Faster Region-based Convolutional Research Articles

ACT-FRCNN: Progress Towards Transformer-Based Object Detection

Maintaining a high input resolution is crucial for more complex tasks like detection or segmentation to ensure that models can adequately identify and reflect fine details in the output. This study aims to reduce the computation costs associated with high-resolution input by using a variant of transformer, known as the Adaptive Clustering Transformer (ACT). The proposed model is named ACT-FRCNN. Which integrates ACT with a Faster Region-Based Convolution Neural Network (FRCNN) for a detection task head. In this paper, we proposed a method to improve the detection framework, resulting in better performance for out-of-domain images, improved object identification, and reduced dependence on non-maximum suppression. The ACT-FRCNN represents a significant step in the application of transformer models to challenging visual tasks like object detection, laying the foundation for future work using transformer models. The performance of ACT-FRCNN was evaluated on a variety of well-known datasets including BSDS500, NYUDv2, and COCO. The results indicate that ACT-FRCNN reduces over-detection errors and improves the detection of large objects. The findings from this research have practical implications for object detection and other computer vision tasks.

Utilization of transformer model in multimodal data fusion learning: Cross-modal knowledge transfer in the new generation learning space

In response to the difficulties in integrating multimodal data and insufficient model generalization ability in traditional cross-modal knowledge transfer, this article used the Transformer model to explore it in the new generation learning space. Firstly, the article analyzed the processing methods of data and models in cross-modal knowledge transfer, and explored the application of Transformer models in the learning space. This model used natural language processing to represent and extract textual features, Mel Frequency Cepstral Coefficients (MFCCs) to represent and extract audio features, and Faster R-CNN (Faster Region-based Convolutional Neural Network) to represent and extract image features. The article also discussed the implementation process of the Transformer model functionality. The experiment used data from four datasets, including Quora Question Pairs, to test the performance of the model’s cross-modal knowledge transfer through intelligent question answering and task analysis. In single type data testing, the accuracy and recall of the model in this article were better than the comparison model in the three types of data. The highest accuracy and recall in the test set were 91% and 93%, respectively. In the most challenging multimodal intelligent question answering test, the speech-image question answering method achieved an accuracy rate of 89% in answering open questions, indicating that the model had good multimodal data fusion ability. In the analysis experiment of 6 homework prone knowledge points on images with text annotations, the induction accuracy reached 85%, indicating that the model had strong generalization ability. The experimental results showed that the Transformer model had good cross-modal knowledge transfer performance, providing a reference for subsequent research on cross-modal knowledge transfer in the new generation learning space.

Performance evaluation of semi-supervised learning frameworks for multi-class weed detection.

Precision weed management (PWM), driven by machine vision and deep learning (DL) advancements, not only enhances agricultural product quality and optimizes crop yield but also provides a sustainable alternative to herbicide use. However, existing DL-based algorithms on weed detection are mainly developed based on supervised learning approaches, typically demanding large-scale datasets with manual-labeled annotations, which can be time-consuming and labor-intensive. As such, label-efficient learning methods, especially semi-supervised learning, have gained increased attention in the broader domain of computer vision and have demonstrated promising performance. These methods aim to utilize a small number of labeled data samples along with a great number of unlabeled samples to develop high-performing models comparable to the supervised learning counterpart trained on a large amount of labeled data samples. In this study, we assess the effectiveness of a semi-supervised learning framework for multi-class weed detection, employing two well-known object detection frameworks, namely FCOS (Fully Convolutional One-Stage Object Detection) and Faster-RCNN (Faster Region-based Convolutional Networks). Specifically, we evaluate a generalized student-teacher framework with an improved pseudo-label generation module to produce reliable pseudo-labels for the unlabeled data. To enhance generalization, an ensemble student network is employed to facilitate the training process. Experimental results show that the proposed approach is able to achieve approximately 76% and 96% detection accuracy as the supervised methods with only 10% of labeled data in CottonWeedDet3 and CottonWeedDet12, respectively. We offer access to the source code (https://github.com/JiajiaLi04/SemiWeeds), contributing a valuable resource for ongoing semi-supervised learning research in weed detection and beyond.

