Pub Date : 2015-11-01DOI: 10.1109/ICVES.2015.7396890
Kenta Fukushima, Kousuke Matsushima
Many researches have worked for the development of automotive technologies, so as to realize a convenient and safety automotive society such as Advanced Safety Vehicle (ASV) and Traffic Monitoring System (TMS). As a result, traffic accidents have decreased as the years pass, and the number of the dead and injuries have been reduced. However, autonomous driving is not only required to detect bicycles around vehicles, but also expected to understand the behaviors of bicycles. In addition, since the proportion of bicycle accident shows a high percentage in the total traffic accident, it has been predicted an increase of the accident of the bicycle in the future. Therefore we propose a multi-directional bicycle recognition system using the distance information obtained by the stereo camera. In the proposed system, we divide the moving direction of the bicycle into three directions. In addition, we propose a robust feature extraction method on rotation in order to cope with the bicycle between each direction. Finally,we show the experimental results and verify the effectiveness of the proposed method.
{"title":"Robust multi-directional bicycle recognition on the rotation using the stereo vision","authors":"Kenta Fukushima, Kousuke Matsushima","doi":"10.1109/ICVES.2015.7396890","DOIUrl":"https://doi.org/10.1109/ICVES.2015.7396890","url":null,"abstract":"Many researches have worked for the development of automotive technologies, so as to realize a convenient and safety automotive society such as Advanced Safety Vehicle (ASV) and Traffic Monitoring System (TMS). As a result, traffic accidents have decreased as the years pass, and the number of the dead and injuries have been reduced. However, autonomous driving is not only required to detect bicycles around vehicles, but also expected to understand the behaviors of bicycles. In addition, since the proportion of bicycle accident shows a high percentage in the total traffic accident, it has been predicted an increase of the accident of the bicycle in the future. Therefore we propose a multi-directional bicycle recognition system using the distance information obtained by the stereo camera. In the proposed system, we divide the moving direction of the bicycle into three directions. In addition, we propose a robust feature extraction method on rotation in order to cope with the bicycle between each direction. Finally,we show the experimental results and verify the effectiveness of the proposed method.","PeriodicalId":325462,"journal":{"name":"2015 IEEE International Conference on Vehicular Electronics and Safety (ICVES)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132279167","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 : 2015-11-01DOI: 10.1109/ICVES.2015.7396893
Zhan-Yao Gu, Yarsun Hsu, Chi-Ming Lee
FlexRay is a communication protocol that combines event- and time-triggered communication to increase the schedulability and flexibility of message scheduling in current car systems. Because safety and reliability are particularly crucial for automotive systems, the worst-case response times of signals transmitted by electronic control units must be under their deadlines. To increase the bandwidth utilization, the slotmultiplexing (SM) mechanism that is allowable in protocol specification was adopted to schedule messages offline in the dynamic segment of the FlexRay protocol, and this mechanism was also considered in the timing analysis. The proposed method was feasible to calculate worst-case response time of message under any bus load when considered slot-multiplexing. Then the approach was applied to a Society of Automotive Engineers benchmark to ensure that all messages were schedulable. The simulation results revealed that by using slot-multiplexing, only 17 identifiers were used, which was less than 23 identifiers that were needed when the slot-multiplexing was not considered. It also improved the schedulability of dynamic segment with up to 27% improvement in bus bandwidth utilization.
