YOLOv3 Model Research Articles

A visual positioning method for wedge support robot based on Pruned-Ghost-YOLOv3

The wedge support robot is the core module of the intelligent dismantling equipment for the bolster spring and wedge of railroad wagon. In this paper, to address the problem of accurate positioning of bolster hole with abnormal geometry and large error in the complex background, a light-weight object detection model is proposed based on GhostNet and model pruning algorithm: Pruned-Ghost-YOLOv3. The proposed models and the original YOLOv3 model are trained and evaluated on the bolster hole custom dataset. The results show that the improved Pruned- Ghost-YOLOv3 model is smaller, has fewer parameters and is faster compared to the original YOLOv3 model. To meet the requirements of operational efficiency and reliability, a precise positioning algorithm based on the bounding box of the bolster hole and an indirect positioning process are proposed in this paper. The comparative experiments of bolster hole positioning and wedge support are conducted on the wedge support robot. The experimental results show that the proposed Pruned-Ghost-YOLOv3 model can meet the requirements of rapid detection and positioning of the bolster holes, and the proposed precise positioning algorithm and robot positioning process have high accuracy and reliability. The research results are successfully applied to the development of a railroad wagon wedge support robot, and it has a good reference value for the development of the intelligent positioning system of heterogeneous workpiece operation robots in the complex background of related industries.

ShuffleNetv2-YOLOv3: a real-time recognition method of static sign language based on a lightweight network

To better meet the communication needs of hearing impaired people and the public, it is of great significance to recognize sign language more quickly and accurately on embedded platforms and mobile terminals. YOLOv3, raised by Joseph Redmon and Ali Farhadi in 2018, achieved a great improvement in detection speed with considerable accuracy by optimizing Yolo. However, YOLOv3 is still too bloated to use on mobile terminals. A static sign language recognition method based on the ShuffleNetv2-YOLOv3 lightweight model was proposed. The ShuffleNetv2-YOLOv3 lightweight model makes the network lightweight by using ShuffleNetv2 as the backbone network of YOLOv3. The lightweight network improved the recognition speed steeply. Combing with the CIoU loss function, the ShuffleNetv2-YOLOv3 keeps the recognition accuracy while improving the recognition speed. Recognition effectiveness of the self-made sign language images and public database by the ShuffleNetv2-YOLOv3 lightweight model was evaluated by F1 score and mAP value. The performance of the ShuffleNetv2-YOLOv3 model was compared with that of the YOLOv3-tiny, SSD, Faster-RCNN, and YOLOv4-tiny model, respectively. The experimental results show that the proposed ShuffleNetv2-YOLOv3 model achieved a good balance between the accuracy and speed of the gesture detection under the premise of model lightweight. The F1 score and mAP value of the ShuffleNetv2-YOLOv3 model were 99.1% and 98.4%, respectively. The gesture detection speed on the GPU reaches 54 frames per second, which is better than other models. The mobile terminal application of the proposed lightweight model was also evaluated. The minimal inference speed of single frame images on the CPU and GPU is 0.14 and 0.025 s per image, respectively. It is only 1/6.5 and 1/8.5 of the running speed of the original YOLOv3 model. The ShuffleNetv2-YOLOv3 lightweight model is conducive to quick, real time, and similar static sign language gesture recognition, laying a good foundation for real-time gesture recognition in the embedded platforms and mobile terminals.

Improved Neural Network with Spatial Pyramid Pooling and Online Datasets Preprocessing for Underwater Target Detection Based on Side Scan Sonar Imagery

