Pub Date : 2022-02-10DOI: 10.1142/s0219265921410255
Jithender Reddy Machana, G. Narsimha
In IPv6, the DAD (Duplicate Address Detection) protocol detects duplicate addresses configured on the local link. Once the IPv6 address is auto configured on an IPv6 enabled host, the host verifies that its address is unique using the DAD procedure. This protocol works when hosts can communicate. If the DAD protocol fails to detect duplication, both the hosts assign the same link-local address. The neighbor discovery protocol verifies the generated address is unique or already exists on the local link. This process is known as Duplicate Address Detection (DAD). This process has critical security vulnerability and is susceptible to many attacks, especially allowing hackers to perform denial of service attacks (DOS). With that, the new devices will not be able to join the network. Researchers have developed various techniques to address DAD vulnerabilities, such as NDPMon, SEND, and Software-defined networking, SAVA, and extension headers. These techniques appear to be neither robust nor performance-oriented with DAD’s DOS detection and mitigation techniques. We have proposed a novel approach that detects and mitigates DOS attacks consuming low bandwidth and overhead.
{"title":"Optimization of IPv6 Neighbor Discovery Protocol","authors":"Jithender Reddy Machana, G. Narsimha","doi":"10.1142/s0219265921410255","DOIUrl":"https://doi.org/10.1142/s0219265921410255","url":null,"abstract":"In IPv6, the DAD (Duplicate Address Detection) protocol detects duplicate addresses configured on the local link. Once the IPv6 address is auto configured on an IPv6 enabled host, the host verifies that its address is unique using the DAD procedure. This protocol works when hosts can communicate. If the DAD protocol fails to detect duplication, both the hosts assign the same link-local address. The neighbor discovery protocol verifies the generated address is unique or already exists on the local link. This process is known as Duplicate Address Detection (DAD). This process has critical security vulnerability and is susceptible to many attacks, especially allowing hackers to perform denial of service attacks (DOS). With that, the new devices will not be able to join the network. Researchers have developed various techniques to address DAD vulnerabilities, such as NDPMon, SEND, and Software-defined networking, SAVA, and extension headers. These techniques appear to be neither robust nor performance-oriented with DAD’s DOS detection and mitigation techniques. We have proposed a novel approach that detects and mitigates DOS attacks consuming low bandwidth and overhead.","PeriodicalId":153590,"journal":{"name":"J. Interconnect. Networks","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127753948","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-02-10DOI: 10.1142/s0219265921430349
Xufei Liu, Jinting Liu, Youlong Gong
The traditional low delay transmission model of Internet of things has the problem of high packet loss rate, so a low delay transmission model of Internet of things based on data spectrum is designed. Firstly, the data preprocessing of the Internet of things mainly includes data fusion, data compression and data filtering, then the trust model is established, and finally the task transmission link model of the Internet of things is constructed to realize the low delay transmission of the Internet of things. The experimental results show that the low delay transmission model of IOT based on data spectrum has lower packet loss rate, higher network throughput and higher network resource utilization than the traditional model.