{"title":"Message scheduling and timing analysis for flexray dynamic segment by considering slot-multiplexing","authors":"Zhan-Yao Gu, Yarsun Hsu, Chi-Ming Lee","doi":"10.1109/ICVES.2015.7396893","DOIUrl":"https://doi.org/10.1109/ICVES.2015.7396893","url":null,"abstract":"FlexRay is a communication protocol that combines event- and time-triggered communication to increase the schedulability and flexibility of message scheduling in current car systems. Because safety and reliability are particularly crucial for automotive systems, the worst-case response times of signals transmitted by electronic control units must be under their deadlines. To increase the bandwidth utilization, the slotmultiplexing (SM) mechanism that is allowable in protocol specification was adopted to schedule messages offline in the dynamic segment of the FlexRay protocol, and this mechanism was also considered in the timing analysis. The proposed method was feasible to calculate worst-case response time of message under any bus load when considered slot-multiplexing. Then the approach was applied to a Society of Automotive Engineers benchmark to ensure that all messages were schedulable. The simulation results revealed that by using slot-multiplexing, only 17 identifiers were used, which was less than 23 identifiers that were needed when the slot-multiplexing was not considered. It also improved the schedulability of dynamic segment with up to 27% improvement in bus bandwidth utilization.","PeriodicalId":325462,"journal":{"name":"2015 IEEE International Conference on Vehicular Electronics and Safety (ICVES)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131763327","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 : 2015-11-01DOI: 10.1109/ICVES.2015.7396905
T. Takano, Shintaro Ono, Y. Matsushita, Hiroshi Kawasaki, K. Ikeuchi
Fisheye cameras are widely adopted in the back view camera of vehicles and the surveillance camera. Compared to the normal digital cameras, their resolution and image quality are low. In this paper, we propose a method to restore the high resolution images from the fisheye camera by the reconstructed type of super resolution. First, we undistort the fisheye images and regularize these images. Then we super-resolve these regularized images. Blur kernel for super resolution includes the lens blur and the expansion and reduction by the undistortion. The experimental results confirms to the effectiveness of our method which applies to the images captured by the digital camera with fish-eye lens.
{"title":"Super resolution of fisheye images captured by on-vehicle camera for visibility support","authors":"T. Takano, Shintaro Ono, Y. Matsushita, Hiroshi Kawasaki, K. Ikeuchi","doi":"10.1109/ICVES.2015.7396905","DOIUrl":"https://doi.org/10.1109/ICVES.2015.7396905","url":null,"abstract":"Fisheye cameras are widely adopted in the back view camera of vehicles and the surveillance camera. Compared to the normal digital cameras, their resolution and image quality are low. In this paper, we propose a method to restore the high resolution images from the fisheye camera by the reconstructed type of super resolution. First, we undistort the fisheye images and regularize these images. Then we super-resolve these regularized images. Blur kernel for super resolution includes the lens blur and the expansion and reduction by the undistortion. The experimental results confirms to the effectiveness of our method which applies to the images captured by the digital camera with fish-eye lens.","PeriodicalId":325462,"journal":{"name":"2015 IEEE International Conference on Vehicular Electronics and Safety (ICVES)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114570937","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 : 2015-11-01DOI: 10.1109/ICVES.2015.7396927
Tianyi Guan, C. Frey
Energy efficiency has become a major issue in trade, transportation and environment protection. While the next generation of zero emission propulsion systems still have difficulties in reaching similar travel distances as combustion engine propulsion systems, it is already possible to increase fuel efficiency in regular vehicles by applying a more fuel efficient driving behaviour. An adapted Dynamic Programming approach is used to calculate optimal behaviour profiles for the road ahead within a finite optimization horizon. The main purpose of this publication is the development of a strategy to reuse historic minimal costs in order to reduce the computational complexity of future optimization steps. The percent reduction is deterministic and increases with the discretization degree of the optimization horizon.
{"title":"Reuse historic costs in dynamic programming to reduce computational complexity in the context of model predictive optimization","authors":"Tianyi Guan, C. Frey","doi":"10.1109/ICVES.2015.7396927","DOIUrl":"https://doi.org/10.1109/ICVES.2015.7396927","url":null,"abstract":"Energy efficiency has become a major issue in trade, transportation and environment protection. While the next generation of zero emission propulsion systems still have difficulties in reaching similar travel distances as combustion engine propulsion systems, it is already possible to increase fuel efficiency in regular vehicles by applying a more fuel efficient driving behaviour. An adapted Dynamic Programming approach is used to calculate optimal behaviour profiles for the road ahead within a finite optimization horizon. The main purpose of this publication is the development of a strategy to reuse historic minimal costs in order to reduce the computational complexity of future optimization steps. The percent reduction is deterministic and increases with the discretization degree of the optimization horizon.","PeriodicalId":325462,"journal":{"name":"2015 IEEE International Conference on Vehicular Electronics and Safety (ICVES)","volume":"101 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115447411","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 : 2015-11-01DOI: 10.1109/ICVES.2015.7396914
Luis Roldão, Joshué Pérez, D. González, V. M. Montero
The Cybernetic Transportation Systems (CTS) is an urban mobility concept based on two ideas: the car sharing and the automation of dedicated systems with door-todoor capabilities. In the last decade, many European projects have been developed in this context, where some of the most important are: Cybercars, Cybercars2, CyberMove, CyberC3 and CityMobil. Different companies have developed a first fleet of CTSs in collaboration with research centers around Europe, Asia and America. Considering these previous works, the FP7 project CityMobil2 is on progress since 2012. Its goal is to solve some of the limitations found so far, including the definition of the legal framework for autonomous vehicles on urban environment. This work describes the different improvements, adaptation and instrumentation of the CTS prototypes involved in European cities. Results show tests in our facilities at INRIARocquencourt (France) and the first showcase at Léon (Spain).