Fast and high-accuracy detection of underwater targets based on side scan sonar images has great potential for marine fisheries, underwater security, marine mapping, underwater engineering and other applications. The following problems, however, must be addressed when using low-resolution side scan sonar images for underwater target detection: (1) the detection performance is limited due to the restriction on the input of multi-scale images; (2) the widely used deep learning algorithms have a low detection effect due to their complex convolution layer structures; (3) the detection performance is limited due to insufficient model complexity in training process; and (4) the number of samples is not enough because of the bad dataset preprocessing methods. To solve these problems, an improved neural network for underwater target detection—which is based on side scan sonar images and fully utilizes spatial pyramid pooling and online dataset preprocessing based on the You Look Only Once version three (YOLO V3) algorithm—is proposed. The methodology of the proposed approach is as follows: (1) the AlexNet, GoogleNet, VGGNet and the ResNet networks and an adopted YOLO V3 algorithm were the backbone networks. The structure of the YOLO V3 model is more mature and compact and has higher target detection accuracy and better detection efficiency than the other models; (2) spatial pyramid pooling was added at the end of the convolution layer to improve detection performance. Spatial pyramid pooling breaks the scale restrictions when inputting images to improve feature extraction because spatial pyramid pooling enables the backbone network to learn faster at high accuracy; and (3) online dataset preprocessing based on YOLO V3 with spatial pyramid pooling increases the number of samples and improves the complexity of the model to further improve detection process performance. Three-side scan imagery datasets were used for training and were tested in experiments. The quantitative evaluation using Accuracy, Recall, Precision, mAP and F1-Score metrics indicates that: for the AlexNet, GoogleNet, VGGNet and ResNet algorithms, when spatial pyramid pooling is added to their backbone networks, the average detection accuracy of the three sets of data was improved by 2%, 4%, 2% and 2%, respectively, as compared to their original formulations. Compared with the original YOLO V3 model, the proposed ODP+YOLO V3+SPP underwater target detection algorithm model has improved detection performance through the mAP qualitative evaluation index has increased by 6%, the Precision qualitative evaluation index has increased by 13%, and the detection efficiency has increased by 9.34%. These demonstrate that adding spatial pyramid pooling and online dataset preprocessing can improve the target detection accuracy of these commonly used algorithms. The proposed, improved neural network with spatial pyramid pooling and online dataset preprocessing based on the YOLO V3 method achieves the highest scores for underwater target detection results for sunken ships, fish flocks and seafloor topography, with mAP scores of 98%, 91% and 96% for the above three kinds of datasets, respectively.

Finding Patterns of Cyber-Attacks and Creating A Detection Model to Detect Cyber-Attacks Using Machine Learning

This research is a finding and detection type of research. That paper focuses on exploratory data analysis and YOLOv3, you only look once at version three, a real-time recognizing model. The hypothesis of this research are, a cyber-attack gives the same pattern in all the different, different IP addresses, and the research model, the YOLOv3 model can detect the cyber-attack by seeing its pattern. First, the researcher collects more than one hundred seventy-eight thousand data from the cyber department of some companies. Then, the researcher does exploratory data analysis of that data in the jupyter notebook. Then, the researcher finds all the important information about cyber-attacks. Then, the researcher finds the patterns of some cyber-attacks from the information of the data collection. Then, the researcher collects pictures of the patterns. Then, with pictures of those patterns, the researcher labeled those pictures by labellmg software and create a zip file of them. Then the researcher use Google colab and trained, "you only look once version three", the YOLOv3 model to detect the name of the pattern. The machine can detect the pattern and can tell us about what cyber-attack it is by only seeing the picture of the pattern. The researcher finds the patterns for eight IP addresses and in all the IP addresses, the attacks give the same patterns. So, the hypothesis is true in all that cases. By this research model, we can easily know about any kind of cyber-attack in detail and also can find the cyber-attacks by their patterns. So, the researcher use jupyter notebook, Google Colab, and pycharm environment. Pattern study always plays an important role to know about anything. By knowing and learning about anything’s pattern, we can easily understand anything. This research does that thing greatly. The researcher first finds the patterns of some cyber-attacks, then make a model which can detect the cyber-attack by just seeing the pattern.

Precision detection of crop diseases based on improved YOLOv5 model.

