connectivity. Oct 8, 2023 · Based on the experimental data, we conclude that the proposed TNS-YOLOv5 algorithm achieves better detection performance than the original YOLOv5 model. This method improved the accuracy of the regression box by introducing the GIoU bounding box regression loss function. The proposed YOLOV5-ATE model can effectively Aug 10, 2022 · Based on the original YOLOv5, the Mosaic-8 data are used to enhance and modify the objective equation to improve the convergence accuracy of the model. Nonetheless, due to the constraints of UAV platform, it is difficult to increase accuracy by deepening the network. proposed a deep YOLOV5 network-based behaviour recognition model for sheep in housed scenes, showing that the algorithm can be used in structured settings with a deep learning model in a structured scenario. Sep 27, 2023 · On the new test set of CCTSDB 2021, for small objects, the precision is 88. Jun 13, 2023 · Through experiments, the test results based on the VisDrone dataset showed that GBS-YOLOv5 was 4. Compared with the comparison algorithm, the training accuracy of the yolov5 model integrated with the ECA module is improved 3. 9%, an increase of 8. Full size image. 2% mAP) exceeds SSD (60. The FPS also increased from 26. 2% over the existing YOLOv5 algorithm, mAP@0. Figure 2. this method are improved, re aching 99. Feb 19, 2023 · Our proposed YOLOv5s-. This paper proposes an enhanced version of the YOLOv5l algorithm specifically designed for traffic light recognition. The Oct 20, 2023 · To solve the problem of low accuracy in vehicle pedestrian target detection, this paper proposes a vehicle pedestrian detection method based on the improved YOLOv5 algorithm. 0 \(\%\) and 3. This paper proposed an Jul 28, 2023 · We improve vehicle detection and localization performance by decoupling YOLOv5 prediction and classification tasks. Specifically, the precision value is 94. YOLOv5s network. Jan 22, 2024 · Due to the large computational requirements of object detection algorithms, high-resolution remote sensing vehicle detection always involves numerous small objects, high level of background complexity, and challenges in balancing model accuracy and parameter count. 5 is the average AP for all categories when the IOU is set Jul 28, 2023 · In the field of Intelligent Traffic Systems (ITS), vehicle recognition is a hot research topic. The experimental results are shown in Table 5; compared with other models, the improved YOLOv5s model has the highest mAP. First, in the Input part, the data are processed to increase the accuracy and discrimination of Jul 28, 2023 · The field of remote sensing information processing places significant research emphasis on object detection (OD) in high-spatial-resolution remote sensing images (HSRIs). 10 (a) that the target recognition accuracy of the improved SE-YOLOv5 model after training is higher than that of the Faster R-CNN, the SSD model and the original YOLOv5 model. The OD task in HSRIs poses additional challenges compared to conventional natural images. However, recognition of traffic signs becomes more complicated in bad weather such as lack of light, rain, fog. In order to improve the accuracy and speed of surface defect detection of aero-engine components, a defect detection model based on an improved YOLOv5 algorithm is proposed in this Sep 1, 2022 · The application of license plate recognition technology is becoming more and more extensive. Small target detection has been widely used in applications that are relevant to everyday life and have many real-time Aug 29, 2023 · The research results on the TT100k dataset show that the improved YOLOv5 precision rate increased from 73. The improvements made to the algorithm, including the NAM module, transformer structure, and SIoU loss function, all contribute to the improved performance of helmet detection. 3% May 1, 2022 · Secondly, in order to solve the localization problem in low resolution and multi-vehicle environment, a license plate method based on YOLOv5s was proposed by using deep learning image recognition technology, and data enhancement was introduced to improve YOLOv5s. 2% to 81. However, traditional vehicle detection algorithms often struggle to deal with the vehicle occlusion problem effectively, necessitating the modification of feature map size as vehicle sizes vary. The color recognition algorithms based on deep learning neural networks are studied in this paper. This exhibits that it is unnecessary to use a large amount of training data when the training data and the data In this paper, the network structure is studied based on the YOLOv5 [15] algo-rithm, and