Faster R-CNN Model Research Articles

Research on fault diagnosis of industrial materials based on hybrid deep learning model

Abstract Bearing fault detection is becoming more and more important in industrial development, and deep learning image processing technology provides a new solution for this. In this study, ResNet50 is used to replace VGG-16 as the feature extraction network of Faster R-CNN, and feature pyramid network (FPN) and parallel attention module (PAM) are introduced to achieve higher detection accuracy and speed. The experimental validation was conducted with the Case Western Reserve University bearing dataset using a three-fold cross-validation and compared with Yolov5, FPN, and the original Faster R-CNN model. The experimental results show that the accuracy of the proposed bearing image fault detection method is 78.6%, the accuracy is 77.4%, and the recall rate is 76.9%, which can locate and identify bearing faults more accurately. Future work could focus on further optimizing the model structure to enhance detection performance, strengthening the model’s generalization ability to meet the detection requirements of different types of bearing faults.

DeepVision based detection for energy-efficiency and indoor air quality enhancement in highly polluted spaces

Cooking can generate substantial heat from cooking equipment, potentially resulting in reduced thermal comfort levels if this excess heat is not adequately dissipated. Additionally, it can significantly affect indoor air quality (IAQ), not only in kitchen spaces but also in adjacent areas lacking sufficient ventilation. To ensure a healthy and comfortable indoor environment while avoiding unnecessary energy use, this research proposes an approach for detecting equipment usage. Utilizing deep learning and computer vision techniques (referred to as DeepVision), this method aids the operation of demand-driven ventilation systems in highly polluted spaces. A Faster RCNN model was employed and trained to detect kitchen equipment usage in real-time. The ventilation rate for the kitchen space was adjusted based on this real-time detection. Experimental tests were carried out in a case study kitchen and results showed that the detection model achieved an overall F1 score of 0.9142. Overall, the model achieved good performance in real-time detection, accurately identifying appliances in use, such as stoves, ovens, and toasters. Field experimental results showed the advantages of combining mechanical ventilation methods, such as extractor fans and cooker hoods, to mitigate IAQ issues while also achieving energy savings. Moreover, the energy simulations demonstrate its potential to reduce energy consumption by dynamically adjusting ventilation rates in response to real-time equipment usage. When the fan speed was varied according to the real-time detection method, the PM2.5 concentration in the cooking period was 16.5 % lower, with only a 3.7 % rise in fan power and a 0.8 % rise in daily heating demand, compared to using a constant fan speed.

Perimeter monitoring of urban buried pipeline threated by construction activities based on distributed fiber optic sensing and real-time object detection.

Urban construction activities seriously jeopardize the security of buried pipeline. Distributed optical fiber vibration monitoring is one of the most promising ways to prevent third-party threats, of which the biggest challenge is to quickly and accurately detect rare abnormal events from extremely large amounts of time-space raw data. By analogy with image recognition, the task here is similar to object detection if considering the time-space optical signals as the grayscale images and the abnormal events as the objects. Given this, what we believe to be a novel monitoring method is proposed, which consists of two Faster R-CNN models, a max pooling layer and a monitoring strategy. In the field tests, the 86-hour optical vibration signals for 5.25 km distance are recognized within 6.6 minutes with the recognition rate of 98.85% for construction activities, and only two false alarms are issued. The proposed method can reduce the recognition time by 99.59% compared to the CNN-based method.

Landscape design of aging rehabilitation in community park based on improved YOLOv4

