Pub Date : 2020-05-01DOI: 10.1109/ZINC50678.2020.9161774
Bian Li, Duan Yingli, Li Penghua
This paper proposes a method to improve the weight of Particle swarm optimization (PSO) by using similarity, so as to realize the fast and accurate diagnosis of power grid fault. First, a mathematical model of power grid fault diagnosis is established by analyzing the circuit breaker, equipment protection and action information in the power grid. Next, the model is transformed into a 0-1 integer programming problem. Last, the traditional PSO algorithm is improved, so that the inertia weight in the algorithm can be adjusted dynamically according to the concept of similarity. Simulation results show that the improved PSO greatly increases the convergence speed and efficiency of power grid fault diagnosis.
{"title":"Application of improved PSO algorithm in power grid fault diagnosis","authors":"Bian Li, Duan Yingli, Li Penghua","doi":"10.1109/ZINC50678.2020.9161774","DOIUrl":"https://doi.org/10.1109/ZINC50678.2020.9161774","url":null,"abstract":"This paper proposes a method to improve the weight of Particle swarm optimization (PSO) by using similarity, so as to realize the fast and accurate diagnosis of power grid fault. First, a mathematical model of power grid fault diagnosis is established by analyzing the circuit breaker, equipment protection and action information in the power grid. Next, the model is transformed into a 0-1 integer programming problem. Last, the traditional PSO algorithm is improved, so that the inertia weight in the algorithm can be adjusted dynamically according to the concept of similarity. Simulation results show that the improved PSO greatly increases the convergence speed and efficiency of power grid fault diagnosis.","PeriodicalId":6731,"journal":{"name":"2020 Zooming Innovation in Consumer Technologies Conference (ZINC)","volume":"27 1","pages":"242-247"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81168175","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 : 2020-05-01DOI: 10.1109/ZINC50678.2020.9161446
Branislav Novak, Velibor Ilic, Bogdan Pavković
The ability of perception and understanding all static and dynamic objects around vehicle in various driving and environmental conditions represent one of the main requirements for autonomous vehicles and most of Advanced Driving Assistance Systems (ADAS). Current promise to deliver safe ADAS in modern cars could be achieved by convolutional neural network (CNN). In this paper we present a software based on YOLO that is extended with a CNN for traffic sign recognition. Since real time detection is required for safe driving, YOLO network used in this paper is pre trained for detection and classification of only five objects which are separated in categories such as cars, trucks, pedestrians, traffic signs, and traffic lights. Detected traffic signs are further passed to CNN which can classify them in one of 75 categories. We demonstrate the high level of classification confidence by accurately recognition more than 99.2% of examined signs in quite diverse conditions.
{"title":"YOLOv3 Algorithm with additional convolutional neural network trained for traffic sign recognition","authors":"Branislav Novak, Velibor Ilic, Bogdan Pavković","doi":"10.1109/ZINC50678.2020.9161446","DOIUrl":"https://doi.org/10.1109/ZINC50678.2020.9161446","url":null,"abstract":"The ability of perception and understanding all static and dynamic objects around vehicle in various driving and environmental conditions represent one of the main requirements for autonomous vehicles and most of Advanced Driving Assistance Systems (ADAS). Current promise to deliver safe ADAS in modern cars could be achieved by convolutional neural network (CNN). In this paper we present a software based on YOLO that is extended with a CNN for traffic sign recognition. Since real time detection is required for safe driving, YOLO network used in this paper is pre trained for detection and classification of only five objects which are separated in categories such as cars, trucks, pedestrians, traffic signs, and traffic lights. Detected traffic signs are further passed to CNN which can classify them in one of 75 categories. We demonstrate the high level of classification confidence by accurately recognition more than 99.2% of examined signs in quite diverse conditions.","PeriodicalId":6731,"journal":{"name":"2020 Zooming Innovation in Consumer Technologies Conference (ZINC)","volume":"116 1","pages":"165-168"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77260645","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 : 2020-05-01DOI: 10.1109/ZINC50678.2020.9161800
Tristan Lim
In consumer electronics where sales cycle is about two to three years, and with increased competition and product differentiation faced by suppliers in online distribution channels, it is important to pay attention to targeted marketing in online consumer electronics sales through the use of predictive analytics, as marketing paradigm is becoming increasingly customer-focused and unsolicited marketing is often costly and ineffective due to low response rates. In this study, customer predictive analytical techniques, including the RecencyFrequency Monetary (or RFM) method and classical classification modelling methods – logistic regression, decision tree, neural network and ensemble models – are utilized to improve predictive accuracy. Results from the neural network model shows a significant improvement over RFM model, with positive response rates improving by more than 2x, from 42.9% to 87.2%. However, if stronger explanability power is preferred, decision tree model may be utilized, although predictive accuracy of about 2% is sacrificed. The study discusses predictive modelling useful to improve the performance of positive response rate targeting, alongside the benefits of improved sampling and reduced computing power, especially with significantly large datasets. In real life implementation, it is imperative that companies understand that classification power of the models and marketing campaign targeting are continuous improvement processes. These processes improve with every iteration from its baseline towards its objective threshold level set by the companies’ management. False positive transactions should be investigated, with the effect of incorporating the findings to the improvement of models going forward.