the lightweight MobileNetv2 [16] design is used to make it meet the require-ments of micro-arithmetic power and low power consumption in the FLIR infrared vehicle pedestrian target detection dataset task. Step 4: The detection results are generated as output. First, by using the triple attention mechanism to capture interactions across dimensions in the backbone network, the target feature region can be localized Dec 27, 2023 · The detection accuracy was improved to 85. First, SiLU activation function is used to replace the original activation function in Yolov5s backbone network, the number of parameters in the network structure is reduced and the problem of gradient disappearance is solved Mar 7, 2024 · In this paper, we propose an improved YOLOv5 model based on the Swin Transformer block and bi-head and focus on the eld of road defect detection. Aug 7, 2022 · Furthermore, SPPF is added to the neck of the model, and can effectively improve the accuracy of multiple object detection and recognition. The model In this paper, we propose a high-performance, lightweight face mask detector based on YOLOv5[3] and attention mechanism to detect whether people wear masks. 98%. Using the models pruned YOLOv5 detection model to detect the UAVs on the input image, the UAV’s bounding boxes are obtained. Step 3: The trained improved YOLOv5 weight file is subsequently deployed on the vehicle-mounted device to perform real-time crack detection on the road surface. Mar 22, 2022 · Experiments on the coco data set show that the improved yolov5 model based on the ECA module proposed in this paper can be used 68. Li Haoran,Xu Li, Zhang Yin, Fu Xiangyuan. TLDR. 02%, which proves that the ECA module can further Aug 15, 2023 · The improved algorithm achieved a Mean Average Precision (mAP) of 41. Step 2 Find the position corresponding to the bounding boxes in the original images. Vehicle detection technology is of great significance for realizing automatic monitoring and AI-assisted driving systems. Sep 16, 2023 · The reasons are as follows: (1) Our improved YOLOv5 integrates some techniques to increase detection speed, which can ensure that our model has a strong real-time; (2) Focus module is replaced by CBS in the main stem of the improved YOLOv5, which greatly improves the extraction of flame features; (3) SPPF improves the feature fusion speed of The mobilenetV3 lightweight network is used as the backbone network of Yolov5, and the SE module of channel-separated convolution and attention mechanism is introduced for license plate information extraction, with a support vector machine model concatenated with the anchor point information of the image output from Yolov5 for the estimation of Feb 21, 2024 · To improve the tempo and correctness of plate number recognition, this paper chooses the YOLOv5s model in YOLOv5 and LPRNet model to recognize license plates. 0 of YOLOv5. Complex scale problems in UAV application scenarios require strong regression localization capabilities from target detection algorithms. A lightweight network May 2, 2022 · In order to solve the problem of feature loss in the process of UAV high-resolution image target detection, an adaptive clipping algorithm based on UAV image as the input of training and detection is proposed in this paper. Feb 13, 2024 · In autonomous driving, vehicles are recognized by computer vision and image processing to reduce the risk of accidents. Most methods for improving item recognition accuracy will also make the model more complicated and require additional computer resources. 5% and 16%. com Synthetic aperture radar (SAR) is very widely used in the military and civilian fields, but the target recognition and detection in the SAR images are relatively difficult. Although object detection methods based on deep learning have achieved great success in recent years, they are not effective in small target detection. A multi-type vehicle target dataset collected in different scenarios was set up. May 16, 2023 · As a lightweight target detection network, YOLOv5 is popular in the industry for its advantages of fast speed and small model, but the detection accuracy is not very high. 1 is shown in Figure 3. In the presented method, C3Ghost and Ghost modules are introduced into the YOLOv5 neck network to reduce the floating-point operations (FLOPs) in the feature channel fusion process and enhance the feature expression performance. 88 to 30. 3. 