Accurate identification of crop diseases can effectively improve crop yield. Most current crop diseases present small targets, dense numbers, occlusions and similar appearance of different diseases, and the current target detection algorithms are not effective in identifying similar crop diseases. Therefore, in this paper, an improved model based on YOLOv5s was proposed to improve the detection of crop diseases. First, the CSP structure of the original model in the feature fusion stage was improved, and a lightweight structure was used in the improved CSP structure to reduce the model parameters, while the feature information of different layers was extracted in the form of multiple branches. A structure named CAM was proposed, which can extract global and local features of each network layer separately, and the CAM structure can better fuse semantic and scale inconsistent features to enhance the extraction of global information of the network. In order to increase the number of positive samples in the model training process, one more grid was added to the original model with three grids to predict the target, and the formula for the prediction frame centroid offset was modified to obtain the better prediction frame centroid offset when the target centroid falled on the special point of the grid. To solve the problem of the prediction frame being scaled incorrectly during model training, an improved DIoU loss function was used to replace the GIoU loss function used in the original YOLOv5s. Finally, the improved model was trained using transfer learning, the results showed that the improved model had the best mean average precision (mAP) performance compared to the Faster R-CNN, SSD, YOLOv3, YOLOv4, YOLOv4-tiny, and YOLOv5s models, and the mAP, F1 score, and recall of the improved model were 95.92%, 0.91, and 87.89%, respectively. Compared with YOLOv5s, they improved by 4.58%, 5%, and 4.78%, respectively. The detection speed of the improved model was 40.01 FPS, which can meet the requirement of real-time detection. The results showed that the improved model outperformed the original model in several aspects, had stronger robustness and higher accuracy, and can provide better detection for crop diseases.

Rice Plaque Detection and Identification Based on an Improved Convolutional Neural Network

Rice diseases are extremely harmful to rice growth, and achieving the identification and rapid classification of rice disease spots is an essential means to promote intelligent rice production. However, due to the large variety of rice diseases and the similar appearance of some rice diseases, the existing deep learning methods are less effective at classification and detection. Aiming at such problems, this paper took the spot images of five common rice diseases as the research object and constructed a rice disease data set containing 2500 images of rice bacterial blight, sheath blight, flax leaf spot, leaf streak and rice blast, including 500 images of each disease. An improved lightweight deep learning network model was proposed to realize the accurate identification of disease types and disease spots. A rice disease image classification network was designed based on the RlpNet (rice leaf plaque net) network model, Which is the underlying network, in addition to the YOLOv3 target detection network model in order to achieve the optimization of the feature extraction link, i.e., upsampling by transposed convolution and downsampling by dilated convolution. The improved YOLOv3 model was compared with traditional convolutional neural network models, including the AlexNet, GoogLeNet, VGG-16 and ResNet-34 models, for disease recognition, and the results showed that the average recall, average precision, average F1-score and overall accuracy of the network model for rice disease classification were 91.84%, 92.14%, 91.87% and 91.84%, respectively, which were all improved compared with the traditional algorithms. The improved YOLOv3 network model was compared with FSSD, Faster-RCNN, YOLOv3 and YOLOv4 for spot detection studies, and the results showed that it could achieve a mean average precision (mAP) of 86.72%, a detection rate (DR) of 93.92%, a frames per second (FPS) rate of 63.4 and a false alarm rate (FAR) of only 5.12%. In summary, the comprehensive performance of the proposed model was better than that of the traditional YOLOv3 algorithm, so this study provides a new method for rice disease identification and disease spot detection. It also had good performance in terms of the common detection and classification of multiple rice diseases, which provides some support for the common differentiation of multiple rice diseases and has some practical application value.

A New Pest Detection Method Based on Improved YOLOv5m.

Pest detection in plants is essential for ensuring high productivity. Convolutional neural networks (CNN)-based deep learning advancements recently have made it possible for researchers to increase object detection accuracy. In this study, pest detection in plants with higher accuracy is proposed by an improved YOLOv5m-based method. First, the SWin Transformer (SWinTR) and Transformer (C3TR) mechanisms are introduced into the YOLOv5m network so that they can capture more global features and can increase the receptive field. Then, in the backbone, ResSPP is considered to make the network extract more features. Furthermore, the global features of the feature map are extracted in the feature fusion phase and forwarded to the detection phase via a modification of the three output necks C3 into SWinTR. Finally, WConcat is added to the fusion feature, which increases the feature fusion capability of the network. Experimental results demonstrate that the improved YOLOv5m achieved 95.7% precision rate, 93.1% recall rate, 94.38% F1 score, and 96.4% Mean Average Precision (mAP). Meanwhile, the proposed model is significantly better than the original YOLOv3, YOLOv4, and YOLOv5m models. The improved YOLOv5m model shows greater robustness and effectiveness in detecting pests, and it could more precisely detect different pests from the dataset.