{"title":"RFM and Classification Predictive Modelling to Improve Response Prediction Rate","authors":"Tristan Lim","doi":"10.1109/ZINC50678.2020.9161800","DOIUrl":"https://doi.org/10.1109/ZINC50678.2020.9161800","url":null,"abstract":"In consumer electronics where sales cycle is about two to three years, and with increased competition and product differentiation faced by suppliers in online distribution channels, it is important to pay attention to targeted marketing in online consumer electronics sales through the use of predictive analytics, as marketing paradigm is becoming increasingly customer-focused and unsolicited marketing is often costly and ineffective due to low response rates. In this study, customer predictive analytical techniques, including the RecencyFrequency Monetary (or RFM) method and classical classification modelling methods – logistic regression, decision tree, neural network and ensemble models – are utilized to improve predictive accuracy. Results from the neural network model shows a significant improvement over RFM model, with positive response rates improving by more than 2x, from 42.9% to 87.2%. However, if stronger explanability power is preferred, decision tree model may be utilized, although predictive accuracy of about 2% is sacrificed. The study discusses predictive modelling useful to improve the performance of positive response rate targeting, alongside the benefits of improved sampling and reduced computing power, especially with significantly large datasets. In real life implementation, it is imperative that companies understand that classification power of the models and marketing campaign targeting are continuous improvement processes. These processes improve with every iteration from its baseline towards its objective threshold level set by the companies’ management. False positive transactions should be investigated, with the effect of incorporating the findings to the improvement of models going forward.","PeriodicalId":6731,"journal":{"name":"2020 Zooming Innovation in Consumer Technologies Conference (ZINC)","volume":"24 1","pages":"333-337"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73114556","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 : 2020-05-01DOI: 10.1109/ZINC50678.2020.9161791
Mario Gluhaković, M. Herceg, M. Popovic, J. Kovacevic
In this paper, a method for the vehicles detection in the surroundings of an autonomous vehicle and warnings of potential collision with them is presented. The method, which consists of two parts, is implemented in robot operating system (ROS). The first part is used to detect vehicles in an autonomous vehicle environment, in which, YOLO v2 algorithm, trained on a newly created set of images, is used. The YOLO v2 algorithm is configured to detect four classes of objects: a car, a van, a truck, and a bus. The second part of the proposed method is the ROS node for distance assessment. In particular, two ROS nodes for distance assessment are created; one ROS node used for distance assessment in the Carla simulator, while the other ROS node is used for real-world distance assessment. The testing results of the proposed method show promising results.
