Pub Date : 2014-07-17DOI: 10.1109/IVS.2014.6856423
S. Miura, Feiyu Chen, S. Kamijo
The accurate and reliable positions of pedestrians are important and useful information. Although global positioning systems (GPSs) in smartphones are currently the most convenient devices to obtain the positions of pedestrians, GPSs still have problems with their accuracy and reliability because of the performance degradation caused by multipath and non-line-of-sight (NLOS) propagation in urban canyons. This study describes an approach to estimate a position by searching around the reference position. Position candidates are prepared and evaluated based on the similarity between the simulated pseudorange from the candidate and the observed pseudorange. Simulated pseudoranges are calculated on the basis of a ray-tracing simulation. The proposed method was verified through field experiments in urban canyons in Tokyo. It successfully estimates the reflection paths and direct paths so that the estimate appears very close to the ground truth even though the GPS result is far away from the ground truth.
{"title":"GPS precise positioning with pseudorange evaluation using 3-dimensional maps","authors":"S. Miura, Feiyu Chen, S. Kamijo","doi":"10.1109/IVS.2014.6856423","DOIUrl":"https://doi.org/10.1109/IVS.2014.6856423","url":null,"abstract":"The accurate and reliable positions of pedestrians are important and useful information. Although global positioning systems (GPSs) in smartphones are currently the most convenient devices to obtain the positions of pedestrians, GPSs still have problems with their accuracy and reliability because of the performance degradation caused by multipath and non-line-of-sight (NLOS) propagation in urban canyons. This study describes an approach to estimate a position by searching around the reference position. Position candidates are prepared and evaluated based on the similarity between the simulated pseudorange from the candidate and the observed pseudorange. Simulated pseudoranges are calculated on the basis of a ray-tracing simulation. The proposed method was verified through field experiments in urban canyons in Tokyo. It successfully estimates the reflection paths and direct paths so that the estimate appears very close to the ground truth even though the GPS result is far away from the ground truth.","PeriodicalId":254500,"journal":{"name":"2014 IEEE Intelligent Vehicles Symposium Proceedings","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115042316","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 : 2014-06-08DOI: 10.1109/IVS.2014.6856579
K. A. Rahman, K. Tepe
The DSRC/WAVE system is standardized to disseminate safety critical information using IEEE 802.11p as a MAC protocol. Studies show that IEEE 802.11p does not address adverse effects of asymmetric radio link and mobility related problems in vehicle to vehicle (V2V) and vehicle to infrastructure (V2I) communications. This paper presents a cross-layer (i.e. MAC and network) algorithm to address these problems for making the V2V and V2I communications efficient and reliable. The analysis shows that the proposed cross-layer algorithm removes contention in channel accessing and confirms a better channel utilization. The solution can be used to disseminate information up to three hops without using a routing protocol. This is particularly important for extending range of safety critical and emergency related messages in the vehicular network.