5% and 23. During the process, high-resolution images are input to the to be improved. A color recognition experiment is carried on to some Sep 10, 2022 · The improved YOLOv5s model and YOLOv5s, YOLOv4, and Faster-RCNN identified the same image set; the experimental results show improved YOLOv5 recognition precision level and confidence level, especially for small target recognition, which is excellent and better than other models. To address this issue, this study proposes a foggy weather detection method based on the YOLOv5s framework, named YOLOv5s-Fog. G. This paper employs the YOLOv5 algorithm as its starting point for vehicle target detection. Aug 1, 2022 · To address these issues, an improved lightweight YOLOv5 method is proposed for vehicle detection in this paper. 2% decrease in Floating Point Operations (FLOPs) compared to the existing. This model maintains high precision and accuracy crack detection in low-light, low-contrast and high-noise environments by introducing several effective data augmentation techniques as well as semantic context encoding (SCE) and detail preserving encoding (DPE) at the head of the network structure. Second, an SE module was added to improve the sensitivity of Jul 17, 2023 · Small target detection has been widely used in applications that are relevant to everyday life and have many real-time requirements, such as road patrols and security surveillance. May 16, 2023 · The experimental results show that the improved algorithm improves the detection accuracy by 1. 9% A Vehicle Recognition Model Based on Improved YOLOv5 Lei Shao, Han Wu , Chao Li * and Ji Li School of Electrical Engineering and Automation, Tianjin University of Technology, Tianjin 300384, China * Correspondence: liton@email. Finally, results of detection are outputted. Jan 31, 2022 · To accurately recognize plant diseases under complex natural conditions, an improved plant disease-recognition model based on the original YOLOv5 network model was established. tjut. The overview working pipeline of the proposed model is shown in Fig. edu. The results show that the improved network structure can significantly improve the recall rate and accuracy of small target detection. The experimental findings on the self-made dataset. The structure of the YOLOv5s model in version 6. Due to the turbidity and weak illumination of an Jan 1, 2022 · YOLOv4-LPRNet, YOLOv5s-LPRNe t and YOLOv5m-LPRNet, the recognition accuracy and recall rate of. 10 (b) shows that the loss function value Jun 3, 2023 · In foggy weather scenarios, the scattering and absorption of light by water droplets and particulate matter cause object features in images to become blurred or lost, presenting a significant challenge for target detection in autonomous driving vehicles. Nov 10, 2023 · Compared with original YOLOv5, W-YOLO we propose in the paper reduces the amount of parameters by about 58. 6%, the size of storage space by 58%, and the computation by 72. Abstract. 1 Chang’an University, China. In this paper, the initial anchor boxes of the dataset are re-clustered by the K-means clustering algorithm, and the CIOU loss function and DIOU_nms, are applied to the Feb 22, 2024 · Accurate recognition of traffic lights is essential for ensuring the safety of passengers and pedestrians, especially in the context of self-driving car technology. To address the challenges associated with the use of biased object detection algorithms in robots, we propose a lightweight target detection algorithm for robots based on the improved YOLOv5. 95 are improved. YOLOv5 (You Only Look Once) is a grid-based object detection algorithm that divides the input image into an S × S grid. cn Abstract: The rapid development of the automobile industry has made life easier for people, but Jul 17, 2023 · Based on the spatial data obtained by using UAV, the study achieves the accurate collection of Tangmo DSM, DOM, 3D model, and spatial feature data and forms a method of data collection, processing Mar 10, 2023 · The flow chart presents the steps of data augmentation. From the final results of experiments, we can discover that W-YOLO can significantly reduce the amount of parameters, model size and Apr 1, 2024 · Step 2: The dataset is utilized to train the improved YOLOv5 model, resulting in weight files. The mAP of the improved YOLOv5s model (87. In order to solve the problems of a Jul 17, 2023 · An improved algorithm based on the YOLOv5s model with a CA attention module and a SPD Conv module is incorporated into the network model to address the problems of reduced learning efficiency and loss of fine-grained information due to cross-layer convolution in the model. In addition, the detection performance is better than most current mainstream target detection algorithms and is of some practical value. 