The principal focus of this paper is to develop a prediction model to predict the turbidity of beach waves. The prediction model is developed using a nonlinear autoregressive neural network model using three input parameters: water temperature, wave height, and wave period. The beach wave turbidity is predicted without installing any additional sensors. The performance of the developed model is evaluated on three beaches in Chicago Park’s district. The proposed model performance showed better tracking ability for all the three considered beaches. The R2 and mean square errors MSE also confirm the best prediction model’s performance for both training and testing.
{"title":"Prediction of Turbidity in Beach Waves Using Nonlinear Autoregressive Neural Networks","authors":"Jhanavi Chaudhary, Harshita Puri, Rh Mantri, Kulkarni Rakshit Raghavendra, Kishore Bingi","doi":"10.1109/ICSCC51209.2021.9528261","DOIUrl":"https://doi.org/10.1109/ICSCC51209.2021.9528261","url":null,"abstract":"The principal focus of this paper is to develop a prediction model to predict the turbidity of beach waves. The prediction model is developed using a nonlinear autoregressive neural network model using three input parameters: water temperature, wave height, and wave period. The beach wave turbidity is predicted without installing any additional sensors. The performance of the developed model is evaluated on three beaches in Chicago Park’s district. The proposed model performance showed better tracking ability for all the three considered beaches. The R2 and mean square errors MSE also confirm the best prediction model’s performance for both training and testing.","PeriodicalId":382982,"journal":{"name":"2021 8th International Conference on Smart Computing and Communications (ICSCC)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130553311","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 : 2021-07-01DOI: 10.1109/ICSCC51209.2021.9528144
Safa Mohammed Sali, K. Joy
Smart Buggy is a surveillance robotic car built to control from anywhere around the globe. It performs every operation with the aid of raspberry pi. Smart Buggy captures the video and is live-streamed via a micro web framework to be viewed from different locations. The video is captured using a pi camera and employs a motion detection algorithm called background subtraction model to detect motions. The camera can be panned and tilted using servo motors. DC motors are employed for maneuvering the Smart Buggy. Movements include forward, backward, left, and right. All the operations are performed via the internet and the concept of the Internet of Things. Smart Buggy is primarily used for surveillance and by port forwarding the device, it can be controlled from anywhere.
{"title":"Smart Buggy: An IoT Based Smart Surveillance Robotic Car Using Raspberry Pi","authors":"Safa Mohammed Sali, K. Joy","doi":"10.1109/ICSCC51209.2021.9528144","DOIUrl":"https://doi.org/10.1109/ICSCC51209.2021.9528144","url":null,"abstract":"Smart Buggy is a surveillance robotic car built to control from anywhere around the globe. It performs every operation with the aid of raspberry pi. Smart Buggy captures the video and is live-streamed via a micro web framework to be viewed from different locations. The video is captured using a pi camera and employs a motion detection algorithm called background subtraction model to detect motions. The camera can be panned and tilted using servo motors. DC motors are employed for maneuvering the Smart Buggy. Movements include forward, backward, left, and right. All the operations are performed via the internet and the concept of the Internet of Things. Smart Buggy is primarily used for surveillance and by port forwarding the device, it can be controlled from anywhere.","PeriodicalId":382982,"journal":{"name":"2021 8th International Conference on Smart Computing and Communications (ICSCC)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127951953","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 : 2021-07-01DOI: 10.1109/ICSCC51209.2021.9528117
P. S, Jihas Khan, L. Jacob
Accurate link adaptation in 5G is a major challenge as it supports a wide range of services, including ultra-reliable low-latency communication (URLLC). URLLC has very strict latency and reliability constraints. The diverse and fast fading channel conditions result in channel quality indicator (CQI) feedback from user equipments (UEs) being outdated at the base station (BS). The CQI values are used at the BS to perform link adaptation by assigning optimal modulation and coding scheme (MCS) according to the reported CQI value. This results in the allocation of either a higher MCS value than required, which affects the reliability; or a lower MCS value than required, which affects the spectral efficiency and latency. Thus, there is a need for novel methods to perform the link adaptation in the case of URLLC. In this paper, we propose a reinforcement learning (RL) based intelligent link adaptation in a time-correlated and fast fading channel. The RL-based method can intelligently predict the future CQI values and accordingly allocate the MCS for data transmission. Here we use a contextual multi-armed bandit (MAB) algorithm for link adaptation. The proposed method is then compared with the baseline outer loop link adaptation (OLLA) method. Simulation results show that the RL-based method has better performance in terms of both reliability and spectral efficiency than the OLLA based scheme.