A deeper generative adversarial network for grooved cement concrete pavement crack detection

Periodic grooved cement concrete pavement crack detection is of great importance for pavement condition monitoring and maintenance. The current state-of-the-art (SOTA) detection solutions highly depend on datasets. However, due to the limited access to crack images, more efficient methods are urgently needed to advance the detection of cracking on grooved cement concrete pavement. This study proposes an improved deeper Wasserstein generative adversarial network with gradient penalty (WGAN-GP) to generate datasets of pavement images with a size of 512 × 512 pixels 2. Poisson bleeding is adopted to create the synthesized grooved cement concrete pavement crack images based on the generated crack images and groove images. The robustness of the proposed improved deeper WGAN-GP model is validated by Faster R-CNN, YOLOv3, and YOLOv4 models trained on original crack images and generated crack images for region-level detection. U-Net and W-segnet are used to achieve pixel-level crack detection to evaluate the effectiveness of proposed model. Results show that the improved deeper WGAN-GP could generate more realistic transverse, longitudinal and oblique crack images. In addition, the Poisson bleeding algorithm contributes to synthesizing grooved cement concrete pavement crack images. Moreover, it is observed that YOLOv3 trained by the augmented dataset could achieve a mean average precision (MAP) of 81.98%, 6% MAP higher than the non-augmented dataset. U-Net and W-segnet benefit from augmented dataset with a better pixel-level segmentation result. Based on the results, it can be concluded that the improved deeper WAGN-GP image generation method can provide a straightforward way to fill the data shortage gap of grooved cement concrete pavement cracks, thus increasing the problem-solving capability of the SOTA crack detection models.

Accurate diagnosis of liver diseases through the application of deep convolutional neural network on biopsy images

<abstract> <p>Accurate detection of non-alcoholic fatty liver disease (NAFLD) through biopsies is challenging. Manual detection of the disease is not only prone to human error but is also time-consuming. Using artificial intelligence and deep learning, we have successfully demonstrated the issues of the manual detection of liver diseases with a high degree of precision. This article uses various neural network-based techniques to assess non-alcoholic fatty liver disease. In this investigation, more than five thousand biopsy images were employed alongside the latest versions of the algorithms. To detect prominent characteristics in the liver from a collection of Biopsy pictures, we employed the YOLOv3, Faster R-CNN, YOLOv4, YOLOv5, YOLOv6, YOLOv7, YOLOv8, and SSD models. A highlighting point of this paper is comparing the state-of-the-art Instance Segmentation models, including Mask R-CNN, U-Net, YOLOv5 Instance Segmentation, YOLOv7 Instance Segmentation, and YOLOv8 Instance Segmentation. The extent of severity of NAFLD and non-alcoholic steatohepatitis was examined for liver cell ballooning, steatosis, lobular, and periportal inflammation, and fibrosis. Metrics used to evaluate the algorithms' effectiveness include accuracy, precision, specificity, and recall. Improved metrics are achieved by optimizing the hyperparameters of the associated models. Additionally, the liver is scored in order to analyse the information gleaned from biopsy images. Statistical analyses are performed to establish the statistical relevance in evaluating the score for different zones.</p> </abstract>

Recognition and Location of Pepper Picking Based on Improved YOLOv5s and Depth Camera

HighlightsAn improved YOLOv5s deep learning model was used to identify peppers in complex background.The deep-level features on 3D (O-XYZ) coordinate of peppers were extracted using RealSense depth camera.An image database set of pepper in different scenes was established.A pepper recognition and location system were constructed based on improved YOLOv5s network.The proposed method achieved a mean average precision of 95.6% and minimum depth error of 0.001 m.Abstract. In order to investigate the impact of different scenes on the recognition performance and obtain the location information of picking targets, the recognition and location system based on improved YOLOv5s network and RealSense depth camera was constructed in this study. An image database in different scenes was established including light intensity, occlusion and overlap degree of pepper. An improved YOLOv5s deep learning model with bidirectional feature pyramid network (BiFPN) was used for the deep feature extraction and high-precision detection of pepper, and the effects of different scenes on recognition accuracy of the model were studied. The results showed that mean average precision (mAP) of YOLOv5s model reached 0.956, which was respectively 6.1%, 9.3%, 44.4%, and 8.2% higher than that of YOLOv4, YOLOv3, YOLOv2, and Faster R-CNN model. The model had good robustness under daytime and evening scenes with the mAP value higher than 0.9. The detection accuracy of the model in the leaf occlusion scenes was better than that of fruit overlap. The detection error was 0.001m which could not affect the picking positioning precision when the Z value of three-dimensional coordinates (O-XYZ) of pepper was 0.2 m. The improved algorithm can accurately recognize and extract three-dimensional coordinates of pepper, which reduces the calculations by eliminating lots of duplicate and redundant prediction boxes and provides a reference for trajectory planning of pepper picking operation. Keywords: Different scenes, Pepper recognition and location, Picking operation, YOLOv5s.