{"title":"Low Delay Transmission Model of Internet of Things Based on Data Spectrum","authors":"Xufei Liu, Jinting Liu, Youlong Gong","doi":"10.1142/s0219265921430349","DOIUrl":"https://doi.org/10.1142/s0219265921430349","url":null,"abstract":"The traditional low delay transmission model of Internet of things has the problem of high packet loss rate, so a low delay transmission model of Internet of things based on data spectrum is designed. Firstly, the data preprocessing of the Internet of things mainly includes data fusion, data compression and data filtering, then the trust model is established, and finally the task transmission link model of the Internet of things is constructed to realize the low delay transmission of the Internet of things. The experimental results show that the low delay transmission model of IOT based on data spectrum has lower packet loss rate, higher network throughput and higher network resource utilization than the traditional model.","PeriodicalId":153590,"journal":{"name":"J. Interconnect. Networks","volume":"112 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114985118","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-02-10DOI: 10.1142/s0219265921480066
Wei Liu, Mohammad Shabaz, Urvashi Garg
To improve the effect of depth information extraction of moving targets in the network, a nonlinear strategy-oriented method is proposed. With the advancement of science and technology, especially in wireless networks, a large amount of data is provided to people every hour of every day. Hence, it can increase the demand for data analysis tools. Nonlinear system modeling by using rough set theory to extract valuable information from large amounts of information, and then through the analytic hierarchy process (ahp) to determine the effect of input factors, then use particle swarm optimization algorithm (PSO) to find the accurate function, and USES the adaptive and population catastrophe and vaccine algorithm to make it to the local optimum, to achieve the aim of the complex. The experimental results show that, compared with M2 and M1 for 30 groups of samples, the model obtained by using M2 has a better fitting effect on the actual curve. The error of M2 is within ±3%, and the error of M1 is within ±6%, and the error is relatively large. The accuracy of the proposed method is higher than that of the neural network method, which proves that the nonlinear strategy is effective in the actual target depth information extraction.
{"title":"Moving Target Depth Information Extraction Based on Nonlinear Strategy Network","authors":"Wei Liu, Mohammad Shabaz, Urvashi Garg","doi":"10.1142/s0219265921480066","DOIUrl":"https://doi.org/10.1142/s0219265921480066","url":null,"abstract":"To improve the effect of depth information extraction of moving targets in the network, a nonlinear strategy-oriented method is proposed. With the advancement of science and technology, especially in wireless networks, a large amount of data is provided to people every hour of every day. Hence, it can increase the demand for data analysis tools. Nonlinear system modeling by using rough set theory to extract valuable information from large amounts of information, and then through the analytic hierarchy process (ahp) to determine the effect of input factors, then use particle swarm optimization algorithm (PSO) to find the accurate function, and USES the adaptive and population catastrophe and vaccine algorithm to make it to the local optimum, to achieve the aim of the complex. The experimental results show that, compared with M2 and M1 for 30 groups of samples, the model obtained by using M2 has a better fitting effect on the actual curve. The error of M2 is within ±3%, and the error of M1 is within ±6%, and the error is relatively large. The accuracy of the proposed method is higher than that of the neural network method, which proves that the nonlinear strategy is effective in the actual target depth information extraction.","PeriodicalId":153590,"journal":{"name":"J. Interconnect. Networks","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125967008","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-02-10DOI: 10.1142/s0219265921430453
Lei Sun
Estimating the relative pose between two calibrated views with 2D-to-2D correspondences is a fundamental problem in computer vision and 2D perception. In this paper, we present the first certifiably globally optimal solver that can simultaneously incorporate both points and lines as the non-minimal 2D-to-2D correspondences for this problem. Our first contribution is to derive a generalized polynomial-based objective function based on the geometric constraints of orthogonal and parallel line pairs. Built upon it, our second contribution is to reformulate the relative pose estimation problem as a constrained global optimization problem with a unified representation of both point and line pair correspondences. Our third contribution lies in relaxing this non-convex optimization problem to a convex Semi-Definite Program (SDP) using Sum of Squares (SOS) relaxations so as to solve it via Gloptipoly 3 with a reliable guarantee of global optimality. In both synthetic and real experiments, we show that adopting line pairs as supplementary correspondences can greatly improve estimation accuracy, especially in the point-sparse situations, and that our solver, named SPLP (SOS-Point-and-Line-Pair), can outperform other state-of-the-art solvers.
