Faster Region-based Convolutional Neural Network Research Articles

Human Detection and Action Recognition for Search and Rescue in Disasters Using YOLOv3 Algorithm

Drone examination has been overall quickly embraced by NDMM (natural disaster mitigation and management) division to survey the state of impacted regions. Manual video analysis by human observers takes time and is subject to mistakes. The human identification examination of pictures caught by drones will give a practical method for saving lives who are being trapped under debris during quakes or in floods and so on. Drone investigation for research and security and search and rescue (SAR) should involve the drone to filter the impacted area using a camera and a model of unmanned area vehicles (UAVs) to identify specific locations where assistance is required. The existing methods (Balmukund et al. 2020) used were faster-region based convolutional neural networks (F-RCNNs), single shot detector (SSD), and region-based fully convolutional network (R-FCN) for the detection of human and recognition of action. Some of the existing methods used 700 images with six classes only, whereas the proposed model uses 1996 images with eight classes. The proposed model is used YOLOv3 (you only look once) algorithm for the detection and recognition of actions. In this study, we provide the fundamental ideas underlying an object detection model. To find the most effective model for human recognition and detection, we trained the YOLOv3 algorithm on the image dataset and evaluated its performance. We compared the outcomes with the existing algorithms like F-RCNN, SSD, and R-FCN. The accuracies of F-RCNN, SSD, R-FCN (existing algorithms), and YOLOv3 (proposed algorithm) are 53%, 73%, 93%, and 94.9%, respectively. Among these algorithms, the YOLOv3 algorithm gives the highest accuracy of 94.9%. The proposed work shows that existing models are inadequate for critical applications like search and rescue, which convinces us to propose a model raised by a pyramidal component extracting SSD in human localization and action recognition. The suggested model is 94.9% accurate when applied to the proposed dataset, which is an important contribution. Likewise, the suggested model succeeds in helping time for expectation in examination with the cutting-edge identification models with existing strategies. The average time taken by our proposed technique to distinguish a picture is 0.40 milisec which is a lot better than the existing method. The proposed model can likewise distinguish video and can be utilized for real-time recognition. The SSD model can likewise use to anticipate messages if present in the picture.

Prediction of tear propagation path of stratospheric airship envelope material based on deep learning

Tear propagation of the envelope material could cause fatal damage to the stratospheric airship (SSA) and it is very important to detect the crack and predict its tear propagation path. A hybrid deep neural network (DNN) model is proposed in this paper to predict tear propagation of the SSA envelope material mainly including stress field predictor and crack map predictor by considering the time and spatial characteristics. The Gated Recurrent Unit (GRU) is applied by using the gating network signaling that control how the present input and previous memory for the stress field predictor. A Feature Pyramid Network (FPN)-based faster region-based Convolutional Neural Network (CNN) is proposed to predict the crack location by declaring the crack propagation direction and velocity of the envelope material. Furthermore, two deformable operation modules are embedded into the crack detector to achieve better identification of out-of-plane cracks of the envelope material for a real airship with curvature. The dataset is obtained by extended finite element method (XFEM) analysis. The proposed approach has potential applications in the field of envelope material design and structural health monitoring of the SSA.

Identifying Mango and Its Ripeness Using Image Processing and Machine Learning Approach

Fruit market is a subject of choice, thereby, a dealer needs to grade the fruit. Fruit grading commercially available systems are very expensive, and manual fruit grading systems used in small businesses and dealers are prone to human error and inaccuracy. This paper proposes a system for identifying and grading Mango which will bebeneficial if we consider Industry 4.0. A Faster Region-based Convolutional Neural Network (Faster R-CNN) object detection algorithm using Tensor Flow has been implemented for identifying the fruit and by Image processing the probable percentage of ripeness can be determined. Thereby categorizing the fruit into classes. The results show that the proposed methods are efficient and cost-effective for determining and detecting the ripeness of fruits. The same system, when trained effectively can be used for multiple fruits.