In the aging rehabilitation landscape design of community parks, the crack detection of landscape architecture is very important, which is related to the beauty and safety of landscape architecture. In order to improve the poor effect of current landscape building crack detection methods, an intelligent landscape building crack detection model based on improved YOLOv4 is proposed. Aiming at the inadequacy of information feature extraction in YOLOv4 algorithm, the coordinate attention module with extended convolution structure optimization is adopted to optimize it. Aiming at the defect that YOLOv4 algorithm has poor information feature utilization rate of shallow position, an improved K-means algorithm is designed to determine the optimal size of prior frame, so as to improve the performance of the algorithm. The performance of the algorithm is improved. Finally, combined with the above content, an intelligent detection model of landscape building cracks based on improved YOLOv4 is constructed. The results verify that the fitting degree of the model is 0.986, which is 0.008 and 0.016 higher than that of the CRF-CNN and Faster-RCNN models, respectively. The F1 value is 0.951, 0.10–0.12 higher than the two models. The accuracy was 98.26%, 0.47%-0.51% higher than the two models. Recall value was 96.44%, which was 0.47%-0.51% higher than that of the two models. The AUC value is 0.988, which is 0.009–0.016 higher than the two models. To sum up, the model built in the study can detect the cracks in landscape architecture with high accuracy and efficiency, and improve the safety and beauty of the landscape. Meanwhile, this model can assist in the design of aging rehabilitation landscape in community parks.

An improved SSD lightweight network with coordinate attention for aircraft target recognition in scene videos

Accurate identification and monitoring of aircraft on the airport surface can assist managers in rational scheduling and reduce the probability of aircraft conflicts, an important application value for constructing a "smart airport." For the airport surface video monitoring, there are small aircraft targets, aircraft obscuring each other, and affected by different weather, the aircraft target clarity is low, and other complex monitoring problems. In this paper, a lightweight model network for video aircraft recognition in airport field video in complex environments is proposed based on SSD network incorporating coordinate attention mechanism. First, the model designs a lightweight feature extraction network with five feature extraction layers. Each feature extraction layer consists of two modules, Block_A and Block_I. The Block_A module incorporates the coordinate attention mechanism and the channel attention mechanism to improve the detection of obscured aircraft and to enhance the detection of small targets. The Block_I module uses multi-scale feature fusion to extract feature information with rich semantic meaning to enhance the feature extraction capability of the network in complex environments. Then, the designed feature extraction network is applied to the improved SSD detection algorithm, which enhances the recognition accuracy of airport field aircraft in complex environments. It was tested and subjected to ablation experiments under different complex weather conditions. The results show that compared with the Faster R-CNN, SSD, and YOLOv3 models, the detection accuracy of the improved model has been increased by 3.2%, 14.3%, and 10.9%, respectively, and the model parameters have been reduced by 83.9%, 73.1%, and 78.2% respectively. Compared with the YOLOv5 model, the model parameters are reduced by 38.9% when the detection accuracy is close, and the detection speed is increased by 24.4%, reaching 38.2fps, which can well meet the demand for real-time detection of aircraft on airport surfaces.

Automatic Recognition of Agriculture Pests with Balanced Feature Pyramid Network

HIGHLIGHTSWe propose a balanced feature pyramid network model to achieve automatic recognition of agricultural pests.We propose and improved feature pyramid module to address the problems of the large semantic gap before feature fusion in FPN (feature pyramid network), information loss during feature fusion, and how to utilize complementary information to strengthen features after feature fusion.Our method is evaluated on the pest dataset and achieves better recognition results, the mAP (mean Average Precision) reaches 90.04%, and the final mAP after combining with the data enhancement strategy reaches 92.56%.Abstract.In order to ensure the steady improvement of the quality and efficiency of agricultural production, the precise prevention and control of agriculture pests should be given top priority. Based on the Faster R-CNN model, we propose a feature-augmented recognition model (FARM) for the detection of agricultural pests to improve the professional level of pest control. Firstly, we select VoVNet as the backbone network to extract rich visual information. Secondly, in view of the existing problems of FPN (Feature Pyramid Network), we propose a feature pyramid enhancement network to improve it. Finally, we use an adaptive anchor box network to train anchor boxes to avoid the problem of unbalanced positive and negative samples caused by artificial parameter adjustment. The experimental result shows that our method can achieve better recognition results; the mAP on the agricultural pest dataset reaches 90.04%, and the final mAP after combining with the data enhancement strategy reaches 92.56%. Keywords: Adaptive anchor box, Agricultural pests, Feature augmented, Feature pyramid.