{"title":"Reinforcement Learning Based Link Adaptation in 5G URLLC","authors":"P. S, Jihas Khan, L. Jacob","doi":"10.1109/ICSCC51209.2021.9528117","DOIUrl":"https://doi.org/10.1109/ICSCC51209.2021.9528117","url":null,"abstract":"Accurate link adaptation in 5G is a major challenge as it supports a wide range of services, including ultra-reliable low-latency communication (URLLC). URLLC has very strict latency and reliability constraints. The diverse and fast fading channel conditions result in channel quality indicator (CQI) feedback from user equipments (UEs) being outdated at the base station (BS). The CQI values are used at the BS to perform link adaptation by assigning optimal modulation and coding scheme (MCS) according to the reported CQI value. This results in the allocation of either a higher MCS value than required, which affects the reliability; or a lower MCS value than required, which affects the spectral efficiency and latency. Thus, there is a need for novel methods to perform the link adaptation in the case of URLLC. In this paper, we propose a reinforcement learning (RL) based intelligent link adaptation in a time-correlated and fast fading channel. The RL-based method can intelligently predict the future CQI values and accordingly allocate the MCS for data transmission. Here we use a contextual multi-armed bandit (MAB) algorithm for link adaptation. The proposed method is then compared with the baseline outer loop link adaptation (OLLA) method. Simulation results show that the RL-based method has better performance in terms of both reliability and spectral efficiency than the OLLA based scheme.","PeriodicalId":382982,"journal":{"name":"2021 8th International Conference on Smart Computing and Communications (ICSCC)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125524093","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 : 2021-07-01DOI: 10.1109/ICSCC51209.2021.9528203
Mohan Kumar Dehury, H. K. Pati
In Voice over LTE (VoLTE), speech is transmitted over packet-switched network. It is often observed that calls get blocked while initiating or during handoff. This Quality of Service (QoS) measure depends on available amount of radio resources within a cell in the Long Term Evolution (LTE) network. Third Generation Partnership Project (3GPP) recommends use of Adaptive Multi-Rate Wideband (AMR-WB) codec for better voice quality in the LTE network offering VoLTE service. The AMR-WB voice codec with varying bit rates may require different amount of radio resources at physical layer. This may affect to the call blocking performance in an LTE network. In this paper, we have proposed a Physical Resource Block (PRB) based model using the concept of Markov Chain to investigate the VoLTE call blocking performance in the LTE network. We have presented the impact of AMR-WB voice codec with different bit rates on call blocking in an LTE network providing VoLTE service.
在VoLTE (Voice over LTE)技术中，语音是通过分组交换网络传输的。经常观察到调用在初始化或切换期间被阻塞。这种服务质量(QoS)指标取决于长期演进(LTE)网络中小区内可用的无线资源数量。第三代合作伙伴计划(3GPP)建议在提供VoLTE服务的LTE网络中使用自适应多速率宽带(AMR-WB)编解码器以获得更好的语音质量。不同比特率的AMR-WB语音编解码器在物理层可能需要不同数量的无线电资源。这可能会影响LTE网络中的呼叫阻塞性能。在本文中，我们提出了一个基于物理资源块(PRB)的模型，利用马尔可夫链的概念来研究LTE网络中VoLTE呼叫阻塞性能。研究了在提供VoLTE服务的LTE网络中，不同比特率的AMR-WB语音编解码器对呼叫阻塞的影响。
{"title":"Impact of AMR-WB Codec on VoLTE Call Blocking in Cellular LTE Network","authors":"Mohan Kumar Dehury, H. K. Pati","doi":"10.1109/ICSCC51209.2021.9528203","DOIUrl":"https://doi.org/10.1109/ICSCC51209.2021.9528203","url":null,"abstract":"In Voice over LTE (VoLTE), speech is transmitted over packet-switched network. It is often observed that calls get blocked while initiating or during handoff. This Quality of Service (QoS) measure depends on available amount of radio resources within a cell in the Long Term Evolution (LTE) network. Third Generation Partnership Project (3GPP) recommends use of Adaptive Multi-Rate Wideband (AMR-WB) codec for better voice quality in the LTE network offering VoLTE service. The AMR-WB voice codec with varying bit rates may require different amount of radio resources at physical layer. This may affect to the call blocking performance in an LTE network. In this paper, we have proposed a Physical Resource Block (PRB) based model using the concept of Markov Chain to investigate the VoLTE call blocking performance in the LTE network. We have presented the impact of AMR-WB voice codec with different bit rates on call blocking in an LTE network providing VoLTE service.","PeriodicalId":382982,"journal":{"name":"2021 8th International Conference on Smart Computing and Communications (ICSCC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126460307","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 : 2021-07-01DOI: 10.1109/ICSCC51209.2021.9528293