1 of YOLOv5. Apr 15, 2023 · To detect a desired underwater target quickly and precisely, a real-time sonar-based target detection system mounted on an autonomous underwater helicopter (AUH) using an improved convolutional neural network (CNN) is proposed in this paper. 7%; the recall rate increased from 74. First, the input contains Mosaic data augmentation, adaptive anchor frame calculation, and adaptive image scaling. Finally, the YOLOv5 algorithm is applied to real vehicle images under complex Vehicle target detection is a very important technology in the field of autonomous driving, This paper presents a road vehicle detection method based on improved Yolov5s. Dec 9, 2022 · As a one-stage detector, the YOLOv5 is used in this paper because of the advantages of low computation and fast recognition speed. However, such detection is easy to classify birds as UAVs. Aug 1, 2022 · To address these issues, an improved lightweight YOLOv5 method is proposed for vehicle detection in this paper. 84% accuracy to detect these object. In this paper, we aim to build a model to recognize and classify the Jun 28, 2023 · In order to meet the fast and accurate automatic detection requirements of equipment maintenance in railway tunnels in the era of high-speed railways, as well as adapting to the high dynamic, low-illumination imaging environment formed by strong light at the tunnel exit, we propose an automatic inspection solution based on panoramic imaging and object recognition with deep learning. Therefore, the improved algorithm in this paper can better meet the Object detection based on unmanned aerial vehicle (UAV) platforms is essential for both engineering and research. First, part of images in the data set are inputted to make data augmentation by rotation, then, the augmented data are inputted into YOLOv5 to make feature extraction and classification. YOLOv5 is introduced as the basic CNN network because of its strength, lightweight and fast speed. Addressing the complexities arising from diverse defect types and intricate backgrounds in visual sensing, this study introduces an enhanced approach to augment the network structure and activation function within the foundational Aug 29, 2023 · The research results on the TT100k dataset show that the improved YOLOv5 precision rate increased from 73. The method mainly consists of two parts: YOLOv5s is used for image segmentation and license plate position detection. Jun 16, 2023 · detection due to the close alignment of vehicles. A new detection model, YOLO-mini, is proposed. Apr 15, 2024 · As a result, we have developed an enhanced traffic sign detection model, named YOLOv5-MCBS, based on the improved YOLOv5. As a result Aug 1, 2022 · Abstract. The proposed YOLOV5-ATE model can effectively carry out Feb 20, 2023 · Due to the dense distribution of tomato fruit with similar morphologies and colors, it is difficult to recognize the maturity stages when the tomato fruit is harvested. accuracy and a 13. Compared with the original YOLOv5 model, the number of model parameters is reduced by 47%, and the detection speed is increased by 54. Each grid cell predicts B bounding mAP is the average of the AP classes and takes a value between 0 and 1. 5:0. An enhanced lightweight real-time detection algorithm, which exhibits higher detection speed and accuracy for vehicle detection and adeptly strikes a finer equilibrium between velocity and precision, providing favorable conditions for embedding the model into mobile devices. We use ShuffleNetV2 [4] as the backbone and increase the kernel. KEYWORDS: UAV image object detection. The model Dec 12, 2022 · In this paper, the forest fire classification detection model is improved based on version 6. Expand. 79%, reducing the missed detection rate; Dong Xudong et al. The speed and accuracy of image recognition have been significantly enhanced, and the size of the YOLOv5 model has been reduced, allowing for improved detection results in the current environment. May 15, 2023 · Similarly, Cheng et al. Feb 16, 2023 · One of significant tasks in autonomous vehicle technology is traffic signs recognizing. In addition, the improved SE-YOLOv5 model has a smaller fluctuation when convergence is achieved. 