{"title":"SPLP: A Certifiably Globally Optimal Solution to the Relative Pose Estimation Problem Using Points and Line Pairs","authors":"Lei Sun","doi":"10.1142/s0219265921430453","DOIUrl":"https://doi.org/10.1142/s0219265921430453","url":null,"abstract":"Estimating the relative pose between two calibrated views with 2D-to-2D correspondences is a fundamental problem in computer vision and 2D perception. In this paper, we present the first certifiably globally optimal solver that can simultaneously incorporate both points and lines as the non-minimal 2D-to-2D correspondences for this problem. Our first contribution is to derive a generalized polynomial-based objective function based on the geometric constraints of orthogonal and parallel line pairs. Built upon it, our second contribution is to reformulate the relative pose estimation problem as a constrained global optimization problem with a unified representation of both point and line pair correspondences. Our third contribution lies in relaxing this non-convex optimization problem to a convex Semi-Definite Program (SDP) using Sum of Squares (SOS) relaxations so as to solve it via Gloptipoly 3 with a reliable guarantee of global optimality. In both synthetic and real experiments, we show that adopting line pairs as supplementary correspondences can greatly improve estimation accuracy, especially in the point-sparse situations, and that our solver, named SPLP (SOS-Point-and-Line-Pair), can outperform other state-of-the-art solvers.","PeriodicalId":153590,"journal":{"name":"J. Interconnect. Networks","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124727989","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-02-10DOI: 10.1142/s0219265921410358
D. Ravisankar, N. Venkateswararao
Cooperative spectrum sensing (CSS) in a cognitive radio uses a fusion center, which receives local sensing decisions from multiple secondary users to predict whether primary user is present or absent. Therefore, an ensemble classifier with heterogenous fusion center (EC-HFC) is proposed in this work, where the ensemble classifier comprise three classification algorithms such as logistic regression (LR), support vector machine (SVM), and gaussian naive bayes (GNB). In addition, voting classifier with its variants also employed for finding the best suitable classifier. Further, the performance metrics such as accuracy, F1-score, area under the curve (AUC), probability of detection and probability of false alarm are computed for evaluating the performance of proposed ensemble classifier-based fusion center for cooperative spectrum sensing in cognitive radio. Finally, the obtained receiver operating characteristics (ROC) and extensive simulation results shows that proposed fusion center resulted in superior performance as compared to individual secondary users.
{"title":"Ensemble Classifier with Heterogenous Fusion Center for Cooperative Spectrum Sensing in Cognitive Radio","authors":"D. Ravisankar, N. Venkateswararao","doi":"10.1142/s0219265921410358","DOIUrl":"https://doi.org/10.1142/s0219265921410358","url":null,"abstract":"Cooperative spectrum sensing (CSS) in a cognitive radio uses a fusion center, which receives local sensing decisions from multiple secondary users to predict whether primary user is present or absent. Therefore, an ensemble classifier with heterogenous fusion center (EC-HFC) is proposed in this work, where the ensemble classifier comprise three classification algorithms such as logistic regression (LR), support vector machine (SVM), and gaussian naive bayes (GNB). In addition, voting classifier with its variants also employed for finding the best suitable classifier. Further, the performance metrics such as accuracy, F1-score, area under the curve (AUC), probability of detection and probability of false alarm are computed for evaluating the performance of proposed ensemble classifier-based fusion center for cooperative spectrum sensing in cognitive radio. Finally, the obtained receiver operating characteristics (ROC) and extensive simulation results shows that proposed fusion center resulted in superior performance as compared to individual secondary users.","PeriodicalId":153590,"journal":{"name":"J. Interconnect. Networks","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129569147","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-02-10DOI: 10.1142/s0219265921480029
Wensheng Yan, Mohammad Shabaz, Manik Rakhra
To study nonlinear distortion image recognition technology. Through the study of neural networks, an image recognition model based on BP neural network is proposed: An improved algorithm for driving quantity factor. According to the established neural network model, 10 commonly used images of Arabic numeral characters are recognized. The effectiveness of the model is verified by experiments with the extracted feature parameters of the target image. The results show that 38 of the 40 distorted images with noise can be correctly identified and 2 of them can be incorrectly identified by the single-stage recognition network, and the recognition rate reaches 95%; the recognition rate of cascade network reaches 100%. Therefore, the BP network which drives the number term can accelerate the training time of the network and improve the recognition efficiency of the system.