Anagha Gopi, Jeslin Anna Jacob, Riya Mary Puthumana, Rizwana A K, K. S, Binu Manohar
Urban India generates tonnes of wastes annually. Our country faces major challenges associated with waste management. Conventional garbage collection is not efficient since the authorities are not notified until the waste bin is full, and this leads to overflow of waste material. Efficient way of waste disposal and collection of disposed garbage is essential for a sustainable and clean India. This paper presents smart waste management using IoT based waste bin for collection and monitoring the level of waste inside bin. The system is implemented using two ultrasonic sensors which is being controlled by Node MCU. One of the ultrasonic sensor detects the level of the waste in the bin and other detects the person approaching the bin to dispose the waste. This detection helps in automatic opening and closing of the lid. Servo motor is connected to the lid which serves the action of closing and opening of the lid. In this system, level of waste in the bin will be sent to concerned authorities. The IoT data is stored and monitored using Blynk app. The proposed system is reliable, cost effective and can be easily implemented.
{"title":"IoT based smart waste management system","authors":"Anagha Gopi, Jeslin Anna Jacob, Riya Mary Puthumana, Rizwana A K, K. S, Binu Manohar","doi":"10.1109/ICSCC51209.2021.9528293","DOIUrl":"https://doi.org/10.1109/ICSCC51209.2021.9528293","url":null,"abstract":"Urban India generates tonnes of wastes annually. Our country faces major challenges associated with waste management. Conventional garbage collection is not efficient since the authorities are not notified until the waste bin is full, and this leads to overflow of waste material. Efficient way of waste disposal and collection of disposed garbage is essential for a sustainable and clean India. This paper presents smart waste management using IoT based waste bin for collection and monitoring the level of waste inside bin. The system is implemented using two ultrasonic sensors which is being controlled by Node MCU. One of the ultrasonic sensor detects the level of the waste in the bin and other detects the person approaching the bin to dispose the waste. This detection helps in automatic opening and closing of the lid. Servo motor is connected to the lid which serves the action of closing and opening of the lid. In this system, level of waste in the bin will be sent to concerned authorities. The IoT data is stored and monitored using Blynk app. The proposed system is reliable, cost effective and can be easily implemented.","PeriodicalId":382982,"journal":{"name":"2021 8th International Conference on Smart Computing and Communications (ICSCC)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122698401","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 : 2021-07-01DOI: 10.1109/ICSCC51209.2021.9528198
G. A. Thushara, S. M. Bhanu
Cloud computing facilitates the access of applications and data from any location by using any device with an internet connection. It enables multiple applications and users to access the same data resources. Cloud based information sharing is a technique that allows researchers to communicate and collaborate, that leads to major new developments in the field. It also enables users to access data over the cloud easily and conveniently. Privacy, authenticity and confidentiality are the three main challenges while sharing data in cloud. There are many methods which support secure data sharing in cloud environment such as Attribute Based Encryption(ABE), Role Based Encryption, Hierarchical Based Encryption, and Identity Based Encryption. ABE provides secure access control mechanisms for integrity. It is classified as Key Policy Attribute Based Encryption(KP-ABE) and Ciphertext Policy Attribute Based Encryption(CP-ABE) based on access policy integration. In KPABE, access structure is incorporated with user’s private key, and data are encrypted over a defined attributes. Moreover, in CPABE, access structure is embedded with ciphertext. This paper reviews CP-ABE methods that have been developed so far for achieving secured data sharing in cloud environment.