{"title":"Towards a cross-layer based MAC for smooth V2V and V2I communications for safety applications in DSRC/WAVE based systems","authors":"K. A. Rahman, K. Tepe","doi":"10.1109/IVS.2014.6856579","DOIUrl":"https://doi.org/10.1109/IVS.2014.6856579","url":null,"abstract":"The DSRC/WAVE system is standardized to disseminate safety critical information using IEEE 802.11p as a MAC protocol. Studies show that IEEE 802.11p does not address adverse effects of asymmetric radio link and mobility related problems in vehicle to vehicle (V2V) and vehicle to infrastructure (V2I) communications. This paper presents a cross-layer (i.e. MAC and network) algorithm to address these problems for making the V2V and V2I communications efficient and reliable. The analysis shows that the proposed cross-layer algorithm removes contention in channel accessing and confirms a better channel utilization. The solution can be used to disseminate information up to three hops without using a routing protocol. This is particularly important for extending range of safety critical and emergency related messages in the vehicular network.","PeriodicalId":254500,"journal":{"name":"2014 IEEE Intelligent Vehicles Symposium Proceedings","volume":"125 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116793536","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 : 2014-06-08DOI: 10.1109/IVS.2014.6856468
Shogo Nagasaka, T. Taniguchi, K. Hitomi, Kazuhito Takenaka, T. Bando
Future advanced driver assistance systems (ADASs) should observe a driving behavior and detect contextual changing points of driving behaviors. In this paper, we propose a novel method for predicting the next contextual changing point of driving behavior on the basis of a Bayesian double articulation analyzer. To develop the method, we extended a previously proposed semiotic predictor using an unsupervised double articulation analyzer that can extract a two-layered hierarchical structure from driving-behavior data. We employ the hierarchical Dirichlet process hidden semi-Markov model [4] to model duration time of a segment of driving behavior explicitly instead of the sticky hierarchical Dirichlet process hidden Markov model (HDP-HMM) employed in the previous model [13]. Then, to recover the hierarchical structure of contextual driving behavior as a sequence of chunks, we use the Nested Pitman-Yor Language model [6], which can extract latent words from sequences of latent letters. On the basis of the extension, we develop a method for calculating posterior probability distribution of the next contextual changing point by marginalizing potentially possible results of the chunking method and potentially successive words theoretically. To evaluate the proposed method, we applied the method to synthetic data and driving behavior data that was recorded in a real environment. The results showed that the proposed method can predict the next contextual changing point more accurately and in a longer-term manner than the compared methods: linear regression and Recurrent Neural Networks, which were trained through a supervised learning scheme.
{"title":"Prediction of Next Contextual Changing Point of Driving Behavior Using Unsupervised Bayesian Double Articulation Analyzer","authors":"Shogo Nagasaka, T. Taniguchi, K. Hitomi, Kazuhito Takenaka, T. Bando","doi":"10.1109/IVS.2014.6856468","DOIUrl":"https://doi.org/10.1109/IVS.2014.6856468","url":null,"abstract":"Future advanced driver assistance systems (ADASs) should observe a driving behavior and detect contextual changing points of driving behaviors. In this paper, we propose a novel method for predicting the next contextual changing point of driving behavior on the basis of a Bayesian double articulation analyzer. To develop the method, we extended a previously proposed semiotic predictor using an unsupervised double articulation analyzer that can extract a two-layered hierarchical structure from driving-behavior data. We employ the hierarchical Dirichlet process hidden semi-Markov model [4] to model duration time of a segment of driving behavior explicitly instead of the sticky hierarchical Dirichlet process hidden Markov model (HDP-HMM) employed in the previous model [13]. Then, to recover the hierarchical structure of contextual driving behavior as a sequence of chunks, we use the Nested Pitman-Yor Language model [6], which can extract latent words from sequences of latent letters. On the basis of the extension, we develop a method for calculating posterior probability distribution of the next contextual changing point by marginalizing potentially possible results of the chunking method and potentially successive words theoretically. To evaluate the proposed method, we applied the method to synthetic data and driving behavior data that was recorded in a real environment. The results showed that the proposed method can predict the next contextual changing point more accurately and in a longer-term manner than the compared methods: linear regression and Recurrent Neural Networks, which were trained through a supervised learning scheme.","PeriodicalId":254500,"journal":{"name":"2014 IEEE Intelligent Vehicles Symposium Proceedings","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116867729","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 : 2014-06-08DOI: 10.1109/IVS.2014.6856482
S. Kwon, Changyoung Jung, T. Choi, Y. Oh, B. You
As the proportion of older people in the population is growing, the demand for older driver safety is increasing sharply because their driving abilities are lowered. In this paper, we propose an autonomous emergency stop system to support older people. It activates an autonomous driving mode when the driver cannot control his vehicle any more, and stops the vehicle safely. It recognizes situation around the vehicle by using a camera, radars, and ultrasonic sensors and makes a decision about safety. The vehicle changes lanes according to the safety and stops on the side of the road.