Black-box adversarial patch attacks using differential evolution against aerial imagery object detectors

Adversarial patch attacks are commonly used to attack aerial imagery object detectors. However, most existing methods are designed for white-box settings, which are impractical in real world scenarios. In this work, we propose a novel framework for black-box adversarial patch attacks against aerial imagery object detectors using differential evolution (DE). Specifically, we first introduce a new dimensionality reduction strategy to address the high-dimensionality curse in DE optimization problems. Then, we design three universal fitness functions to help DE to select better individuals within a limited computational budget. Finally, we conduct extensive experiments on the Dataset for Object Detection in Aerial images (DOTA) against You Only Look Once (YOLOv3, YOLOv4), and Faster Region-based Convolutional Network (Faster R-CNN), utilizing attack success rate (ASR) and average precision (AP) to quantitatively evaluate the attack efficiency. Results on YOLOv3 for the plane category indicate that our proposed strategy achieves at least a 20.97% improvement in ASR compared to existing dimensionality reduction schemes. Moreover, experiments conducted on detectors with different architectures reveal inconsistent adversarial robustness across categories. To the best of our knowledge, this is the first work to explore the use of DE in black-box adversarial patch attacks against aerial imagery object detectors. Our code has been released at https://github.com/tang-agui/Bbox-Att-Detector.

Oral Cancer Detection Using Deep Learning

Oral cancer is a very serious, complex, and common type of cancer. Oral cancer ranks eighth globally in terms of cancer incidence in India, with 130,000 deaths reported annually. The tumor affects the tonsils, salivary glands, neck, face, and mouth. Numerous methods, including screening procedures and biopsies—which entail taking a small sample of body tissue and analyzing it under a microscope—can be used to identify oral cancer. The disadvantage of cancer cells is that they are hard to identify and quantify. For this reason, digital processing technology will be employed in this study to identify and classify cancer cells that have affected the oral cavity. State-of-the-art technology and an in-depth learning algorithm can be employed for early detection and categorization. This work employs the Zernike Moment, wavelet features, and the bag histogram of directed gradients as three techniques for character extraction. After the characteristics are obtained, the best texture characteristic is chosen using the fuzzy particle swarm optimization technique (FPSO). In the end, these features were classified using the Faster Region-based Convolution Neural Network (faster RCNN) classifier. to evaluate the efficiency, error, recall rate, precision rate, and classification accuracy of the recommended approach.

Disease Detection In Rice And Wheat Leaves: A Comparative Study On Various Deep Learning Techniques

Rice and wheat are considered as the most significant foods in agriculture all over the globe. Around 50% of all calories consumed in the human diet are rendered by both rice and wheat. Rice is a rich source of carbohydrates that is the main energy source of the human body. Wheat, which comprises vitamins and minerals, is a staple food source. Also, wheat is extensively used as flour to make a variety of food products. However, the disease that occurs in the leaves of rice and wheat could decelerate the production of these two food sources. Thus, timely detection of disease that occurs within the rice and wheat leaves is very significant. To detect Rice Leaf Diseases (RLD) and Wheat Leaf Diseases (WLD), numerous conventional methods are established. Specifically, You Only Look Once (YOLO), Faster Regionbased Convolutional Neural Network (FRCNN), and Single Shot Detector (SSD) are extensively implemented in various works to detect diverse leaf diseases in rice and wheat plants. Therefore, in this review, the merits and demerits of the traditional Object Detection (OD) models in RLD and WLD detection are provided systematically. The robustness of the Deep learning (DL) techniques in detecting various kinds of leaf diseases in rice and wheat plants with a classification accuracy of 99% and a precision of 98% is proved by the analysis outcomes.

Vehicle detection and tracking in intelligent transportation systems based deep learning

This research paper focuses on the advancements and optimizations made to fundamental object detection algorithms in vehicle detection. The study explores integrating and reusing CNN (Convolutional Neural Networks) models with other techniques to enhance performance. Three main models, namely Faster R-CNN (Faster Region-based Convolutional Neural Network), Improved SSD (Single Shot Multibox Detector), and YOLOv4 (You Only Look Once v4), are analyzed, showcasing their incremental improvements in accuracy and overall detection performance. However, the increased computational complexity and time demands are trade-offs. The study also presents EnsembleNet, a model combining Faster R-CNN and YOLOv5, which achieves higher average precision values. Another approach involves fusing edge features with CNN models, resulting in faster and more accurate vehicle recognition. The paper predicts future deep learning trends, emphasizing the need for improved hardware capabilities to handle complex models. Integrating deep learning with sensor fusion and edge computing holds promise for intelligent transportation systems.