云计算可以通过使用任何连接互联网的设备，方便地从任何位置访问应用程序和数据。它允许多个应用程序和用户访问相同的数据资源。基于云的信息共享是一种允许研究人员进行交流和协作的技术，它导致了该领域的重大新发展。它还使用户能够轻松方便地通过云访问数据。隐私、真实性和保密性是在云中共享数据时面临的三大挑战。在云环境中支持安全数据共享的方法有很多，如基于属性的加密(ABE)、基于角色的加密、基于层次的加密和基于身份的加密。ABE为完整性提供了安全的访问控制机制。基于访问策略集成，可分为Key Policy Attribute Based Encryption(KP-ABE)和cipher Policy Attribute Based Encryption(CP-ABE)。在KPABE中，访问结构与用户的私钥结合在一起，数据通过定义的属性进行加密。此外，在CPABE中，访问结构中嵌入了密文。本文综述了迄今为止为实现云环境下安全数据共享而开发的CP-ABE方法。
{"title":"A Survey on Secured Data Sharing using Ciphertext Policy Attribute Based Encryption in Cloud","authors":"G. A. Thushara, S. M. Bhanu","doi":"10.1109/ICSCC51209.2021.9528198","DOIUrl":"https://doi.org/10.1109/ICSCC51209.2021.9528198","url":null,"abstract":"Cloud computing facilitates the access of applications and data from any location by using any device with an internet connection. It enables multiple applications and users to access the same data resources. Cloud based information sharing is a technique that allows researchers to communicate and collaborate, that leads to major new developments in the field. It also enables users to access data over the cloud easily and conveniently. Privacy, authenticity and confidentiality are the three main challenges while sharing data in cloud. There are many methods which support secure data sharing in cloud environment such as Attribute Based Encryption(ABE), Role Based Encryption, Hierarchical Based Encryption, and Identity Based Encryption. ABE provides secure access control mechanisms for integrity. It is classified as Key Policy Attribute Based Encryption(KP-ABE) and Ciphertext Policy Attribute Based Encryption(CP-ABE) based on access policy integration. In KPABE, access structure is incorporated with user’s private key, and data are encrypted over a defined attributes. Moreover, in CPABE, access structure is embedded with ciphertext. This paper reviews CP-ABE methods that have been developed so far for achieving secured data sharing in cloud environment.","PeriodicalId":382982,"journal":{"name":"2021 8th International Conference on Smart Computing and Communications (ICSCC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131122723","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 : 2021-07-01DOI: 10.1109/ICSCC51209.2021.9528171
Sangari A, Sivamani D, A. J, J. K., N. A, K. J.
Water scarcity is becoming one of the major problems in India. It endangers the health, economy, environment and food supply of India. Nowadays, the cost of purified water has increased tremendously. To overcome the demand for drinking water, a small-scale solar energy-based water purification system is proposed. The novelty of the proposed work is to supply drinking water continuously without any interruption and minimize the cost of water purification. In this work, a desalination chamber is coupled with the solar panel. During lack of solar energy, the potential energy of the water is utilized for the purification process. The opening and closing of the valves are controlled by the microcontroller based on the sensor outputs. The energy efficiency and water quality of the system is analyzed and compared with the conventional water purification system in a short-term basis.
{"title":"Portable Solar PV based Water Purification System for Subcontinent Conditions","authors":"Sangari A, Sivamani D, A. J, J. K., N. A, K. J.","doi":"10.1109/ICSCC51209.2021.9528171","DOIUrl":"https://doi.org/10.1109/ICSCC51209.2021.9528171","url":null,"abstract":"Water scarcity is becoming one of the major problems in India. It endangers the health, economy, environment and food supply of India. Nowadays, the cost of purified water has increased tremendously. To overcome the demand for drinking water, a small-scale solar energy-based water purification system is proposed. The novelty of the proposed work is to supply drinking water continuously without any interruption and minimize the cost of water purification. In this work, a desalination chamber is coupled with the solar panel. During lack of solar energy, the potential energy of the water is utilized for the purification process. The opening and closing of the valves are controlled by the microcontroller based on the sensor outputs. The energy efficiency and water quality of the system is analyzed and compared with the conventional water purification system in a short-term basis.","PeriodicalId":382982,"journal":{"name":"2021 8th International Conference on Smart Computing and Communications (ICSCC)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131175096","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 : 2021-07-01DOI: 10.1109/ICSCC51209.2021.9528194
Kshitij Patel, Meet Patel
Today, in the technological era of the 21st century, CCTV cameras have been proven to be very fruitful in our daily lives. From monitoring the baby in the bassinet to prevent some crimes, CCTV camera has become of vital importance. We as humans, always try to make things perfect around us. Using this article, we also have attempted to present our perspective to make these CCTV cameras more perfect. We have made an effort to enhance regular CCTV cameras using the vast field of deep learning and IoT. We have attempted to accomplish our goal by providing a protoStype for the smart surveillance system. We have tried to upgrade the regular CCTV cameras with some customized deep learning models developed by us. In this modified version, we have given the CCTV cameras the ability to detect fire and weapons. Also, we have tried to fulfil an ad-hoc requirement of Face Mask Detection considering the current situation of COVID19. For fulfilling our objective, we have provided an outline combining IoT (RaspberryPi) to deep learning using AWS EC2 Cloud Architecture. To make the surveillance system user-friendly, we have also taken account of the client-side interface. Considering all the above applications, we have successfully provided an archetype in this paper.