Scene Recognition for Construction Projects Based on the Combination Detection of Detailed Ground Objects

The automatic identification of construction projects, which can be considered as complex scenes, is a technical challenge for the supervision of soil and water conservation in urban areas. Construction projects in high-resolution remote sensing images have no unified semantic definition, thereby exhibiting significant differences in image features. This paper proposes an identification method for construction projects based on the detection of detailed ground objects, which construction projects comprise, including movable slab houses, buildings under construction, dust screens, and bare soil (rock). To create the training data set, we select highly informative detailed ground objects from high-resolution remote sensing images. Then, the Faster RCNN (region-based convolutional neural network) algorithm is used to detect construction projects and the highly informative detailed ground objects separately. The merging of detection boxes and the correction of detailed ground object combinations are used to jointly improve the confidence of construction project detection results. The empirical experiments show that the accuracy evaluation indicators of this method on a data set of Wuhan construction projects outperform other comparative methods, and its AP value and F1 score reached 0.773 and 0.417, respectively. The proposed method can achieve satisfactory identification results for construction projects with complex scenes, and can be applied to the comprehensive supervision of soil and water conservation in construction projects.

Crack detection based on deep learning: a method for evaluating the object detection networks considering the random fractal of crack

The visual test for cracks is a tough work for human eyes. With the help of cameras, methods for object detection based on deep learning can detect the cracks automatically from digital images. However, an anomaly is observed that the models for crack detection are obviously underestimated by the widely used mean Average Precision (mAP) standard. In this study, by theoretical analyses about the topology of cracks, we attribute the failure of mAP standard to the random fractal feature. More deeply, this issue is due to the strict box matching during the calculation. To solve this problem, we construct a practical fractal-available evaluation method adopting the idea of covering box matching. Several metrics including Extended Recall (XR), Extended Precision (XP), and Extended F-score (Fext) are defined for scoring the crack detectors. Then, we conduct experiments on several mainstream models for object detection. Results show two advantages of the proposed evaluation method: (1) the proposed metrics evaluate cases better; (2) the proposed evaluation is non-maximum suppression-unrelated. Moreover, we present a case study to optimize a faster region-based convolutional neural networks model for crack detection adopting the proposed metrics. Recall (represented by the XR) of our best model achieves an industrial-level at 95.8%. These results denote that the proposed evaluation method removes the obstacle in evaluating the methods for object detection for cracks, which show great potential for automatic industrial inspections.

Infrared Image Target Detection of Substation Electrical Equipment Using an Improved Faster R-CNN

Infrared camera can be used to monitor the condition of substation electrical equipment. Fast and accurate target detection algorithm is the key for infrared intelligent on-line routing inspection. However, the performance of traditional detection algorithm is poor due to the complex background of substation. To solve this problem, this paper proposes a target detection model based on the improved faster region-based convolutional neural networks (Faster R-CNN), which can be used for automatic detection of five kinds of electrical equipment in substations. The feature extraction network of this model is improved based on VGG16 by abandoning some high-level convolutions to accelerate the training and testing speed. Meanwhile, the 1:3 and 3:1 aspect ratio of anchor are added to improve the detection accuracy of elongated equipment. Experiments are performed on an infrared image dataset of substation to detect five types of equipment. The robustness tests of our model are carried out, too. The results show that our model performs well in detection accuracy and speed, achieving a mean detected accuracy of 95.32% and running at 11 frame/second. In addition, our model is robust to noise and lightness, which is suitable to other substations. Comparing to other models, our model has the highest mAP@0.5 of 92.78%.

Development of a Deep Learning Model for Pothole Detection on Roads to Prevent Traffic Accidents

Vehicle detection is the most crucial component of automated driving and traffic monitoring. Additionally, pothole-caused bad road conditions are to blame for collisions and car damage. Deep learning models are used in the suggested work. In this study, a fast region-based convolutional neural network (Faster R-CNN) and an inception network V2 model were utilized to detect vehicles and potholes in images. To verify the proposed study, Faster R-CNN, Single Shot Detector (SSD), and YOLO algorithms were compared in performance, number of accuracy, detection time, and strengths and weaknesses. Accuracy serves as the benchmark for performance evaluation. When compared to the earlier approaches, such as SSD and YOLO, the suggested method exhibits a 6% improvement.