Lightweight Detection Methods for Insulator Self-Explosion Defects.

The accurate and efficient detection of defective insulators is an essential prerequisite for ensuring the safety of the power grid in the new generation of intelligent electrical system inspections. Currently, traditional object detection algorithms for detecting defective insulators in images face issues such as excessive parameter size, low accuracy, and slow detection speed. To address the aforementioned issues, this article proposes an insulator defect detection model based on the lightweight Faster R-CNN (Faster Region-based Convolutional Network) model (Faster R-CNN-tiny). First, the Faster R-CNN model's backbone network is turned into a lightweight version of it by substituting EfficientNet for ResNet (Residual Network), greatly decreasing the model parameters while increasing its detection accuracy. The second step is to employ a feature pyramid to build feature maps with various resolutions for feature fusion, which enables the detection of objects at various scales. In addition, replacing ordinary convolutions in the network model with more efficient depth-wise separable convolutions increases detection speed while slightly reducing network detection accuracy. Transfer learning is introduced, and a training method involving freezing and unfreezing the model is employed to enhance the network's ability to detect small target defects. The proposed model is validated using the insulator self-exploding defect dataset. The experimental results show that Faster R-CNN-tiny significantly outperforms the Faster R-CNN (ResNet) model in terms of mean average precision (mAP), frames per second (FPS), and number of parameters.

A Comparative Analysis of Modern Object Detection Algorithms: YOLO vs. SSD vs. Faster R-CNN

In recent years, object detection has become a crucial component in various computer vision applications, including autonomous driving, surveillance, and image recognition. This study provides a comprehensive comparative analysis of three prominent object detection algorithms: You Only Look Once (YOLO), Single Shot MultiBox Detector (SSD), and Faster Region-Based Convolutional Neural Networks (Faster R-CNN). The background of this research lies in the growing need for efficient and accurate object detection methods that can operate in real-time. YOLO is known for its speed, SSD for its balance between speed and accuracy, and Faster R-CNN for its high detection accuracy, albeit at a slower pace. The methodology involves implementing these algorithms on a standardized dataset and evaluating their performance based on various metrics, including detection accuracy, processing speed, and computational resource requirements. Each algorithm is tested under similar conditions to ensure a fair comparison. The results indicate that while YOLO excels in real-time applications due to its high speed, SSD offers a middle ground with respectable accuracy and speed, making it suitable for applications requiring a balance of both. Faster R-CNN demonstrates superior accuracy, making it ideal for scenarios where detection precision is paramount, despite its slower performance. This comparative analysis highlights the strengths and weaknesses of each algorithm, providing valuable insights for researchers and practitioners in selecting the appropriate object detection method for their specific needs.

Artificial intelligence to identify fractures on pediatric and young adult upper extremity radiographs.

Pediatric fractures are challenging to identify given the different response of the pediatric skeleton to injury compared to adults, and most artificial intelligence (AI) fracture detection work has focused on adults. Develop and transparently share an AI model capable of detecting a range of pediatric upper extremity fractures. In total, 58,846 upper extremity radiographs (finger/hand, wrist/forearm, elbow, humerus, shoulder/clavicle) from 14,873 pediatric and young adult patients were divided into train (n = 12,232 patients), tune (n = 1,307), internal test (n = 819), and external test (n = 515) splits. Fracture was determined by manual inspection of all test radiographs and the subset of train/tune radiographs whose reports were classified fracture-positive by a rule-based natural language processing (NLP) algorithm. We trained an object detection model (Faster Region-based Convolutional Neural Network [R-CNN]; "strongly-supervised") and an image classification model (EfficientNetV2-Small; "weakly-supervised") to detect fractures using train/tune data and evaluate on test data. AI fracture detection accuracy was compared with accuracy of on-call residents on cases they preliminarily interpreted overnight. A strongly-supervised fracture detection AI model achieved overall test area under the receiver operating characteristic curve (AUC) of 0.96 (95% CI 0.95-0.97), accuracy 89.7% (95% CI 88.0-91.3%), sensitivity 90.8% (95% CI 88.5-93.1%), and specificity 88.7% (95% CI 86.4-91.0%), and outperformed a weakly-supervised model (AUC 0.93, 95% CI 0.92-0.94, P < 0.0001). AI accuracy on cases preliminary interpreted overnight was higher than resident accuracy (AI 89.4% vs. 85.1%, 95% CI 87.3-91.5% vs. 82.7-87.5%, P = 0.01). An object detection AI model identified pediatric upper extremity fractures with high accuracy.