6. Mar 1, 2022 · It can be seen from Fig. The attention mechanism and efficient architecture lightweight-YOLO (AMEA-YOLO) is proposed in this paper. This paper proposed an improved lightweight recognition algorithm, which is based on YOLOv5. Tomato maturity Aug 7, 2023 · Parking space recognition is an important part in the process of automatic parking, and it is also a key issue in the research field of automatic parking technology. mAP@0. Those bad weather conditions cause low accuracy of detecting and recognizing. First, the K The modified Yolov5 make the accuracy of vehicle color recognition improved effectively to the complex color vehicles and part covered vehicles comparing with original yolov 5 network. Mar 27, 2024 · In order to determine whether electric vehicle drivers are wearing helmets, we propose a study of an improved YOLOv5 electric vehicle helmet recognition algorithm to detect whether an electric vehicle driver is wearing a helmet or not. Firstly, the fisheye camera around the body was calibrated using the Zhang Zhengyou calibration method, and then the Sep 27, 2022 · To reduce the false detection rate of vehicle targets caused by occlusion, an improved method of vehicle detection in different traffic scenarios based on an improved YOLO v5 network is proposed. Finally, accurate vehicle localization is achieved by combining the binocular depth information and the improved YOLOv5 detection results. The proposed algorithm has enhanced recognition In addition, IBR-Yolov5 combined with BiFPN (Bidirectional Feature Pyramid Network) can fuse features extracted by different layers of networks to reduce feature loss. 8% better than the baseline network. The parking space recognition process was studied based on vision and the YOLOv5 target detection algorithm. However, traffic lights present challenges due to their small size and limited recognition accuracy. Color features play a unique role in vehicle recognition. This paper proposes an improved YOLOv5s algorithm for vehicle identification and detection to reduce vehicle driving safety issues based on this problem. plant disease-recognition model based on the original YOLOv5 network model was established. Although the detection speed is lower than that of YOLOv5s, it can still meet the real-time requirements of the environment perception system. An improved real-time tunnel lining crack detection model based on YOLOv5 is proposed. Sep 1, 2023 · 1. First, a new InvolutionBottleneck module was used to reduce the numbers of parameters and cal-culations, and to capture long-distance information in the space. Vehicle Aug 1, 2022 · When the trained network model is evaluated on VOC validation set, the mean accuracy of YOLOv5s-ATE mAP@0. 49% and 98. 1 is shown in Figure 2. 2%. in this research indicate that compared with YOLOv5s, the mAP@0. 95 of YOLOv5 . We proposed an approach that, based on the recognition of vehicle type, further detects and classifies the color of the vehicle's license plate to achieve the recognition of new energy vehicles. Conclusion. 5 \(\%\) higher than the original YOLOv5 algorithm under the conditions of IoU of 0. 9%, an increase of 6. Jun 30, 2023 · To tackle the problem of missed detections in long-range detection scenarios caused by the small size of forest fire targets, initiatives have been undertaken to enhance the feature extraction and detection precision of models designed for forest fire imagery. Jul 4, 2022 · Therefore, a real-time anomaly detection system based on the improved YOLOv5 key place video is proposed for such key places with dense personnel, intricate and complex identities, low accuracy of anomalous behaviour detection and slow detection speed. Second, an SE module was added to improve the sensitivity of the model to channel features. The network structure of YOLOv5 is shown in Figure 2. 1% and 0. 2024. The state-of-the-art object detection method, namely, a class of Jan 1, 2023 · Based on Improved YOLOv5 Jie Yang 1 , Ting Sun 2,* , Wenchao Zhu 3 , and Zonghao Li 4 1 School of Machinery and Transportation, Southwest Forestry Unive rsity, Kunming, 650224, China; 351725623@qq. 2%, while the accuracy can reach 75. YOLOv5 Network Architecture. 5 and mAP@0. Attention Enhancement. 1. 0% increase in detection. com. 8%, compared with the traditional YOLOv5s model, it is improved by 12. 95 by 1. In this model, the YOLOv3 model was improved by integrating more shallow feature maps to improve Mar 30, 2023 · In this paper, the network structure is studied based on the YOLOv5 [ 15] algorithm, and the lightweight MobileNetv2 [ 16] design is used to make it meet the requirements of micro-arithmetic power and low power consumption in the FLIR infrared vehicle pedestrian target detection dataset task. To address these issues, we proposed RBS-YOLO, a vehicle detection model based on Jan 9, 2024 · This paper proposes a lightweight obstacle detection model based on YOLOv5n specifically designed for tunnel construction scenarios. 