{"title":"Vehicle Detection in the Autonomous Vehicle Environment for Potential Collision Warning","authors":"Mario Gluhaković, M. Herceg, M. Popovic, J. Kovacevic","doi":"10.1109/ZINC50678.2020.9161791","DOIUrl":"https://doi.org/10.1109/ZINC50678.2020.9161791","url":null,"abstract":"In this paper, a method for the vehicles detection in the surroundings of an autonomous vehicle and warnings of potential collision with them is presented. The method, which consists of two parts, is implemented in robot operating system (ROS). The first part is used to detect vehicles in an autonomous vehicle environment, in which, YOLO v2 algorithm, trained on a newly created set of images, is used. The YOLO v2 algorithm is configured to detect four classes of objects: a car, a van, a truck, and a bus. The second part of the proposed method is the ROS node for distance assessment. In particular, two ROS nodes for distance assessment are created; one ROS node used for distance assessment in the Carla simulator, while the other ROS node is used for real-world distance assessment. The testing results of the proposed method show promising results.","PeriodicalId":6731,"journal":{"name":"2020 Zooming Innovation in Consumer Technologies Conference (ZINC)","volume":"100 1","pages":"178-183"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73734153","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 : 2020-05-01DOI: 10.1109/ZINC50678.2020.9161819
Zahra Pezeshki, Ali Gholipour Soleimani, A. Darabi
This paper offers a novel method with the help of Genetic Algorithm (GA) to find the optimal solution for determining the HVAC location. It wants to follow a world optimal solution to find the best result by removing the limitations such as unknown fitness conditions, instability, noise, as well as much local minimum. This new method is called GA for Best Heating-Cooling Location (GA-FBHCL). According to our prior work which have accommodated the Taguchi method for the aims of Building Energy Modelling (BEM) and optimization to forecast the best heating and cooling appliances location in one of the Toos Arman Star Apartment Hotel units in Mashhad, Iran, now we introduce a new theory and design with the help of GA for this goal which the EM results achieved from the GA-FBHCL method are 5-9% better than the Taguchi method and initial design of room. This approach can be utilized with project developers, policymakers and researchers as a new globally approach in construction industry.
本文提出了一种利用遗传算法求解暖通空调选址问题的新方法。它希望遵循世界最优解，通过消除未知适应度条件、不稳定性、噪声以及许多局部最小值等限制来找到最佳结果。这种新方法被称为GA- fbhcl (GA- fbhcl)。根据我们之前的工作，在伊朗马什哈德Toos Arman Star Apartment Hotel单元之一的建筑能源建模(BEM)和优化预测最佳供暖和制冷设备位置的目标中，我们采用了田口方法，现在我们引入了一种新的理论和设计，通过GA- fbhcl方法获得的EM结果比田口方法和房间初始设计好5-9%。这种方法可以与项目开发商、政策制定者和研究人员一起使用，作为建筑行业的一种新的全球方法。
{"title":"GA-FBHCL: A method for the best HVAC location*","authors":"Zahra Pezeshki, Ali Gholipour Soleimani, A. Darabi","doi":"10.1109/ZINC50678.2020.9161819","DOIUrl":"https://doi.org/10.1109/ZINC50678.2020.9161819","url":null,"abstract":"This paper offers a novel method with the help of Genetic Algorithm (GA) to find the optimal solution for determining the HVAC location. It wants to follow a world optimal solution to find the best result by removing the limitations such as unknown fitness conditions, instability, noise, as well as much local minimum. This new method is called GA for Best Heating-Cooling Location (GA-FBHCL). According to our prior work which have accommodated the Taguchi method for the aims of Building Energy Modelling (BEM) and optimization to forecast the best heating and cooling appliances location in one of the Toos Arman Star Apartment Hotel units in Mashhad, Iran, now we introduce a new theory and design with the help of GA for this goal which the EM results achieved from the GA-FBHCL method are 5-9% better than the Taguchi method and initial design of room. This approach can be utilized with project developers, policymakers and researchers as a new globally approach in construction industry.","PeriodicalId":6731,"journal":{"name":"2020 Zooming Innovation in Consumer Technologies Conference (ZINC)","volume":"139 1","pages":"93-98"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80402118","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 : 2020-05-01DOI: 10.1109/ZINC50678.2020.9161772
Davor Barić, R. Grbić, M. Subotic, V. Mihic
Nowadays software testing in the automotive industry is a very important step in overall software development. The work in this paper is based on a pre-existing special testing environment for Advanced Driver Assistance Systems (ADAS) software solutions which automates the process of testing as much as possible. Within the paper, this environment was analyzed and some of the shortcomings were identified. An alternative solution is proposed which, instead of storing tests in one large dictionary, uses an SQLite database as a storage method. Before integration into the existing environment, a standalone solution was developed. After that, efforts were made to integrate such a solution into the existing environment. While the proposed standalone solution obtains smaller processing time regarding test adding in comparison with existing solution, after integration into the existing environment, the proposed solution obtains slightly higher processing time. However, the proposed approach provides security, robustness and stability of the entire environment with respect to data storage.