An improved deep learning-based optimal object detection system from images

Computer vision technology for detecting objects in a complex environment often includes other key technologies, including pattern recognition, artificial intelligence, and digital image processing. It has been shown that Fast Convolutional Neural Networks (CNNs) with You Only Look Once (YOLO) is optimal for differentiating similar objects, constant motion, and low image quality. The proposed study aims to resolve these issues by implementing three different object detection algorithms—You Only Look Once (YOLO), Single Stage Detector (SSD), and Faster Region-Based Convolutional Neural Networks (R-CNN). This paper compares three different deep-learning object detection methods to find the best possible combination of feature and accuracy. The R-CNN object detection techniques are performed better than single-stage detectors like Yolo (You Only Look Once) and Single Shot Detector (SSD) in term of accuracy, recall, precision and loss.

Deep learning and computer vision for leaf miner infestation severity detection on muskmelon (Cucumis melo) leaves

Corp protection against pests is known to play a crucial role in developing efficient crop management strategies for Precision Agriculture. A recent estimation by Food and Agriculture Organization (FAO) shows that the perennial loss due to crop pests and diseases amounts to nearly 40% of agricultural crop production at a global level. Identifying pests and diseases and eradicating them without automation is laborious and time-consuming. Automation in detecting and identifying miners at the onset and their eradication is possible using deep learning (DL) and computer vision. This study aims to develop a Detectron2-based framework to detect and localize miner infestations on muskmelon leaves by developing a detection model that integrates DL and a computer vision library to enhance detection capabilities. The approach develops, experiments, and compares a region-based detector (Faster Region-based Convolutional Neural networks (R-CNN)) with a region-free (RetinaNet) by training and validating the bounding box annotated custom dataset of leaf miner infected muskmelon leaves imaged using a smartphone camera. The results show that the RetinaNet-based detector outperforms the Faster R-CNN-based detector in recognizing the infestation severity levels, significantly increasing mean average precision and acquiring faster detection speeds.

A Study on Pine Larva Detection System Using Swin Transformer and Cascade R-CNN Hybrid Model

Pine trees are more vulnerable to diseases and pests than other trees, so prevention and management are necessary in advance. In this paper, two models of deep learning were mixed to quickly check whether or not to detect pine pests and to perform a comparative analysis with other models. In addition, to select a good performance model of artificial intelligence, a comparison of the recall values, such as Precision (AP), Intersection over Union (IoU) = 0.5, and AP (IoU), of four models including You Only Look Once (YOLOv5s)_Focus+C3, Cascade Region-Based Convolutional Neural Networks (Cascade R-CNN)_Residual Network 50, Faster Region-Based Convolutional Neural Networks, and Faster R-CNN_ResNet50 was performed, and in addition to the mixed model Swin Transformer_Cascade R-CNN proposed in this paper, they were evaluated. As a result of this study, the recall value of the YOLOv5s_Focus+C3 model was 66.8%, the recall value of the Faster R-CNN_ResNet50 model was 91.1%, and the recall value of the Cascade R-CNN_ResNet50 model was 92.9%. The recall value of the model that mixed the Cascade R-CNN_Swin Transformer proposed in this study was 93.5%. Therefore, as a result of comparing the recall values of the performances of the four models in detecting pine pests, the Cascade R-CNN_Swin Transformer mixed model proposed in this paper showed the highest accuracy.