Underwater Engineering Crack Identification based on Lightweight Convolutional Neural Network

Convolutional neural network is an effective model for image feature recognition, which is widely used in crack recognition and risk detection. The crack identification of underwater engineering involves a huge scale of data, and the traditional R-CNN model and Faster R-CNN model have the problems of large number of model parameters and low efficiency for crack identification. Therefore, a lightweight convolutional neural network based crack identification method for underwater engineering is proposed to optimize the efficiency and accuracy of crack identification. Deep separable convolution is used to replace the common convolution of YOLOX network (an open source high-performance object detection algorithm), reducing the redundant parameters of the model to achieve lightweight design. Following the backbone feature extraction network framework of YOLOX, Transformer (a structure based on attention mechanism and forward neural network) vision module is adopted to replace the CSP structure (a feature extraction structure) at the end of the backbone network, adding attention mechanism and enhancing key information extraction capability. Make up for the problem of decreasing feature extraction accuracy caused by decreasing parameter number; Finally, the adaptive spatial feature fusion strategy is used instead of the traditional feature pyramid cascade to implement feature fusion and improve the feature extraction ability of small targets. The test results show that the improved YOLOX lightweight convolutional neural network has good prediction ability for underwater engineering cracks, and can accurately select the crack location, with fewer false detection and missed detection cases. Ablation experiments show that this study builds a lightweight convolutional neural network model, which improves the accuracy of the model to identify underwater engineering cracks. The improved lightweight convolutional neural network is suitable for crack identification in underwater engineering and can be widely applied in the field of underwater engineering risk identification.

Detection of Chicken Carcass Defects in Hyperspectral Images Based on the Faster RCNN Model Research on Hyperspectral Image Detection Method of Chicken Carcass Skin Damage Defect Based on Faster RCNN Model

Detection of Chicken Carcass Defects in Hyperspectral Images Based on the Faster RCNN Model Research on Hyperspectral Image Detection Method of Chicken Carcass Skin Damage Defect Based on Faster RCNN Model

Comparative Analysis of Faster R-CNN Models for Coconut Tree Detection: ResNet-101, MobileNetV2, VGG16

Comparative Analysis of Faster R-CNN Models for Coconut Tree Detection: ResNet-101, MobileNetV2, VGG16

Accelerating biomedical image segmentation using equilibrium optimization with a deep learning approach

<abstract> <p>Biomedical image segmentation is a vital task in the analysis of medical imaging, including the detection and delineation of pathological regions or anatomical structures within medical images. It has played a pivotal role in a variety of medical applications, involving diagnoses, monitoring of diseases, and treatment planning. Conventionally, clinicians or expert radiologists have manually conducted biomedical image segmentation, which is prone to human error, subjective, and time-consuming. With the advancement in computer vision and deep learning (DL) algorithms, automated and semi-automated segmentation techniques have attracted much research interest. DL approaches, particularly convolutional neural networks (CNN), have revolutionized biomedical image segmentation. With this motivation, we developed a novel equilibrium optimization algorithm with a deep learning-based biomedical image segmentation (EOADL-BIS) technique. The purpose of the EOADL-BIS technique is to integrate EOA with the Faster RCNN model for an accurate and efficient biomedical image segmentation process. To accomplish this, the EOADL-BIS technique involves Faster R-CNN architecture with ResNeXt as a backbone network for image segmentation. The region proposal network (RPN) proficiently creates a collection of a set of region proposals, which are then fed into the ResNeXt for classification and precise localization. During the training process of the Faster RCNN algorithm, the EOA was utilized to optimize the hyperparameter of the ResNeXt model which increased the segmentation results and reduced the loss function. The experimental outcome of the EOADL-BIS algorithm was tested on distinct benchmark medical image databases. The experimental results stated the greater efficiency of the EOADL-BIS algorithm compared to other DL-based segmentation approaches.</p> </abstract>

Enhanced Detection of Glass Insulator Defects Using Improved Generative Modeling and Faster RCNN