{"title":"Research on Nonlinear Distorted Image Recognition Based on Artificial Neural Network Algorithm","authors":"Wensheng Yan, Mohammad Shabaz, Manik Rakhra","doi":"10.1142/s0219265921480029","DOIUrl":"https://doi.org/10.1142/s0219265921480029","url":null,"abstract":"To study nonlinear distortion image recognition technology. Through the study of neural networks, an image recognition model based on BP neural network is proposed: An improved algorithm for driving quantity factor. According to the established neural network model, 10 commonly used images of Arabic numeral characters are recognized. The effectiveness of the model is verified by experiments with the extracted feature parameters of the target image. The results show that 38 of the 40 distorted images with noise can be correctly identified and 2 of them can be incorrectly identified by the single-stage recognition network, and the recognition rate reaches 95%; the recognition rate of cascade network reaches 100%. Therefore, the BP network which drives the number term can accelerate the training time of the network and improve the recognition efficiency of the system.","PeriodicalId":153590,"journal":{"name":"J. Interconnect. Networks","volume":"174 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124252921","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-02-10DOI: 10.1142/s0219265921430416
Qing An, Zhen Gong, Jupu Yuan
Rock mass fraction is one of the main indexes to evaluate the blasting effect of mining. We take some rock blocks after blasting as the research objects and use 3D laser scanner to obtain the point cloud data of rock blocks. Then we use statistical filtering method to process the original point cloud data, and then calculate the point cloud data after pre-processing. We obtain the supervoxel clustering point cloud. On the supervoxel clustering algorithm, the concave convex criterion is used to fuse the clustering results. The regional growth algorithm is used to complete the segmentation of rock point cloud, so as to achieve the purpose of automatic recognition of blasting rock block contour. Based on the segmentation results of the rock block point cloud, the rock block point cloud with obvious characteristics is extracted, and the length of the long axis of the rock block is obtained according to the feature information of the rock block. The results show that the method can solve the defects of traditional measurement methods. The proposed recognition algorithm will meet the requirement of the intelligent of blasting fragmentation analysis. Additionally, it will satisfy the requirements of blasting quality analysis and evaluation.
{"title":"Automatic Recognition and Feature Extraction of Rock Blocks Based on 3D Point Cloud Data Analytics","authors":"Qing An, Zhen Gong, Jupu Yuan","doi":"10.1142/s0219265921430416","DOIUrl":"https://doi.org/10.1142/s0219265921430416","url":null,"abstract":"Rock mass fraction is one of the main indexes to evaluate the blasting effect of mining. We take some rock blocks after blasting as the research objects and use 3D laser scanner to obtain the point cloud data of rock blocks. Then we use statistical filtering method to process the original point cloud data, and then calculate the point cloud data after pre-processing. We obtain the supervoxel clustering point cloud. On the supervoxel clustering algorithm, the concave convex criterion is used to fuse the clustering results. The regional growth algorithm is used to complete the segmentation of rock point cloud, so as to achieve the purpose of automatic recognition of blasting rock block contour. Based on the segmentation results of the rock block point cloud, the rock block point cloud with obvious characteristics is extracted, and the length of the long axis of the rock block is obtained according to the feature information of the rock block. The results show that the method can solve the defects of traditional measurement methods. The proposed recognition algorithm will meet the requirement of the intelligent of blasting fragmentation analysis. Additionally, it will satisfy the requirements of blasting quality analysis and evaluation.","PeriodicalId":153590,"journal":{"name":"J. Interconnect. Networks","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130065694","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-02-10DOI: 10.1142/s0219265921480042
Diansheng Yang, Ming Ji, Yuntong Lv, Fangchu Zhao, Quanfeng Geng, J. Bhola
To explore the partition optimization and stability of telecommunication network under nonlinear control, a routing optimization algorithm for power control of distribution communication network is proposed, which is based on the Ad-hoc On-demand Distance Vector (AODV) routing optimization algorithm, based on the energy consumption model of wireless sensor network, the optimal routing mechanism for power control is constructed, and the optimal routing mechanism is used to select the route with low energy consumption to solve the problem of energy limitation of wireless sensor nodes. This paper aims at the network routing selection problem in the terminal information collection of the distribution network and designs the routing optimization algorithm of the wireless sensor network. Experimental results show that the model accuracy of the optimized model is 99.8%, the average residual error of the model is about 5.5[Formula: see text]nm, the model accuracy meets the requirements, and the method is effective. According to the confidence interval prediction results of wireless communication link reliability, a node power control system structure of wireless sensor network is proposed, and an optimal control algorithm of communication link quality and reliability of microgrid wireless sensor network based on fuzzy control is studied.