{"title":"Testing Environment for ADAS Software Solutions","authors":"Davor Barić, R. Grbić, M. Subotic, V. Mihic","doi":"10.1109/ZINC50678.2020.9161772","DOIUrl":"https://doi.org/10.1109/ZINC50678.2020.9161772","url":null,"abstract":"Nowadays software testing in the automotive industry is a very important step in overall software development. The work in this paper is based on a pre-existing special testing environment for Advanced Driver Assistance Systems (ADAS) software solutions which automates the process of testing as much as possible. Within the paper, this environment was analyzed and some of the shortcomings were identified. An alternative solution is proposed which, instead of storing tests in one large dictionary, uses an SQLite database as a storage method. Before integration into the existing environment, a standalone solution was developed. After that, efforts were made to integrate such a solution into the existing environment. While the proposed standalone solution obtains smaller processing time regarding test adding in comparison with existing solution, after integration into the existing environment, the proposed solution obtains slightly higher processing time. However, the proposed approach provides security, robustness and stability of the entire environment with respect to data storage.","PeriodicalId":6731,"journal":{"name":"2020 Zooming Innovation in Consumer Technologies Conference (ZINC)","volume":"49 1","pages":"190-194"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74678578","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 : 2020-05-01DOI: 10.1109/ZINC50678.2020.9161783
Subhadeep Koley
Due to the unprecedented growth of the internet and portable consumer imaging devices, copyright protection of digital images has become a topical affair. In this paper, a fast Tensor-SVD based red-cyan anaglyph 3D image watermarking has been presented which provides high imperceptibility, and robustness. To integrate the Human Visual System modelling into our framework, integer lifting wavelet transform has been incorporated. After that, the watermark has been infused within the first diagonal matrix generated by Tensor-SVD. The proposed method is free from false positive issues due to its total insertion-based approach. Furthermore, the proposed method is also implemented in a low-power Single Board Computer for seamless integration in personal and industrial consumer imaging devices. Moreover, the watermark’s security has been further increased by encrypting it with Arnold’s Cat Map based cryptic algorithm. Qualitative and quantitative comparison with various state-of-the-art methods justifies the superiority of the suggested algorithm under most form of signal processing, and geometric impairments.
{"title":"Hardware Implementation of a Fast 3D Anaglyph Image Watermarking Framework for Integration in Consumer Electronics Devices","authors":"Subhadeep Koley","doi":"10.1109/ZINC50678.2020.9161783","DOIUrl":"https://doi.org/10.1109/ZINC50678.2020.9161783","url":null,"abstract":"Due to the unprecedented growth of the internet and portable consumer imaging devices, copyright protection of digital images has become a topical affair. In this paper, a fast Tensor-SVD based red-cyan anaglyph 3D image watermarking has been presented which provides high imperceptibility, and robustness. To integrate the Human Visual System modelling into our framework, integer lifting wavelet transform has been incorporated. After that, the watermark has been infused within the first diagonal matrix generated by Tensor-SVD. The proposed method is free from false positive issues due to its total insertion-based approach. Furthermore, the proposed method is also implemented in a low-power Single Board Computer for seamless integration in personal and industrial consumer imaging devices. Moreover, the watermark’s security has been further increased by encrypting it with Arnold’s Cat Map based cryptic algorithm. Qualitative and quantitative comparison with various state-of-the-art methods justifies the superiority of the suggested algorithm under most form of signal processing, and geometric impairments.","PeriodicalId":6731,"journal":{"name":"2020 Zooming Innovation in Consumer Technologies Conference (ZINC)","volume":"91 1","pages":"40-45"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77227769","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 : 2020-05-01DOI: 10.1109/ZINC50678.2020.9161788
M. Zivkovic, N. Bačanin, Tamara Zivkovic, I. Strumberger, Eva Tuba, M. Tuba
Wireless sensor networks have entered a period of a rapid development, due to several novel technologies which have emerged in the past few years, such as Internet of Things and cloud computing. Miniature sensor nodes are integral components of numerous complex systems. The biggest problem for any wireless sensor network, in any possible application domain, is to maximize the overall network lifetime by improving the total energy consumption of the network. A large number of clustering algorithms have been implemented in the past decade, with a main goal to balance the energy consumption of each node in the network and to increase energy efficiency - the term known in literature as load balancing. One important representative of these traditional algorithms for load balancing which is still in frequent use is LEACH. On the other hand, swarm intelligence meaheuristics have recently been successfully applied in solving a large number of NP hard problems from the wireless sensor networks domain. In this paper, we propose an improved version of grey wolf algorithm, that has been applied to improve the network lifetime optimization. Grey wolf algorithm was employed in forming the clusters and the cluster head selection process. As a part of our research, we have evaluated the performance of the proposed exploration enhanced grey wolf algorithm by comparing it to the traditional LEACH algorithm, basic grey wolf approach and particle swarm optimization, that were all tested under the same experimental conditions. Obtained results from conducted simulations have proven that our proposed metaheuristics performs better that other considered algorithms.