{"title":"Description and technical specifications of cybernetic transportation systems: an urban transportation concept","authors":"Luis Roldão, Joshué Pérez, D. González, V. M. Montero","doi":"10.1109/ICVES.2015.7396914","DOIUrl":"https://doi.org/10.1109/ICVES.2015.7396914","url":null,"abstract":"The Cybernetic Transportation Systems (CTS) is an urban mobility concept based on two ideas: the car sharing and the automation of dedicated systems with door-todoor capabilities. In the last decade, many European projects have been developed in this context, where some of the most important are: Cybercars, Cybercars2, CyberMove, CyberC3 and CityMobil. Different companies have developed a first fleet of CTSs in collaboration with research centers around Europe, Asia and America. Considering these previous works, the FP7 project CityMobil2 is on progress since 2012. Its goal is to solve some of the limitations found so far, including the definition of the legal framework for autonomous vehicles on urban environment. This work describes the different improvements, adaptation and instrumentation of the CTS prototypes involved in European cities. Results show tests in our facilities at INRIARocquencourt (France) and the first showcase at Léon (Spain).","PeriodicalId":325462,"journal":{"name":"2015 IEEE International Conference on Vehicular Electronics and Safety (ICVES)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116910023","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 : 2015-11-01DOI: 10.1109/ICVES.2015.7396892
Marcus Larsson, Fredrik Warg, K. Karlsson, M. Jonsson
In this paper we present a novel message forwarding algorithm, the reachability matrix algorithm, for V2V communication in a platooning scenario. The algorithm uses a communication quality estimate to determine appropriate forwarding candidates. We show that the algorithm achieve a higher reliability in the communication compared to only using broadcast but still keeping the message intensity at a low level. The reachability matrix algorithm can decrease the ratio of missing a data age limit of 0.2 seconds from 18% to 11%, a decrease of 40%, while increasing the message intensity by only 21% compared to only using broadcast. The evaluation has been performed through simulation using input from real-life V2V measurements on heavy duty trucks in a platooning scenario.
{"title":"Evaluation of a low-overhead forwarding algorithm for platooning","authors":"Marcus Larsson, Fredrik Warg, K. Karlsson, M. Jonsson","doi":"10.1109/ICVES.2015.7396892","DOIUrl":"https://doi.org/10.1109/ICVES.2015.7396892","url":null,"abstract":"In this paper we present a novel message forwarding algorithm, the reachability matrix algorithm, for V2V communication in a platooning scenario. The algorithm uses a communication quality estimate to determine appropriate forwarding candidates. We show that the algorithm achieve a higher reliability in the communication compared to only using broadcast but still keeping the message intensity at a low level. The reachability matrix algorithm can decrease the ratio of missing a data age limit of 0.2 seconds from 18% to 11%, a decrease of 40%, while increasing the message intensity by only 21% compared to only using broadcast. The evaluation has been performed through simulation using input from real-life V2V measurements on heavy duty trucks in a platooning scenario.","PeriodicalId":325462,"journal":{"name":"2015 IEEE International Conference on Vehicular Electronics and Safety (ICVES)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115246632","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 : 2015-11-01DOI: 10.1109/ICVES.2015.7396884
Chisa Takahasi, Y. Nakano, Y. Iribe, H. Kawanaka, K. Oguri
Japan is one of the leading country of the aging society. For traffic as well, the number of the traffic accidents caused by senior driver is increasing year by year. So we have to make countermeasure for it ahead of the other countries. Currently, Japanese government moved into actions for example to have the campaign for returning of the senior drivers' licenses, or oblige senior driver who doesn't want to return his/her license to take a driving lessons at the driving school each 3 years. But to resolve this problem, society have to take a radically -new way to support senior drivers they can drive much more safely. It would be help for the senior people to keep healthy life. We had to 2 activity. One was a questioner research to understand what type of the traffic situations have the possibility of the traffic accident caused by senior drivers. The result was, it likely to be better to prioritize supporting for the decreasing visual cognitive ability and judgment for the countermeasures. Secondly, we analyzed senior drivers driving test results using driving simulator to see whether there is any variability of the performance among in senior drivers, and also to see their driving ability tendency.