The precise defect detections for glass insulators are of utmost importance to ensure their safety and functionality. Therefore, this study proposes an improved defect detection algorithm based on the optimized deep learning network. The collected glass insulator data was limited in size. Even after data augmentation, it remained insufficient for the training requirements of deep learning models. In this study, employing the improved Denoising Diffusion Probabilistic Models (DDPM) generative model to expand the glass insulator data. The glass insulator defect images generated by the improved noise-fitting network exhibit enhanced quality and high fidelity. Through manual selection and iterative experiments, a total of 1200 images were curated, constituting the glass insulator defect dataset for training and test of deep learning models. Faster RCNN was chosen as the defect detection model, and its VGG16 feature extraction network was replaced with ResNet50 to address the issue of gradient vanishing caused by excessive network stacking. Additionally, the Feature Pyramid Network (FPN) structure was introduced to enhance semantic extraction for different defect scales. The Kmeans++ algorithm was utilized to improve the proposal box generation parameters in RPN. Compared to the baseline Faster RCNN model's mAP of 72.7%, our improved version achieved a significant increase, reaching a mAP of 85.9%.

An effective object detection and tracking using automated image annotation with inception based faster R-CNN model

The present study advances object detection and tracking techniques by proposing a novel model combining Automated Image Annotation with Inception v2-based Faster RCNN (AIA-IFRCNN). The research methodology utilizes the DCF-CSRT model for image annotation, Faster RCNN for object detection, and the inception v2 model for feature extraction, followed by a softmax layer for image classification. The proposed AIA-IFRCNN model is evaluated on three benchmark datasets: Bird (Dataset 1), UCSDped2 (Dataset 2), and Under Water (Dataset 3), to determine prediction accuracy, annotation time, Center Location Error (CLE), and Overlap Rate (OR). The experimental results indicate that the AIA-IFRCNN model outperformed existing models regarding detection accuracy and tracking performance. Notably, it achieved a maximum detection accuracy of 95.62 % on Dataset 1, outperforming other models. Additionally, it achieved minimum average CLE values of 4.16, 5.78, and 3.54, and higher overlap rates of 0.92, 0.90, and 0.94 on the respective datasets (1, 2 and 3). Hence, this research work on object detection and tracking using the AIA-IFRCNN model is essential for improving system efficiency and fostering innovation in the field of computer vision and object tracking.

Agricultural Pest Detection Methods and Control Measures Combining Deep Learning Algorithms

Abstract Agricultural pests and diseases critically impact the quality and yield of crops, thereby underscoring the practical importance of their automatic monitoring, identification, and timely management in agricultural production. This study develops a targeted detection model using a deep learning approach, specifically by enhancing the Faster R-CNN algorithm. Modifications were implemented in three key areas of the basic Faster R-CNN: First, the DIOU-NMS technique was employed to optimize the ancillary network during the feature extraction phase. Secondly, an attention mechanism along with an SE module was integrated within the DIOU-NMS to augment the network’s capability. During the training phase, optimization was facilitated through stochastic gradient descent. The efficacy of the refined Faster RCNN model was established via ablation studies, and its performance was benchmarked against existing methodologies for small and general target detection. Results indicate that the enhanced Faster R-CNN framework surpasses conventional small target and generic detection models in accuracy, achieving a 6.4% higher detection rate for various pest categories compared to its predecessor. The findings affirm the potential of the advanced Faster R-CNN in effective agricultural pest detection. Furthermore, this paper advocates a tripartite strategy for pest management, encompassing phytosanitary measures, agricultural interventions, and chemical controls.

Classification and Localization of Arabic Handwritten Text in KHATT Dataset Based on Faster R-CNN

Arabic handwriting recognition is an important research area in computer vision. Due to the complexity of the Arabic script, this is an arduous task. Several approaches have been proposed to address this challenge, including deep learning algorithms. Despite their efficiency, these approaches present some limitations such as the use of lexicon-driven models, the need of a lot of data for training and the huge computational cost. We propose, in this paper, two novel models based on the robust Faster Region-Convolution Neural Network (Faster R-CNN) to recognize Arabic handwritten sentences. The Faster R-CNN is commonly used to detect objects in images and depends on region proposal algorithms. These models use the pre-trained VGG 16 and ResNet50. Moreover, they use a soft non-maximum suppression strategy (Soft-NMS) in the post-processing stage instead of the traditional NMS to increase the detection rate of overlapping items. The models will be trained independently to identify words in the text lines and tested using sentences from the (KFUPM Handwritten Arabic TexT) KHATT dataset. It will be shown that the faster R-CNN models allow greater accuracy and effectiveness in handwriting recognition. They achieve accuracy rates of 99% and 98% for the two networks, VGG16 and ResNet50, respectively