An Innovative Deep Learning Model for Detecting Automobiles and Potholes

It is essential for autonomous driving systems and traffic monitoring systems to be able to recognise cars. When there are potholes on the road, there is an increased likelihood that there will be automotive accidents as well as other types of property damage. In the suggested research, deep learning models were applied. In the process that has been explained, photographs are utilised to identify the kind of vehicle or pothole that is being seen. The model employs both the inception network V2 as well as the region-based convolutional neural network (CNN), which is known for its increased speed. In the suggested study, the You only look once (YOLO) and single-shot detection (SSD) methodologies are contrasted and compared with the faster region-based convolution neural network. The suggested strategy is leagues ahead of conventional alternatives such as ”seize the day” and ”live for today,” both of which may be translated as ”make the most of today.” The accuracy of a metric is used to compare different competitors against one another. The strategy that has been offered offers a 5% improvement over the current standard, which consists of SSD and YOLO.

Improved Traffic Sign Detection Algorithm Based on Faster R-CNN

The traffic sign detection algorithm based on Faster Region-Based Convolutional Neural Network (R-CNN) has been applied to various intelligent-vehicles driving scenarios. However, the model of the current detection algorithm has certain shortcomings, which include the influence of weather and light, the detection of distance traffic signs, and the detection of similar traffic signs. To solve these problems, this paper proposes an improved traffic sign detection method based on Faster R-CNN. First, we propose a fusion method that fuses the feature pyramid into the Faster R-CNN algorithm. This fusion method can extract object features with precision and decrease the influence of weather and light. Second, a deformable convolution (DCN) which can train the algorithm to identify traffic signs with precision and make similar signs more distinguishable, and in particular make it work better with distorted images, is added to the backbone network. Lastly, we apply ROI align to replace the ROI pooling, which can avoid the distant traffic sign detail loss caused by pooling and increase the detection precision of distant traffic signs. The experimental results on both the TT100k dataset and real intelligent vehicle tests demonstrate that the algorithm is superior to the original Faster R-CNN algorithm and four other state-of-the-art methods in traffic sign detection, specifically in small-target traffic sign detection and low-intensity environments such as sunset time and rainy days. Therefore, the proposed method is helpful to improve the traffic sign detection performance in extreme environments (low-light intensity or rainy weather).

COVID-19: Social distancing monitoring using faster-RCNN and YOLOv3 algorithms.

As of March 31, 2021, the Coronavirus COVID-19 was affecting 219 countries and territories worldwide, with approximately 129,574,017 confirmed cases and 2,830,220 death cases. Social isolation is the most reliable way to deal with this pandemic situation. Motivated by this notion, this paper proposes a deep learning-based technique for automating the task of monitoring social distancing using surveillance cameras. To separate humans from the background, the proposed system employs object detection models based on F-RCNN (Faster Region-based Convolutional Neural Networks) and YOLO (You Only Look Once) algorithms. In the COVID-19 environment, these models track the percentage of people who violate social distancing norms on a daily basis. The authors compared the performance of both models in experimental work using the MS COCO dataset. Many tests were carried out, and we discovered that YOLOv3 demonstrated efficient performance with balanced FPS (frames per second).

Identification of Asbestos Slates in Buildings Based on Faster Region-Based Convolutional Neural Network (Faster R-CNN) and Drone-Based Aerial Imagery

Asbestos is a class 1 carcinogen, and it has become clear that it harms the human body. Its use has been banned in many countries, and now the investigation and removal of installed asbestos has become a very important social issue. Accordingly, many social costs are expected to occur, and an efficient asbestos investigation method is required. So far, the examination of asbestos slates was performed through visual inspection. With recent advances in deep learning technology, it is possible to distinguish objects by discovering patterns in numerous training data. In this study, we propose the use of drone images and a faster region-based convolutional neural network (Faster R-CNN) to identify asbestos slates in target sites. Furthermore, the locations of detected asbestos slates were estimated using orthoimages and compiled cadastral maps. A total of 91 asbestos slates were detected in the target sites, and 91 locations were estimated from a total of 45 addresses. To verify the estimated locations, an on-site survey was conducted, and the location estimation method obtained an accuracy of 98.9%. The study findings indicate that the proposed method could be a useful research method for identifying asbestos slate roofs.