{"title":"Smart Surveillance System using Deep Learning and RaspberryPi","authors":"Kshitij Patel, Meet Patel","doi":"10.1109/ICSCC51209.2021.9528194","DOIUrl":"https://doi.org/10.1109/ICSCC51209.2021.9528194","url":null,"abstract":"Today, in the technological era of the 21st century, CCTV cameras have been proven to be very fruitful in our daily lives. From monitoring the baby in the bassinet to prevent some crimes, CCTV camera has become of vital importance. We as humans, always try to make things perfect around us. Using this article, we also have attempted to present our perspective to make these CCTV cameras more perfect. We have made an effort to enhance regular CCTV cameras using the vast field of deep learning and IoT. We have attempted to accomplish our goal by providing a protoStype for the smart surveillance system. We have tried to upgrade the regular CCTV cameras with some customized deep learning models developed by us. In this modified version, we have given the CCTV cameras the ability to detect fire and weapons. Also, we have tried to fulfil an ad-hoc requirement of Face Mask Detection considering the current situation of COVID19. For fulfilling our objective, we have provided an outline combining IoT (RaspberryPi) to deep learning using AWS EC2 Cloud Architecture. To make the surveillance system user-friendly, we have also taken account of the client-side interface. Considering all the above applications, we have successfully provided an archetype in this paper.","PeriodicalId":382982,"journal":{"name":"2021 8th International Conference on Smart Computing and Communications (ICSCC)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133729578","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 : 2021-07-01DOI: 10.1109/icscc51209.2021.9528224
{"title":"[ICSCC 2021 Front matter]","authors":"","doi":"10.1109/icscc51209.2021.9528224","DOIUrl":"https://doi.org/10.1109/icscc51209.2021.9528224","url":null,"abstract":"","PeriodicalId":382982,"journal":{"name":"2021 8th International Conference on Smart Computing and Communications (ICSCC)","volume":"414 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134319550","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 : 2021-07-01DOI: 10.1109/ICSCC51209.2021.9528220
A. Mauri, R. Khemmar, B. Decoux, Tahar Benmoumen, Madjid Haddad, R. Boutteau
In autonomous vehicle systems, the quality of scene perception is of great importance for security preoccupation in road environments. In this context, an accurate localization of potential obstacles is one of the most challenging tasks. In recent years, substantial progress has been made in the field of depth estimation for detection purposes with the spread of methods relying on deep learning with monocular or stereo-scopic camera(s). These two families of approaches did show an upstanding yet inconsistent performance in different road scenes circumstances. A deep understanding and comparison of these approaches is required to allow the community an easier assessment, which breeds to more adequate choice for their own systems. In this paper, we propose a comparative study of state-of-the-art deep learning depth estimation methods using monocular and stereoscopic cameras. The evaluation is performed on road environment over the challenging KITTI dataset.
{"title":"A Comparative Study of Deep Learning-based Depth Estimation Approaches: Application to Smart Mobility","authors":"A. Mauri, R. Khemmar, B. Decoux, Tahar Benmoumen, Madjid Haddad, R. Boutteau","doi":"10.1109/ICSCC51209.2021.9528220","DOIUrl":"https://doi.org/10.1109/ICSCC51209.2021.9528220","url":null,"abstract":"In autonomous vehicle systems, the quality of scene perception is of great importance for security preoccupation in road environments. In this context, an accurate localization of potential obstacles is one of the most challenging tasks. In recent years, substantial progress has been made in the field of depth estimation for detection purposes with the spread of methods relying on deep learning with monocular or stereo-scopic camera(s). These two families of approaches did show an upstanding yet inconsistent performance in different road scenes circumstances. A deep understanding and comparison of these approaches is required to allow the community an easier assessment, which breeds to more adequate choice for their own systems. In this paper, we propose a comparative study of state-of-the-art deep learning depth estimation methods using monocular and stereoscopic cameras. The evaluation is performed on road environment over the challenging KITTI dataset.","PeriodicalId":382982,"journal":{"name":"2021 8th International Conference on Smart Computing and Communications (ICSCC)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129807069","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：