Maize Leaf Compound Disease Recognition Based on Attention Mechanism

In addition to the conventional situation of detecting a single disease on a single leaf in corn leaves, there is a complex phenomenon of multiple diseases overlapping on a single leaf (compound diseases). Current research on corn leaf disease detection predominantly focuses on single leaves with single diseases, with limited attention given to the detection of compound diseases on a single leaf. However, the occurrence of compound diseases complicates the accuracy of traditional deep learning algorithms for disease detection, necessitating the exploration of new models for the identification of compound diseases on corn leaves. To achieve rapid and accurate identification of compound diseases in corn fields, this study adopts the YOLOv5s model as the base network, chosen for its smaller size and faster detection speed. We propose a corn leaf compound disease recognition method, YOLOv5s-C3CBAM, based on an attention mechanism. To address the challenge of limited data for corn leaf compound diseases, a CycleGAN model is employed to generate synthetic images. The scarcity of real data is thereby mitigated, facilitating the training of deep learning models with sufficient data. The YOLOv5s model is selected as the base network, and an attention mechanism is introduced to enhance the network’s focus on disease lesions while mitigating interference from compound diseases. This augmentation results in improved recognition accuracy. The YOLOv5s-C3CBAM compound disease recognition model, incorporating the attention mechanism, achieves an average precision of 83%, an F1 score of 81.98%, and a model size of 12.6 Mb. Compared to the baseline model, the average precision is improved by 3.1 percentage points. Furthermore, it outperforms Faster R-CNN and YOLOv7-tiny models by 27.57 and 2.7 percentage points, respectively. This recognition method demonstrates the ability to rapidly and accurately identify compound diseases on corn leaves, offering valuable insights for future research on precise identification of compound agricultural crop diseases in field conditions.

Detection of Esophageal Cancer Lesions Based on CBAM Faster R-CNN

Esophageal cancer is a common malignant tumor in daily life, which seriously affects human health. Esophageal cancer in China. The incidence rate is among the highest in the world, and there are a large number of new cases of esophageal cancer every year. At present, the diagnosis of esophageal cancer is mainly based on the use of electronic gastroscopy, which reflects the observed situation on the fluorescent screen and conducts detection through the fluorescent screen. With the increasing number of patients, the pressure and intensity of the doctor's work are getting greater and greater[1]. From the perspective of molecular level, the occurrence and development of esophageal cancer, like other cancers, are related to the activation of proto-oncogenes and the inhibition of anti-apoptosis genes. CBAM Faster R-CNN is proposed to solve the problems such as the esophageal region is not obvious and the background region occupies a large proportion in the feature map obtained by the backbone network of Faster R-CNN in barium meal imaging. CBAM is added to the convolutional attention module CBAM on the basis of the original Faster R-CNN model. To enhance the saliency of the features of the esophageal region in the feature map. CBAM Faster R-CNN model was used to train the training set after data enhancement, and Recall, Precision and AP values were used for evaluation and analysis.

A novel system for assessing paraquat toxicity using Desmodesmus maximus as a potential bio-indicator and deep learning-based approach