{"title":"Research on Zoning, Optimization, Stability, and Nonlinear Control of Wireless Network in Power Grid Communication","authors":"Diansheng Yang, Ming Ji, Yuntong Lv, Fangchu Zhao, Quanfeng Geng, J. Bhola","doi":"10.1142/s0219265921480042","DOIUrl":"https://doi.org/10.1142/s0219265921480042","url":null,"abstract":"To explore the partition optimization and stability of telecommunication network under nonlinear control, a routing optimization algorithm for power control of distribution communication network is proposed, which is based on the Ad-hoc On-demand Distance Vector (AODV) routing optimization algorithm, based on the energy consumption model of wireless sensor network, the optimal routing mechanism for power control is constructed, and the optimal routing mechanism is used to select the route with low energy consumption to solve the problem of energy limitation of wireless sensor nodes. This paper aims at the network routing selection problem in the terminal information collection of the distribution network and designs the routing optimization algorithm of the wireless sensor network. Experimental results show that the model accuracy of the optimized model is 99.8%, the average residual error of the model is about 5.5[Formula: see text]nm, the model accuracy meets the requirements, and the method is effective. According to the confidence interval prediction results of wireless communication link reliability, a node power control system structure of wireless sensor network is proposed, and an optimal control algorithm of communication link quality and reliability of microgrid wireless sensor network based on fuzzy control is studied.","PeriodicalId":153590,"journal":{"name":"J. Interconnect. Networks","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122325431","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-02-09DOI: 10.1142/s0219265921430301
Zhiyong She, Tao Song, Lei Zhang
Attribute reduction is proved to be a non-deterministic polynomial problem (NP). Minimal attribute reduction is the main research content in rough set theory. We find that in the traditional rough set attribute reduction algorithm, the rough set attribute reduction based on discrete particle swarm optimization (DPSO) performs well. However, the fitness function of this method has some limitations. When the minimum attribute reduction result is the conditional attribute set itself, the correct result cannot be obtained. For enhancing the accuracy and efficiency of attribute reduction, we propose an attribute reduction algorithm based on DPSO and variable precision rough set (VPRS). The proposed algorithm uses VPRS to process data more accurately. The new fitness function is constructed, and the attribute dependence is used as the function judgment basis. It can be adjusted automatically as the discrete binary particle swarm evolves, ensuring the convergence speed and evolution direction. Experimental results show that compared with traditional method, the proposed algorithm has stronger effectiveness and higher application value.