Soft-masks guided faster region-based convolutional neural network for domain adaptation in wind turbine detection

Wind turbine generator system plays a fundamental role in electricity generation in industry 4.0, and wind turbines are usually distributed separately and in poor locations. Unmanned Aerial Vehicles (UAV) which could overcome the above challenges are deployed to collect photographs of wind turbines, could be used for predictive maintenance of wind turbines and energy management. However, identifying meaningful information from huge amounts of photographs taken by drones is a challenging task due to various scales, different viewpoints, and tedious manual annotation. Besides, deep neural networks (DNN) are dominant in object detection, and training DNN requires large numbers of accurately labeled training data, and manual data annotation is tedious, inefficient, and error-prone. Considering these issues, we generate a synthetic UAV-taken dataset of wind turbines, which provides RGB images, target bounding boxes, and precise pixel annotations as well. But directly transferring the model trained on the synthetic dataset to the real dataset may lead to poor performance due to domain shifts (or domain gaps). The predominant approaches to alleviate the domain discrepancy are adversarial feature learning strategies, which focus on feature alignment for style (e.g., color, texture, illumination, etc.) gaps without considering the content (e.g., densities, backgrounds, and layout scenes) gaps. In this study, we scrutinize the real UAV-taken imagery of wind turbines and develop a synthetic generation method trying to simulate the real ones from the aspects of style and content. Besides, we propose a novel soft-masks guided faster region-based convolutional neural network (SMG Faster R-CNN) for domain adaptation in wind turbine detection, where the soft masks help to extract highly object-related features and suppress domain-specific features. We evaluate the accuracy of SMG Faster R-CNN on the wind turbine dataset and demonstrate the effectiveness of our approach compared with some prevalent object detection models and some adversarial DA models.

An automatic facial landmarking for children with rare diseases.

Two to three thousand syndromes modify facial features: their screening requires the eye of an expert in dysmorphology. A widely used tool in shape characterization is geometric morphometrics based on landmarks, which are precise and reproducible anatomical points. Landmark positioning is user dependent and time consuming. Many automatic landmarking tools are currently available but do not work for children, because they have mainly been trained using photographic databases of healthy adults. Here, we developed a method for building an automatic landmarking pipeline for frontal and lateral facial photographs as well as photographs of external ears. We evaluated the algorithm on patients diagnosed with Treacher Collins (TC) syndrome as it is the most frequent mandibulofacial dysostosis in humans and is clinically recognizable although highly variable in severity. We extracted photographs from the photographic database of the maxillofacial surgery and plastic surgery department of Hôpital Necker-Enfants Malades in Paris, France with the diagnosis of TC syndrome. The control group was built from children admitted for craniofacial trauma or skin lesions. After testing two methods of object detection by bounding boxes, a Haar Cascade-based tool and a Faster Region-based Convolutional Neural Network (Faster R-CNN)-based tool, we evaluated three different automatic annotation algorithms: the patch-based active appearance model (AAM), the holistic AAM, and the constrained local model (CLM). The final error corresponding to the distance between the points placed by automatic annotation and those placed by manual annotation was reported. We included, respectively, 1664, 2044, and 1375 manually annotated frontal, profile, and ear photographs. Object recognition was optimized with the Faster R-CNN-based detector. The best annotation model was the patch-based AAM (p < 0.001 for frontal faces, p=0.082 for profile faces and p < 0.001 for ears). This automatic annotation model resulted in the same classification performance as manually annotated data. Pretraining on public photographs did not improve the performance of the model. We defined a pipeline to create automatic annotation models adapted to faces with congenital anomalies, an essential prerequisite for research in dysmorphology.

A High-Precision Detection Method of Apple Leaf Diseases Using Improved Faster R-CNN

Apple leaf diseases seriously affect the sustainable production of apple fruit. Early infection monitoring of apple leaves and timely disease control measures are the key to ensuring the regular growth of apple fruits and achieving a high-efficiency economy. Consequently, disease detection schemes based on computer vision can compensate for the shortcomings of traditional disease detection methods that are inaccurate and time-consuming. Nowadays, to solve the limitations ranging from complex background environments to dense and small characteristics of apple leaf diseases, an improved Faster region-based convolutional neural network (Faster R-CNN) method was proposed. The advanced Res2Net and feature pyramid network architecture were introduced as the feature extraction network for extracting reliable and multi-dimensional features. Furthermore, RoIAlign was also employed to replace RoIPool so that accurate candidate regions will be produced to address the object location. Moreover, soft non-maximum suppression was applied for precise detection performance of apple leaf disease when making inferences to the images. The improved Faster R-CNN structure behaves effectively in the annotated apple leaf disease dataset with an accuracy of 63.1% average precision, which is higher than other object detection methods. The experiments proved that our improved Faster R-CNN method provides a highly precise apple leaf disease recognition method that could be used in real agricultural practice.

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.

Detecting pediatric wrist fractures using deep-learning-based object detection.