9% mAP) by 26. The existing deep learning methods for the SAR target detection and recognition has the problem of many model parameters and low efficiency, thus this paper has proposed a lightweight vehicle detection and recognition Nov 30, 2023 · As a result, many researchers have been introducing new improved models based on YOLOv3, YOLOv4 and YOLOv5 in recent years, in Xing, Zhang, Yao, Qin, and Jia (2022) a rail wheel tread defect detection model based on improved YOLOv3 was introduced. Liu and Wang (2020) proposed a recognition method of tomato leaf spot based on MobileNetv2-YOLOv3 model. 79% respectively; The mAP of this meth od is also Oct 2, 2023 · Currently, in the process of autonomous parking, the algorithm detection accuracy and rate of parking spaces are low due to the diversity of parking scenes, changes in lighting conditions, and other unfavorable factors. In view of these issues, in this paper, we proposed an algorithmic model of YOLOv5s-CCAB based on YOLOv5 by adding a CA attention mechanism, replacing the backbone network module, improving the loss function, and optimizing the neck network. 8%, respectively, and also has certain improvements in detection speed. The proposed method uses the Flip-Mosaic algorithm to enhance the network’s perception of small targets. Nov 10, 2023 · The algorithm is based on YOLOv5, which introduces the improved network structure Ghostnet-C in the backbone layer to simplify the network structure and while increasing the detection speed of it Feb 3, 2023 · Based on ablation experiments and detection results, IVP-YOLOv5 has good detection performance and significantly improves small-scale and occluded pedestrians’ detection effect. 8%, which is 7. In this paper, an improved YOLOv5 network is proposed, which not only ensures that the model size can meet the requirements of deployment on the vehicle side but also improve the ability of multi-scale targets and Apr 9, 2024 · The experimental results show that the improved algorithm has a vehicle type recognition accuracy of 96% on the BIT-Vehicle dataset. In this paper, we propose a New Energy Vehicle Recognition and Traffic Flow Statistics (NEVTS) approach However, existing traffic sign recognition algorithms suffer from problems such as large model size, complex computation, high computational cost, which make it difficult to achieve an effective balance between detection speed and detection accuracy. YOLOv5. 6%. 42 frames per second. Firstly, the backbone module is Jan 4, 2022 · To demonstrate the superiority of the improved method based on YOLOv5, YOLOv4 and SSD were used as other models for comparison experiments. Although different types of vehicles can already be recognized, further identification and statistics of new energy and fuel vehicles in unknown and complex environments remain a challenging task. When the trained network model is evaluated on VOC validation set, the mean accuracy of YOLOv5s-ATE [email protected] and [email protected]:0. 3%. These challenges include variations in object scales, complex backgrounds, dense arrangement, and uncertain orientations. First, a new InvolutionBottleneck module was used to reduce the numbers of parameters and calculations, and to capture long-distance information in the space. In order to solve the problem of low recognition rate caused by Feb 11, 2024 · Then, based on the improved YOLOv5 target detection algorithm, the vehicle is detected in the image information to achieve fast and accurate target recognition. Finally, in Reference [13], a lightweight remote sensing rotating object detection model based on YOLOv5 is proposed in this study to improve the performance of remote sensing image object detection. If the center point of an object falls within a grid cell, that grid cell is responsible for predicting the bounding box and class information for that object. 1018927641@qq. In this study, two algorithms, DenseM-YOLOv5 and SimAM-YOLOv5, were proposed by modifying the backbone network of You Only Look Once Mar 26, 2023 · The comparison experiments of various models on the same VOC dataset are shown in Table 1. The primary objective of this model is to reduce the deployment cost of complex models while enhancing detection speed, achieving a balance between detection accuracy and speed. network offers a 1. The method improves the target recognition effect by improving the loss function and Aug 1, 2023 · Therefore, the improved YOLOv5 algorithm is more sensitive to the size and occlusion of the detected objects. In this paper, we propose a forest fire smoke detection model that is based on the improved YOLOv5s model version 6. Aug 1, 2022 · Sensors. 1%, and the recall rate is 79. 1. The larger the mAP the better the performance of the model. bp cc fk sf ib yq wu tf qw zt