An Accurate and Fast Animal Species Detection System for Embedded Devices

Encounters between humans and wildlife often lead to injuries, especially in remote wilderness regions, and highways. Therefore, animal detection is a vital safety and wildlife conservation component that can mitigate the negative impacts of these encounters. Deep learning techniques have achieved the best results compared to other object detection techniques; however, they require many computations and parameters. A lightweight animal species detection model based on YOLOv2 was proposed. It was designed as a proof of concept of and as a first step to build a real-time mitigation system with embedded devices. Multi-level features merging is employed by adding a new pass-through layer to improve the feature extraction ability and accuracy of YOLOv2. Moreover, the two repeated 3 × 3 convolutional layers in the seventh block of the YOLOv2 architecture are removed to reduce computational complexity, and thus increase detection speed without reducing accuracy. Animal species detection methods based on regular Convolutional Neural Networks (CNNs) have been widely applied; however, these methods are difficult to adapt to geometric variations of animals in images. Thus, a modified YOLOv2 with the addition of deformable convolutional layers (DCLs) was proposed to resolve this issue. Our experimental results show that the proposed model outperforms the original YOLOv2 by 5.0% in accuracy and 12.0% in speed. Furthermore, our analysis shows that the modified YOLOv2 model is more suitable for deployment than YOLOv3 and YOLOv4 on embedded devices.

Region-of-interest based video coding strategy for rate/energy-constrained smart surveillance systems using WMSNs

Video surveillance systems that involve embedded visual sensor nodes have significant constraints due to their limited energy sources. Reducing the power consumption of the in-node processing and the required bandwidth while maintaining a high QoS is still a challenging task. The difficulty increases when a smart task must be performed on the received video in the destination. In this context, this paper proposes an energy-efficient video coding strategy based on a new and fast region-of-interest (ROI) detection method. The lightweight ROI detection method segments the frame into four regions. And the coding strategy aims to extract two different classes of the ROI for coding and transmission using variable quality levels based on their relevance. Furthermore, the strategy aims to exclude the regions of lower importance and any non-ROI that has insignificant movement. We assess the strategy’s ability to perform object recognition tasks at the destination under quality degradation. The performance results using different datasets demonstrate a better trade-off between awareness of ROI quality, energy consumption and bandwidth savings for the proposed strategy compared to other methods. This results in 96% reduction of bandwidth and 93% reduction in energy for some sequences at the expense of a 1-4 dB decrease in PSNR when compared to MJPEG standard. While the recognition accuracy of the YOLOv3 model at the destination outperforms the other techniques by about 4% to 22%.

Tomato detection based on convolutional neural network for robotic application

AbstractThe development of agricultural robots and the promotion of agricultural production automation are important means to alleviate the shortage of agricultural labor. Fruit and vegetable detection is a prerequisite for accurate harvesting by robots. It directly determines the efficiency and quality of harvesting operations. In order to meet the requirements of target positioning and recognition of tomato harvesting robots, this paper studies tomato recognition technology based on YOLOv3 convolutional neural network algorithm. And the tomato detection process of the YOLOv3 model is presented. The YOLOv3 model training dataset is constructed based on greenhouse tomato plants. The test results show that the model based on the YOLOv3 convolutional neural network has a better detection effect.