{"title":"Attribute Reduction Algorithm Based on Discrete Particle Swarm Optimization and Variable Precision Rough Set","authors":"Zhiyong She, Tao Song, Lei Zhang","doi":"10.1142/s0219265921430301","DOIUrl":"https://doi.org/10.1142/s0219265921430301","url":null,"abstract":"Attribute reduction is proved to be a non-deterministic polynomial problem (NP). Minimal attribute reduction is the main research content in rough set theory. We find that in the traditional rough set attribute reduction algorithm, the rough set attribute reduction based on discrete particle swarm optimization (DPSO) performs well. However, the fitness function of this method has some limitations. When the minimum attribute reduction result is the conditional attribute set itself, the correct result cannot be obtained. For enhancing the accuracy and efficiency of attribute reduction, we propose an attribute reduction algorithm based on DPSO and variable precision rough set (VPRS). The proposed algorithm uses VPRS to process data more accurately. The new fitness function is constructed, and the attribute dependence is used as the function judgment basis. It can be adjusted automatically as the discrete binary particle swarm evolves, ensuring the convergence speed and evolution direction. Experimental results show that compared with traditional method, the proposed algorithm has stronger effectiveness and higher application value.","PeriodicalId":153590,"journal":{"name":"J. Interconnect. Networks","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123626264","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-02-09DOI: 10.1142/s0219265921440102
V. Joshi, Jeena Thomas, Ebin Deni Raj
Coconut is a multipurpose fruit with high economic value and since it is unique to the landscape of Kerala, it plays an important role in the economy of the state. Skilled labour is one of the key components in coconut farming and lack of its availability can hurt its business. Even if this requirement is met, currently practiced traditional methods for plucking the fruit requires the labour to climb the tree which involves a huge risk factor given the height of the tree they have to scale. There are tools that assist in the climb but they can only reduce the risk factor by a small margin. Robotic harvesting is one of the key solutions to the aforementioned problem as it has the ability to perform accurate coconut plucking since it relies on cutting edge object detection modules, it can provide deep insights into the quality of coconuts to be yielded and also excel at working in remote conditions. The primary aim of this paper is to cover the development of a fast as well as accurate perception module for detection of coconuts, which will serve as a strong foundation for any robotic implementation. In this study we try to explore and compare multiple deep learning based object detection frameworks such as Single Shot Detector and YOLO for efficient and accurate deployment on various edge devices like Raspberry Pi and Nvidia jetson nano by using state of the art methods such as quantization aware training, inference accelerators, multiple augmentation strategies (cutmix, mosaic) for best results. We have also curated a novel, manually annotated dataset of drone based coconut videos (effective/usable content of 30 minutes) in order to capture the naturally setting of coconuts i.e. the true distribution of image data containing background noises, occlusion, shadow as well as natural lighting conditions. The peak performance achieved in our study was a frame rate of 12.7 with a mean average precision of 0.4 by using a tiny YOLOv4 on an Nvidia Jetson Nano.
{"title":"Quantized Coconut Detection Models with Edge Devices","authors":"V. Joshi, Jeena Thomas, Ebin Deni Raj","doi":"10.1142/s0219265921440102","DOIUrl":"https://doi.org/10.1142/s0219265921440102","url":null,"abstract":"Coconut is a multipurpose fruit with high economic value and since it is unique to the landscape of Kerala, it plays an important role in the economy of the state. Skilled labour is one of the key components in coconut farming and lack of its availability can hurt its business. Even if this requirement is met, currently practiced traditional methods for plucking the fruit requires the labour to climb the tree which involves a huge risk factor given the height of the tree they have to scale. There are tools that assist in the climb but they can only reduce the risk factor by a small margin. Robotic harvesting is one of the key solutions to the aforementioned problem as it has the ability to perform accurate coconut plucking since it relies on cutting edge object detection modules, it can provide deep insights into the quality of coconuts to be yielded and also excel at working in remote conditions. The primary aim of this paper is to cover the development of a fast as well as accurate perception module for detection of coconuts, which will serve as a strong foundation for any robotic implementation. In this study we try to explore and compare multiple deep learning based object detection frameworks such as Single Shot Detector and YOLO for efficient and accurate deployment on various edge devices like Raspberry Pi and Nvidia jetson nano by using state of the art methods such as quantization aware training, inference accelerators, multiple augmentation strategies (cutmix, mosaic) for best results. We have also curated a novel, manually annotated dataset of drone based coconut videos (effective/usable content of 30 minutes) in order to capture the naturally setting of coconuts i.e. the true distribution of image data containing background noises, occlusion, shadow as well as natural lighting conditions. The peak performance achieved in our study was a frame rate of 12.7 with a mean average precision of 0.4 by using a tiny YOLOv4 on an Nvidia Jetson Nano.","PeriodicalId":153590,"journal":{"name":"J. Interconnect. Networks","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129910260","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：