{"title":"Study of the senior driver's driving conscious against the specification traffic situation and driving behaviors","authors":"Chisa Takahasi, Y. Nakano, Y. Iribe, H. Kawanaka, K. Oguri","doi":"10.1109/ICVES.2015.7396884","DOIUrl":"https://doi.org/10.1109/ICVES.2015.7396884","url":null,"abstract":"Japan is one of the leading country of the aging society. For traffic as well, the number of the traffic accidents caused by senior driver is increasing year by year. So we have to make countermeasure for it ahead of the other countries. Currently, Japanese government moved into actions for example to have the campaign for returning of the senior drivers' licenses, or oblige senior driver who doesn't want to return his/her license to take a driving lessons at the driving school each 3 years. But to resolve this problem, society have to take a radically -new way to support senior drivers they can drive much more safely. It would be help for the senior people to keep healthy life. We had to 2 activity. One was a questioner research to understand what type of the traffic situations have the possibility of the traffic accident caused by senior drivers. The result was, it likely to be better to prioritize supporting for the decreasing visual cognitive ability and judgment for the countermeasures. Secondly, we analyzed senior drivers driving test results using driving simulator to see whether there is any variability of the performance among in senior drivers, and also to see their driving ability tendency.","PeriodicalId":325462,"journal":{"name":"2015 IEEE International Conference on Vehicular Electronics and Safety (ICVES)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121357646","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 : 2015-11-01DOI: 10.1109/ICVES.2015.7396899
Ryo Gohara, H. Premachandra, Kiyotaka Kato
Various studies have been conducted regarding road obstacle detection and avoidance, but very few studies deal with the detection and avoidance of obstacles that suddenly and unexpectedly appear during vehicle operation. Therefore, we have been conducting studies on problem of detecting suddenly and unexpectedly appear obstacles. As an extension stage of those studies, this paper presents about automatic smooth stopping of vehicle using a fuzzy control system. The proposed system conducts stopping control of the vehicle depending on the distance to the obstacle and vehicle speed when obstacle is detected. The simulation experiments and actual experiments using a mobile robot on behalf of a vehicle were conducted regarding the proposal.
{"title":"A study on smooth automatic vehicle stopping control for suddenly-appeared obstacles","authors":"Ryo Gohara, H. Premachandra, Kiyotaka Kato","doi":"10.1109/ICVES.2015.7396899","DOIUrl":"https://doi.org/10.1109/ICVES.2015.7396899","url":null,"abstract":"Various studies have been conducted regarding road obstacle detection and avoidance, but very few studies deal with the detection and avoidance of obstacles that suddenly and unexpectedly appear during vehicle operation. Therefore, we have been conducting studies on problem of detecting suddenly and unexpectedly appear obstacles. As an extension stage of those studies, this paper presents about automatic smooth stopping of vehicle using a fuzzy control system. The proposed system conducts stopping control of the vehicle depending on the distance to the obstacle and vehicle speed when obstacle is detected. The simulation experiments and actual experiments using a mobile robot on behalf of a vehicle were conducted regarding the proposal.","PeriodicalId":325462,"journal":{"name":"2015 IEEE International Conference on Vehicular Electronics and Safety (ICVES)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123239595","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 : 2015-11-01DOI: 10.1109/ICVES.2015.7396889
Jaewoong Ko, Juho Lee, Chulsung Park, Sungkown Park
The existing In-Vehicle Network (IVN) is hard to support multimedia/infotainment service because it does not have enough bandwidth. In order to solve this problem, IEEE 802.1 Time Sensitive Network (TSN) has been developed. TSN standard defines the scheduled traffic which is based on the time-triggered communication. But the details of transmission period and Maximum Transmit Unit (MTU) size of the scheduled traffic have not been defined yet. In this paper, we simulated several cases in order to decide the optimal bandwidth allocation ratio for the scheduled traffic by adjusting scheduled traffic's MTU size.