Missed fractures are the leading cause of diagnostic error in the emergency department, and fractures of pediatric bones, particularly subtle wrist fractures, can be misidentified because of their varying characteristics and responses to injury. This study evaluated the utility of an object detection deep learning framework for classifying pediatric wrist fractures as positive or negative for fracture, including subtle buckle fractures of the distal radius, and evaluated the performance of this algorithm as augmentation to trainee radiograph interpretation. We obtained 395 posteroanterior wrist radiographs from unique pediatric patients (65% positive for fracture, 30% positive for distal radial buckle fracture) and divided them into train (n = 229), tune (n = 41) and test (n = 125) sets. We trained a Faster R-CNN (region-based convolutional neural network) deep learning object-detection model. Two pediatric and two radiology residents evaluated radiographs initially without the artificial intelligence (AI) assistance, and then subsequently with access to the bounding box generated by the Faster R-CNN model. The Faster R-CNN model demonstrated an area under the curve (AUC) of 0.92 (95% confidence interval [CI] 0.87-0.97), accuracy of 88% (n = 110/125; 95% CI 81-93%), sensitivity of 88% (n = 70/80; 95% CI 78-94%) and specificity of 89% (n = 40/45, 95% CI 76-96%) in identifying any fracture and identified 90% of buckle fractures (n = 35/39, 95% CI 76-97%). Access to Faster R-CNN model predictions significantly improved average resident accuracy from 80 to 93% in detecting any fracture (P < 0.001) and from 69 to 92% in detecting buckle fracture (P < 0.001). After accessing AI predictions, residents significantly outperformed AI in cases of disagreement (73% resident correct vs. 27% AI, P = 0.002). An object-detection-based deep learning approach trained with only a few hundred examples identified radiographs containing pediatric wrist fractures with high accuracy. Access to model predictions significantly improved resident accuracy in diagnosing these fractures.

Artificial intelligence for automated detection of large mammals creates path to upscale drone surveys

Imagery from drones is becoming common in wildlife research and management, but processing data efficiently remains a challenge. We developed a methodology for training a convolutional neural network model on large-scale mosaic imagery to detect and count caribou (Rangifer tarandus), compare model performance with an experienced observer and a group of naïve observers, and discuss the use of aerial imagery and automated methods for large mammal surveys. Combining images taken at 75 m and 120 m above ground level, a faster region-based convolutional neural network (Faster-RCNN) model was trained in using annotated imagery with the labels: “adult caribou”, “calf caribou”, and “ghost caribou” (animals moving between images, producing blurring individuals during the photogrammetry processing). Accuracy, precision, and recall of the model were 80%, 90%, and 88%, respectively. Detections between the model and experienced observer were highly correlated (Pearson: 0.96–0.99, P value < 0.05). The model was generally more effective in detecting adults, calves, and ghosts than naïve observers at both altitudes. We also discuss the need to improve consistency of observers’ annotations if manual review will be used to train models accurately. Generalization of automated methods for large mammal detections will be necessary for large-scale studies with diverse platforms, airspace restrictions, and sensor capabilities.

An AI-Aided Diagnostic Framework for Hematologic Neoplasms Based on Morphologic Features and Medical Expertise

A morphologic examination is essential for the diagnosis of hematological diseases. However, its conventional manual operation is time-consuming and laborious. Herein, we attempt to establish an artificial intelligence (AI)-aided diagnostic framework integrating medical expertise. This framework acts as a virtual hematological morphologist (VHM) for diagnosing hematological neoplasms. Two datasets were established as follows: An image dataset was used to train the Faster Region-based Convolutional Neural Network to develop an image-based morphologic feature extraction model. A case dataset containing retrospective morphologic diagnostic data was used to train a support vector machine algorithm to develop a feature-based case identification model based on diagnostic criteria. Integrating these 2 models established a whole-process AI-aided diagnostic framework, namely, VHM, and a 2-stage strategy was applied to practice case diagnosis. The recall and precision of VHM in bone marrow cell classification were 94.65% and 93.95%, respectively. The balanced accuracy, sensitivity, and specificity of VHM were 97.16%, 99.09%, and 92%, respectively, in the differential diagnosis of normal and abnormal cases, and 99.23%, 97.96%, and 100%, respectively, in the precise diagnosis of chronic myelogenous leukemia in chronic phase. This work represents the first attempt, to our knowledge, to extract multimodal morphologic features and to integrate a feature-based case diagnosis model for designing a comprehensive AI-aided morphologic diagnostic framework. The performance of our knowledge-based framework was superior to that of the widely used end-to-end AI-based diagnostic framework in terms of testing accuracy (96.88% vs 68.75%) or generalization ability (97.11% vs 68.75%) in differentiating normal and abnormal cases. The remarkable advantage of VHM is that it follows the logic of clinical diagnostic procedures, making it a reliable and interpretable hematological diagnostic tool.