{"title":"Enhanced Grey Wolf Algorithm for Energy Efficient Wireless Sensor Networks","authors":"M. Zivkovic, N. Bačanin, Tamara Zivkovic, I. Strumberger, Eva Tuba, M. Tuba","doi":"10.1109/ZINC50678.2020.9161788","DOIUrl":"https://doi.org/10.1109/ZINC50678.2020.9161788","url":null,"abstract":"Wireless sensor networks have entered a period of a rapid development, due to several novel technologies which have emerged in the past few years, such as Internet of Things and cloud computing. Miniature sensor nodes are integral components of numerous complex systems. The biggest problem for any wireless sensor network, in any possible application domain, is to maximize the overall network lifetime by improving the total energy consumption of the network. A large number of clustering algorithms have been implemented in the past decade, with a main goal to balance the energy consumption of each node in the network and to increase energy efficiency - the term known in literature as load balancing. One important representative of these traditional algorithms for load balancing which is still in frequent use is LEACH. On the other hand, swarm intelligence meaheuristics have recently been successfully applied in solving a large number of NP hard problems from the wireless sensor networks domain. In this paper, we propose an improved version of grey wolf algorithm, that has been applied to improve the network lifetime optimization. Grey wolf algorithm was employed in forming the clusters and the cluster head selection process. As a part of our research, we have evaluated the performance of the proposed exploration enhanced grey wolf algorithm by comparing it to the traditional LEACH algorithm, basic grey wolf approach and particle swarm optimization, that were all tested under the same experimental conditions. Obtained results from conducted simulations have proven that our proposed metaheuristics performs better that other considered algorithms.","PeriodicalId":6731,"journal":{"name":"2020 Zooming Innovation in Consumer Technologies Conference (ZINC)","volume":"48 1","pages":"87-92"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79784182","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 : 2020-05-01DOI: 10.1109/ZINC50678.2020.9161818
Marko Dragojevic, Stevan Stevic, Momcilo Krunic, N. Lukic
In order to achieve functionality of autonomous driving, modern vehicles must be aware of theirs surrounding in any given moment. Complex software modules within such systems oversee vehicle’s environment and use this environmental data to pinpoint vehicles position in the world. Often these perception modules process numerous calculations and fuse data acquired from different sensors to achieve, as precise as possible, understanding of vehicles environment. Alongside these highlevel data fusion modules, many modern vehicles have redundant subsystems that handle similar functionality but in smaller scale in order to achieve shorter “Sense-Plan-Act” loop. In this paper we will present prototype for Advance Lane Finding (ALF) application, which could be utilized as an enhancement of multiple ADAS systems. Proposed solution is implemented in C+ + programming language as a part of Autoware/ROS platform. Prototype’s performances are tested on Nvidia DRIVE PX2 hardware platform.
{"title":"Advanced Lane Finding Prototype Based on Autoware Platform","authors":"Marko Dragojevic, Stevan Stevic, Momcilo Krunic, N. Lukic","doi":"10.1109/ZINC50678.2020.9161818","DOIUrl":"https://doi.org/10.1109/ZINC50678.2020.9161818","url":null,"abstract":"In order to achieve functionality of autonomous driving, modern vehicles must be aware of theirs surrounding in any given moment. Complex software modules within such systems oversee vehicle’s environment and use this environmental data to pinpoint vehicles position in the world. Often these perception modules process numerous calculations and fuse data acquired from different sensors to achieve, as precise as possible, understanding of vehicles environment. Alongside these highlevel data fusion modules, many modern vehicles have redundant subsystems that handle similar functionality but in smaller scale in order to achieve shorter “Sense-Plan-Act” loop. In this paper we will present prototype for Advance Lane Finding (ALF) application, which could be utilized as an enhancement of multiple ADAS systems. Proposed solution is implemented in C+ + programming language as a part of Autoware/ROS platform. Prototype’s performances are tested on Nvidia DRIVE PX2 hardware platform.","PeriodicalId":6731,"journal":{"name":"2020 Zooming Innovation in Consumer Technologies Conference (ZINC)","volume":"35 1","pages":"169-173"},"PeriodicalIF":0.0,"publicationDate":"2020-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90520093","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：