Helminth egg analysis platform (HEAP): An opened platform for microscopic helminth egg identification and quantification based on the integration of deep learning architectures.

Millions of people throughout the world suffer from parasite infections. Traditionally, technicians use manual eye inspection of microscopic specimens to perform a parasite examination. However, manual operations have limitations that hinder the ability to obtain precise egg counts and cause inefficient identification of infected parasites on co-infections. The technician requirements for handling a large number of microscopic examinations in countries that have limited medical resources are substantial. We developed the helminth egg analysis platform (HEAP) as a user-friendly microscopic helminth eggs identification and quantification platform to assist medical technicians during parasite infection examination. Multiple deep learning strategies including SSD (Single Shot MultiBox Detector), U-net, and Faster R-CNN (Faster Region-based Convolutional Neural Network) are integrated to identify the same specimen allowing users to choose the best predictions. An image binning and egg-in-edge algorithm based on pixel density detection was developed to increase the performance. Computers with different operation systems can be gathered to lower the computation time using our easy-to-deploy software architecture. A user-friendly interface is provided to substantially increase the efficiency of manual validation. To adapt to low-cost computers, we architected a distributed computing structure with high flexibilities. HEAP serves not only as a prediction service provider but also as a parasitic egg database of microscopic helminth egg image collection, labeling data and pretrained models. All images and labeling resources are free and accessible at http://heap.cgu.edu.tw. HEAP can also be an ideal education and training resource for helminth egg examination.

Weed Identification by Single-Stage and Two-Stage Neural Networks: A Study on the Impact of Image Resizers and Weights Optimization Algorithms.

The accurate identification of weeds is an essential step for a site-specific weed management system. In recent years, deep learning (DL) has got rapid advancements to perform complex agricultural tasks. The previous studies emphasized the evaluation of advanced training techniques or modifying the well-known DL models to improve the overall accuracy. In contrast, this research attempted to improve the mean average precision (mAP) for the detection and classification of eight classes of weeds by proposing a novel DL-based methodology. First, a comprehensive analysis of single-stage and two-stage neural networks including Single-shot MultiBox Detector (SSD), You look only Once (YOLO-v4), EfficientDet, CenterNet, RetinaNet, Faster Region-based Convolutional Neural Network (RCNN), and Region-based Fully Convolutional Network (RFCN), has been performed. Next, the effects of image resizing techniques along with four image interpolation methods have been studied. It led to the final stage of the research through optimization of the weights of the best-acquired model by initialization techniques, batch normalization, and DL optimization algorithms. The effectiveness of the proposed work is proven due to a high mAP of 93.44% and validated by the stratified k-fold cross-validation technique. It was 5.8% improved as compared to the results obtained by the default settings of the best-suited DL architecture (Faster RCNN ResNet-101). The presented pipeline would be a baseline study for the research community to explore several tasks such as real-time detection and reducing the computation/training time. All the relevant data including the annotated dataset, configuration files, and inference graph of the final model are provided with this article. Furthermore, the selection of the DeepWeeds dataset shows the robustness/practicality of the study because it contains images collected in a real/complex agricultural environment. Therefore, this research would be a considerable step toward an efficient and automatic weed control system.

A Development of Robotic Scrub Nurse System - Detection for Surgical Instruments Using Faster Region-Based Convolutional Neural Network –

There is presently a shortage of nurses in Japan, with a further shortage of 3,000–130,000 nurses expected. There is also shortage of scrub nurses. Scrub nurses are nurses who work in the operating room. The main job of scrub nurses is to assist surgeons. Scrub nurses are a high turnover rate, because it is a difficult job. Therefore, system for assisting scrub nurses are needed. The purpose of this study was to develop a robotic scrub nurse. As a first step, a detection system for surgical instruments was developed using the “Faster Region-Based Convolutional Neural Network” (Faster R-CNN). In experiments, computer graphics (CG) model images and 3D-printed model images were evaluated, and the system showed high accuracy. Consequently, the Faster R-CNN system can be considered as suitable for detecting surgical instruments.