A novel method for multiple object detection on road using improved YOLOv2 model

Artificial Intelligence has a wide range of uses. AI is currently solely used in the areas of object identification and speech recognition. Object detection is a branch of machine vision and image processing that deals with instances of a certain class of semantic items. One of the most significant habits of object detection in intelligent transportation schemes is vehicle detection. Its aim is to extract clear-cut vehicle-type information from photographs or videos of automobiles. Object detection is critical in self-driving cars. A fully convolutional network (FCN) is employed in sophisticated driver assistance systems for high performance and quick object identification (ADAS). A novel vehicle detection model employing YOLOv2 is presented to tackle the difficulties of prevailing vehicle detection, such as the absence of vehicle-type recognition, stumpy detection accuracy and sluggish speed. The detection model is trained using the VOC and COCO datasets, and the detection enactment is evaluated quantitatively using KITTI training pictures. In addition, the performance of the YOLOv2 model was compared to that of prior models.

Detecting volunteer cotton plants in a corn field with deep learning on UAV remote-sensing imagery

Volunteer cotton (VC) plants growing in the fields of inter-seasonal and rotated crops, like corn, can serve as hosts to boll weevil pests once they reach pin-head square stage (5–6 leaf stage). The VC plants therefore need to be detected, located, and destroyed or sprayed. In this paper, we present a study on using deep learning (DL) to detect VC plants in a corn field using RGB images collected with an unmanned aerial vehicle (UAV). The objectives were (i) to determine whether the YOLOv3 DL algorithm could be used for VC detection in a corn field based on UAV-derived RGB images, and (ii) to investigate the behavior of YOLOv3 on images at three different pixel scales (320 × 320, S1; 416 × 416, S2; and 512 × 512, S3). The metrics used to evaluate the results were average precision (AP), mean average precision (mAP) and F1-score at 95 % confidence level. It was found that YOLOv3 was able to detect VC plants in corn field at an average detection accuracy of more than 80 %, F1-score of 78.5 % and mAP of 80.38 %. With respect to images size, no significant differences existed for mAP among the three scales, but a significant difference was found for AP between S1 and S3 (p = 0.04) and between S2 and S3 (p = 0.02). A significant difference was also found for F1-score between S2 and S3 (p = 0.02). The overall goal of this study was to minimize boll weevil pest infestation by maximizing the true positive detection of VC plants in a corn field which is represented by the mAP values. The lack of significant differences of these at all three scales indicated that the trained YOLOv3 model can be used for VC detection irrespective of the three input image sizes. The capability of YOLOv3 to detect VC plants demonstrates the potential of DL algorithms for real-time detection and mitigation using computer vision and a spot-spray capable UAV.

Promotion of Color Sorting in Industrial Systems Using a Deep Learning Algorithm

Color sorting is a technological operation performed with the aim of classifying compliant and noncompliant agricultural products in large-capacity industrial systems for agricultural product processing. This paper investigates the application of the YOLOv3 algorithm on raspberry images as a method developed for the detection, localization, and classification of objects based on convolutional neural networks (CNNs). To our knowledge, this is the first time a YOLO algorithm or CNN has been used with original images from the color sorter to focus on agricultural products. Results of the F1 measure were in the 92–97% range. Images in full resolution, 1024 × 1024, produced an average detection time of 0.37 s. The impact of the hyperparameters that define the YOLOv3 model as well as the impact of the application of the chosen augmentative methods on the model are evaluated. The successful classification of stalks, which is particularly challenging due to their shape, small dimensions, and variations, was achieved. The presented model demonstrates the ability to classify noncompliant products into four classes, some of which are appropriate for reprocessing. The software, including a graphic interface that enables the real-time testing of machine learning algorithm, is developed and presented.