Microalgae play a crucial role as environmental indicators, offering valuable insights into ecosystem health and aiding in the assessment of water source contamination by toxins. In recent times, the presence of paraquat in water sources has become a grave concern due to its high toxicity and persistence. The detection of paraquat in natural water is of paramount importance for safeguarding water quality and public safety. Microalgae are invaluable bio-indicators for pollutant detection, but using small-sized microalgae according to OECD guidelines may not suit toxicity field combined with deep learning due to limitations. In this regard, this study proposes the use of Desmodesmus maximus as a potential bio-indicator, known for its larger cell size, surpassing Desmodesmus subspicatus, the reference strain specified by OECD guidelines. Exposure of D. maximus to 2 mg/L paraquat resulted in significant internal damage and loss of chlorophyll content, with a determined 72 h-EC50 of 0.25 mg/L. Accurate microalgae recognition typically requires time-consuming and inaccessible expert analysis. Therefore, this study explores deep learning techniques to enhance the efficiency and accuracy of microalgae toxicity testing. Deep convolutional neural networks (D-CNNs), including RetinaNet, YOLOv5, EfficientDet, and Faster R-CNN models, are compared for microalgae detection and differentiation. The analysis demonstrates the superiority of the Faster R-CNN model, achieving a remarkable mAP@0.5 value of 0.98 in multiclass conditions for identifying normal, empty, and toxified colonies. These findings underscore the considerable potential of deep learning techniques in advancing microalgae toxicity testing, thereby facilitating enhanced accessibility and cost-effectiveness in monitoring the environmental impact on water resources.

Advanced Faster-RCNN Model for Automated Recognition and Detection of Weld Defects on Limited X-Ray Image Dataset

Advanced Faster-RCNN Model for Automated Recognition and Detection of Weld Defects on Limited X-Ray Image Dataset

Artificial intelligent identification of apatite fission tracks based on machine learning

Over the past half century, apatite fission track (AFT) thermochronometry has been widely used in the studies of thermal histories of Earth’s uppermost crust. The acquired thermal histories in turn can be used to quantify many geologic processes such as erosion, sedimentary burial, and tectonic deformation. However, the current practice of acquiring AFT data has major limitations due to the use of traditional microscopes by human operators, which is slow and error-prone. This study uses the local binary pattern feature based on the OpenCV cascade classifier and the faster region-based convolutional neural network model based on the TensorFlow Object Detection API, these two methods offer a means for the rapid identification and measurement of apatite fission tracks, leading to significant improvements in the efficiency and accuracy of track counting. We employed a training dataset consisting of 50 spontaneous fission track images and 65 Durango standard samples as training data for both techniques. Subsequently, the performance of these methods was evaluated using additional 10 spontaneous fission track images and 15 Durango standard samples, which resulted in higher Precision, Recall, and F1-Score values. Through these illustrative examples, we have effectively demonstrated the higher accuracy of these newly developed methods in identifying apatite fission tracks. This suggests their potential for widespread applications in future apatite fission track research.

Deep Learning-based Automated Knee Joint Localization in Radiographic Images Using Faster R-CNN.

Osteoarthritis is a condition that poses a risk to the knee joint, resulting in pain and impaired function. However, traditional knee X-ray evaluations using the Kellgren-Lawrence grading system have proven to be inefficient. These evaluations are subjective, time-consuming, and labor-intensive, particularly in busy hospital settings. The objective of this research was to present a deep learning-based approach that can detect knee joint regions in medical images. By addressing the limitations of traditional methods, the aim was to develop a more efficient and automated approach for knee joint analysis. The proposed method utilizes the Faster R-CNN model, which consists of a region proposal network (RPN) and Fast R-CNN. The RPN generates region proposals that potentially contain knee joint regions, while the Fast R-CNN network categorizes and extracts features from these proposals. To train the model, a dataset of knee joint images was employed. The performance of the model was evaluated using metrics, such as accuracy, precision, recall, F1-score, and mean IoU (Intersection Over Union). The results demonstrated the high accuracy of the proposed method in detecting knee joint regions. The model achieved a mean IoU of 94.5, indicating a strong overlap between the predicted and ground truth regions. These findings highlight the potential of deep learning-based approaches in automating medical image analysis, specifically in the diagnosis and management of knee joint disorders. This study emphasizes the significance of leveraging advanced technologies, such as deep learning, in medical imaging. By developing more efficient and accurate methods for identifying knee joint regions in medical images, it becomes feasible to enhance patient outcomes and healthcare delivery. The proposed deep learning-based approach showcases promising results, paving the way for further advancements in the field of medical image analysis and contributing to improved diagnostic capabilities for knee joint disorders.