现有车载网络(IVN)带宽不足，难以支持多媒体/信息娱乐服务。为了解决这一问题，IEEE 802.1时间敏感网络(TSN)应运而生。TSN标准定义了基于时间触发通信的计划流量。但是关于调度流量的传输周期和最大传输单元(Maximum Transmit Unit, MTU)大小的详细信息还没有定义。在本文中，我们模拟了几种情况，通过调整计划流量的MTU大小来确定计划流量的最佳带宽分配比例。
{"title":"Research on optimal bandwidth allocation for the scheduled traffic in ieee 802.1 AVB","authors":"Jaewoong Ko, Juho Lee, Chulsung Park, Sungkown Park","doi":"10.1109/ICVES.2015.7396889","DOIUrl":"https://doi.org/10.1109/ICVES.2015.7396889","url":null,"abstract":"The existing In-Vehicle Network (IVN) is hard to support multimedia/infotainment service because it does not have enough bandwidth. In order to solve this problem, IEEE 802.1 Time Sensitive Network (TSN) has been developed. TSN standard defines the scheduled traffic which is based on the time-triggered communication. But the details of transmission period and Maximum Transmit Unit (MTU) size of the scheduled traffic have not been defined yet. In this paper, we simulated several cases in order to decide the optimal bandwidth allocation ratio for the scheduled traffic by adjusting scheduled traffic's MTU size.","PeriodicalId":325462,"journal":{"name":"2015 IEEE International Conference on Vehicular Electronics and Safety (ICVES)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123534272","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 : 2015-11-01DOI: 10.1109/ICVES.2015.7396923
V. John, Qian Long, Zheng Liu, S. Mita
Perception of the environment is an important task for intelligent vehicles, and to effectively perceive the environment, multiple sensors are often employed. In this paper, we propose to integrate the perceived data from 3D LIDAR and stereo camera using particle swarm optimization algorithm, without the aid of any external calibration aids. The proposed optimisation algorithm automatically calibrates and registers the LIDAR range image and stereo depth image, as a precursor to the sensor fusion. Multiple parameters are optimised by adopting a model-based approach during the parameter estimation phase. The evaluation of the parameters is performed using a novel depth-based cost function. During the sensor fusion phase, the optimised parameters are used to generate the LIDAR range image, which functions as the disparity range image for the Viterbi-based stereo disparity estimation. The disparity range image constrains the Viterbi search during the stereo disparity estimation. To evaluate our proposed algorithm, the calibration and registration algorithm is compared with baseline algorithms on multiple datasets acquired with varying illuminations. Compared to the baseline algorithms, we show that our proposed algorithm demonstrates better accuracy. We also demonstrate that integrating the LIDAR range image within the stereo's disparity estimation results in an improved disparity map with significant reduction in the computational complexity.
{"title":"Automatic calibration and registration of lidar and stereo camera without calibration objects","authors":"V. John, Qian Long, Zheng Liu, S. Mita","doi":"10.1109/ICVES.2015.7396923","DOIUrl":"https://doi.org/10.1109/ICVES.2015.7396923","url":null,"abstract":"Perception of the environment is an important task for intelligent vehicles, and to effectively perceive the environment, multiple sensors are often employed. In this paper, we propose to integrate the perceived data from 3D LIDAR and stereo camera using particle swarm optimization algorithm, without the aid of any external calibration aids. The proposed optimisation algorithm automatically calibrates and registers the LIDAR range image and stereo depth image, as a precursor to the sensor fusion. Multiple parameters are optimised by adopting a model-based approach during the parameter estimation phase. The evaluation of the parameters is performed using a novel depth-based cost function. During the sensor fusion phase, the optimised parameters are used to generate the LIDAR range image, which functions as the disparity range image for the Viterbi-based stereo disparity estimation. The disparity range image constrains the Viterbi search during the stereo disparity estimation. To evaluate our proposed algorithm, the calibration and registration algorithm is compared with baseline algorithms on multiple datasets acquired with varying illuminations. Compared to the baseline algorithms, we show that our proposed algorithm demonstrates better accuracy. We also demonstrate that integrating the LIDAR range image within the stereo's disparity estimation results in an improved disparity map with significant reduction in the computational complexity.","PeriodicalId":325462,"journal":{"name":"2015 IEEE International Conference on Vehicular Electronics and Safety (ICVES)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2015-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128200257","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：