A Conceptual Multi-Layer Framework for the Detection of Nighttime Pedestrian in Autonomous Vehicles Using Deep Reinforcement Learning

The major challenge faced by autonomous vehicles today is driving through busy roads without getting into an accident, especially with a pedestrian. To avoid collision with pedestrians, the vehicle requires the ability to communicate with a pedestrian to understand their actions. The most challenging task in research on computer vision is to detect pedestrian activities, especially at nighttime. The Advanced Driver-Assistance Systems (ADAS) has been developed for driving and parking support for vehicles to visualize sense, send and receive information from the environment but it lacks to detect nighttime pedestrian actions. This article proposes a framework based on Deep Reinforcement Learning (DRL) using Scale Invariant Faster Region-based Convolutional Neural Networks (SIFRCNN) technologies to efficiently detect pedestrian operations through which the vehicle, as agents train themselves from the environment and are forced to maximize the reward. The SIFRCNN has reduced the running time of detecting pedestrian operations from road images by incorporating Region Proposal Network (RPN) computation. Furthermore, we have used Reinforcement Learning (RL) for optimizing the Q-values and training itself to maximize the reward after getting the state from the SIFRCNN. In addition, the latest incarnation of SIFRCNN achieves near-real-time object detection from road images. The proposed SIFRCNN has been tested on KAIST, City Person, and Caltech datasets. The experimental results show an average improvement of 2.3% miss rate of pedestrian detection at nighttime compared to the other CNN-based pedestrian detectors.

Performance analysis of object detection algorithms for robotic welding applications in planar environment

ABSTRACT Weld seam detection and tracking using intelligent techniques is a common task in robotic welding. In this study, vision-based robotic welding is implemented using a 2D Camera to reduce the experimental cost in a planar environment. Firstly, different multi-class object recognition algorithms namely Faster Region-Based Convolutional Neural Network (Faster R-CNN), Single Shot Detector (SSD) and You Look Only Once (YOLOv3) are trained with 1530 manually labeled images. To recognize the weld seam under different brightness levels addressing arc light and splash, Contrast-Limited Adaptive Histogram Equalization (CLAHE) method has been used. Further, an extensive experimental study is conducted to find the optimal hyperparameters among three deep learning models. The performance metrics like Accuracy, Root Mean Square Error, Precision, Recall, Mean Average Precision and F1-score are calculated for different test cases. Finally, homogeneous coordinate transformation is implemented to obtain robot coordinates from weld seam pixel coordinates. The analysis is also extended to detect the bad welding conditions for improper shapes and track the weld seam for good welding shapes using TAL BRABO manipulator. It was found that the weld shapes were accurately detected and tracked precisely with 99.9% accuracy using YOLOv3 than Faster R-CNN and SSD.

An Appropriate Approach to Recognize Coke Size Distribution in a Blast Furnace

The size distribution of coke is important in order to decide the burden layer structure and the burden porosity in the shaft of a blast furnace (BF), which fluctuates daily and can be determined by several parameters. It is measured two or three times per shift by screening the raw material. However, the screening method used is random and takes a lot of time and manpower, resulting in the susceptive size distribution of the raw material and delayed operation of the BF. Therefore, in this paper, a new online approach used to measure the size distribution of particles was selected through comparison. Four common algorithms were used to detect the coke particles from images, including the Marker-based Watershed (MW), Histogram of Oriented Gradient + Support Vector Machine (HOG + SVM), Faster Region-based Convolutional Neural Networks (Faster R-CNN), and You Only Look Once (YOLOv3). The results show that the MW and HOG + SVM were not suitable for coke image detection. The average mean average precisions (mAPs) of Faster R-CNN and YOLOv3 were 93.391% and 91.348%, respectively, which meet the requirements of coke particle recognition. However, the YOLOv3 (5.419 fps) was selected as the final coke particle image detection algorithm, which is about 4.3 times faster than the average detection speed of Faster RCNN (1.269 fps). After this, the YOLOv3 and screening were used to detect 100 coke images and to generate particle size distribution statistics. The results show that the two methods are basically consistent. YOLOv3 can be used in the online measurement of BF coke. This research, which is of important value, provides a basis for the online measurement of the particle size distribution of raw material in a BF.