Deep learning based channel estimation optimization in VLC systems

This paper aims to improve the channel estimation (CE) in the indoor visible light communication system. The proposal of this paper deals with a system that depends on a comparison between Deep Neural Network (DNN), Yolo v3, and Kalman filter (KF) algorithm, for two optical modulation techniques; asymmetrically clipped optical-orthogonal frequency-division multiplexing (ACO-OFDM) and direct current optical-orthogonal frequency division multiplexing (DCO-OFDM). The CE can be evaluated by the error rates in the received bits, where increased error means a performance decrease of the system and vice versa. Receiving less errors at the receiver indicates improved CE and system performance. Hence, the main aim of our work is to decrease the error rate by using different estimators. Furthermore, we apply automatic hyper-parameter approach and Bayesian optimization, to Yolo v3 model to improve the system performance and reduce the positioning error. The metric parameter of bit error rate (BER) aims to determine the improvement ratio in different systems. The model in this paper is based on training with OFDM samples of signal with labels which are received and are corresponding to the signals of OFDM. At a BER = 10−3 with DCO-OFDM, the DNN outperforms KF with 1.7 dB (8.09%) at the bit energy per noise (E_{b} {/}N_{o} ) axis. Also, for ACO-OFDM at BER = 10−3, the DNN achieves better results than KF by about 1.9 dB (11.8%) at the (E_{b} {/}N_{o} ){ } axis. For different values of M in QAM, the DNN outperforms KF for ACO-OFDM by average improvement of ~ 1.2 dB (~ 13%).

Deep learning-based detection of tie bars in concrete pavement using ground penetrating radar

ABSTRACT Detection of the tie bars in concrete pavement has been a challenging task. To address the purpose, ground penetrating radar (GPR) was used to acquire a large amount of image data along the longitudinal construction joints of plain concrete pavement in the field. The GPR image data was filtered to construct the dataset, containing 2185 tie bar reflected waves in 670 GPR images. Then, the YOLO series models, as the deep learning algorithms applied in inspecting the tie bars from GPR images, were well trained with the GPR training and validation sets. The comprehensive detection accuracy of the YOLOv4 model outperforms the YOLOv3, YOLOv3-tiny, and YOLOv4-tiny models in the test set. The mAP@0.5 value of the YOLOv4 model can reach 99.74%. All the signatures of tie bars in the testing GPR images, no matter whether they are incomplete, compressed, blurry with missing signal, or strong background noise, can be correctly and completely anchored using the bounding box based on the YOLOv4 model. Meanwhile, the detection speed of the YOLOv4 model for GPR data video is 50.8 frames per second. Therefore, the YOLOv4 model is reliable for automatically detecting the tie bars from GPR data in real-time.

Automatic recognition of pavement cracks from combined GPR B-scan and C-scan images using multiscale feature fusion deep neural networks

Pavement crack detection is critical for transportation infrastructure assessment using ground penetrating radar (GPR). This paper describes a YOLOv3 model with four-scale detection layers (FDL) to detect combined B-scan and C-scan GPR images subject to poor detection effects and a high missed detection rate of small crack feature sizes. Multiscale fusion structures, efficient intersection over union (EIoU) loss function, K-means++ clustering, and hyperparameter optimization were used in this proposed model to further improve detection performance. Results indicated that the F1 score and mAP of the YOLOv3-FDL model reached 88.1% and 87.8% and had an 8.8% and 7.5% improvement on the GPR dataset of concealed cracks, respectively, compared with the YOLOv3 model. This illustrated that this model solved the problem of missed crack detection to some extent. Future studies can take these results further, especially the three-dimensional feature analysis of pavement cracks.

Performance Evaluation of Deep Learning Algorithm Using High-End Media Processing Board in Real-Time Environment

Image processing-based artificial intelligence algorithm is a critical task, and the implementation requires a careful examination for the selection of the algorithm and the processing unit. With the advancement of technology, researchers have developed many algorithms to achieve high accuracy at minimum processing requirements. On the other hand, cost-effective high-end graphical processing units (GPUs) are now available to handle complex processing tasks. However, the optimum configurations of the various deep learning algorithms implemented on GPUs are yet to be investigated. In this proposed work, we have tested a Convolution Neural Network (CNN) based on You Only Look Once (YOLO) variants on NVIDIA Jetson Xavier to identify compatibility between the GPU and the YOLO models. Furthermore, the performance of the YOLOv3, YOLOv3-tiny, YOLOv4, and YOLOv5s models is evaluated during the training using our PowerEdge Dell R740 Server. We have successfully demonstrated that YOLOV5s is a good benchmark for object detection, classification, and traffic congestion using the Jetson Xavier GPU board. The YOLOv5s achieved an average precision of 95.9% among all YOLO variants and the highest success rate achieved is 98.89.