Comparative Study of Some Deep Learning Object Detection Algorithms: R-CNN, FAST R-CNN, FASTER R-CNN, SSD, and YOLO

Due to its numerous applications and new technological advancements, object detection has gained more attention in the last few years. This study examined various uses of some deep learning object detection algorithms. These algorithms are divided into two-stage detectors like Region Based Convolutional Neural Network (R-CNN), Fast Region Based Convolutional Neural Network (Faster R-CNN), and Faster Region Based Convolutional Neural Network (Faster R-CNN), and one-stage detectors like Single Shot MultiBox Detector (SSD) and You Only Look Once (YOLO) algorithms that are used in text and face detection, image retrieval, security, surveillance, traffic control, traffic sign/light detection, pedestrian detection and in medical areas among others. This research primarily focuses on three applications: drone surveillance, applications relating to traffic, and medical fields. From the analysis performed, it was found that of the various deep learning models used in the various application areas, YOLO, a one-stage detector, is the most popular algorithm for drone surveillance. SSD, another one-stage detector, was primarily used in applications related to traffic, and Faster R-CNN, a two-stage detector, is the most popular algorithm for applications in the medical field

An Adaptive Traffic Lights System using Machine Learning

Traffic congestion is a major problem in many cities of the Hashemite Kingdom of Jordan as in most countries. The rapidly increase of vehicles and dealing with the fixed infrastructure have caused traffic congestion. One of the main problems is that the current infrastructure cannot be expanded further. Therefore, there is a need to make the system work differently with more sophistication to manage the traffic better, rather than creating a new infrastructure. In this research, a new adaptive traffic lights system is proposed to determine vehicles type, calculate the number of vehicles in a traffic junction using patterns detection methods, and suggest the necessary time for each side of the traffic junction using machine learning tools. In this context, the contributions of this paper are: (a) creating a new image-based dataset for vehicles, (b) proposing a new time management formula for traffic lights, and (c) providing literature of many studies that contributed to the development of the traffic lights system in the past decade. For training the vehicle detector, we have created an image-based dataset related to our work and contains images for traffic. We utilized Region-Based Convolutional Neural Networks (R-CNN), Fast Region-Based Convolutional Neural Networks (Fast R-CNN), Faster Region-Based Convolutional Neural Networks (Faster R-CNN), Single Shot Detector (SSD), and You Only Look Once v4 (YOLO v4) deep learning algorithms to train the model and obtain the suggested mathematical formula to the required process and give the appropriate timeslot for every junction. For evaluation, we used the mean Average Precision (mAP) metric. The obtained results were as follows: 78.2%, 71%, 75.2%, 79.8%, and 86.4% for SSD, R-CNN, Fast R-CNN, Faster R-CNN, and YOLO v4, respectively. Based on our experimental results, it is found that YOLO v4 achieved the highest mAP of the identification of vehicles with (86.4%) mAP. For time division (the junctions timeslot), we proposed a formula that reduces about 10% of the waiting time for vehicles.

Detection Method Based on Image Enhancement and an Improved Faster R-CNN for Failed Satellite Components

The components detection of a failed satellite is an important work in space on-orbit service. However, the current detection methods for failed satellite components do not consider the effects of low illumination and small targets on the detection accuracy of components at the same time, and most of the datasets used are manually designed. This article proposes a detection method based on image enhancement and an improved faster region-based convolutional neural network (R-CNN) for small components of a failed satellite in low illumination. First, the dataset of failed satellite components dataset containing low-illumination scenarios is established in a simulated real space environment. Second, an image enhancement based on reflection model and principal component analysis is proposed, which further enhances images while conserving richer details. Finally, an improved faster R-CNN for small components is proposed. To improve the detection accuracy of small components, the original faster R-CNN is improved by modifying three modules: backbone, region proposal network, and region of interest (RoI) pooling layer, respectively [i.e., modified high-resolution neural network (M-HRNet), intersection over union (IoU)-balanced sampling, and RoI align]. Experimental results show that the proposed method can accurately detect all the small components on satellite capture plane, and the detection performance for low illumination and small components is improved significantly compared to the state-of-the-art methods and original faster R-CNN.