{"title":"Autonomous emergency stop system","authors":"S. Kwon, Changyoung Jung, T. Choi, Y. Oh, B. You","doi":"10.1109/IVS.2014.6856482","DOIUrl":"https://doi.org/10.1109/IVS.2014.6856482","url":null,"abstract":"As the proportion of older people in the population is growing, the demand for older driver safety is increasing sharply because their driving abilities are lowered. In this paper, we propose an autonomous emergency stop system to support older people. It activates an autonomous driving mode when the driver cannot control his vehicle any more, and stops the vehicle safely. It recognizes situation around the vehicle by using a camera, radars, and ultrasonic sensors and makes a decision about safety. The vehicle changes lanes according to the safety and stops on the side of the road.","PeriodicalId":254500,"journal":{"name":"2014 IEEE Intelligent Vehicles Symposium Proceedings","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120845611","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 : 2014-06-08DOI: 10.1109/IVS.2014.6856576
A. Peker, T. Acarman, Cagdas Yaman, E. Yüksel
This paper presents an assisted system for vehicle localization and map-matching by utilizing Vehicle ad-hoc Networks (VANETs). Fusion of the GNSS and odometer measurement is augmented by ranging distance. Ranging is computed by exchanging the data packets between the vehicular nodes equipped with Dedicated Short Range Communication (DSRC) modem and GNSS receiver. Time-of-Arrival (ToA) of exchanged data packet between the two vehicular nodes is converted in distance. Map matching enhances accuracy of localization while projecting the result of multilateration created by numerous ranging queries. Realistic simulations are conducted to test the performance of the algorithm. Test results show bounded and acceptable particle filter positioning results. The scenario of GPS outages and low number of vehicles collaborating for positioning are simulated. Tracking performance of the particle filter is illustrated. Algorithm helps dead reckoning when GPS data is not available temporarily. A simple GPS receiver is fused with odometer data during tests. Particularly, expensive sensors are not used to achieve better price/performance towards commercial usage.
{"title":"Vehicle localization enhancement with VANETs","authors":"A. Peker, T. Acarman, Cagdas Yaman, E. Yüksel","doi":"10.1109/IVS.2014.6856576","DOIUrl":"https://doi.org/10.1109/IVS.2014.6856576","url":null,"abstract":"This paper presents an assisted system for vehicle localization and map-matching by utilizing Vehicle ad-hoc Networks (VANETs). Fusion of the GNSS and odometer measurement is augmented by ranging distance. Ranging is computed by exchanging the data packets between the vehicular nodes equipped with Dedicated Short Range Communication (DSRC) modem and GNSS receiver. Time-of-Arrival (ToA) of exchanged data packet between the two vehicular nodes is converted in distance. Map matching enhances accuracy of localization while projecting the result of multilateration created by numerous ranging queries. Realistic simulations are conducted to test the performance of the algorithm. Test results show bounded and acceptable particle filter positioning results. The scenario of GPS outages and low number of vehicles collaborating for positioning are simulated. Tracking performance of the particle filter is illustrated. Algorithm helps dead reckoning when GPS data is not available temporarily. A simple GPS receiver is fused with odometer data during tests. Particularly, expensive sensors are not used to achieve better price/performance towards commercial usage.","PeriodicalId":254500,"journal":{"name":"2014 IEEE Intelligent Vehicles Symposium Proceedings","volume":"193 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121048678","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 : 2014-06-08DOI: 10.1109/IVS.2014.6856535
R. Belaroussi, D. Gruyer
In camera-based Advance Driver Assistance System (ADAS) such as traffic sign recognition, some failure may be inferred by adverse meteorological conditions, in particular under foggy weather. This paper investigates the effects of reduced visibility from fog in an ADAS operating range, more specifically a traffic sign detection algorithm. For this purpose, we produced a database of synthetic images containing road signs with and without fog, that is intended to be shared with the scientific community. The database enables a study of the effects of reduced visibility from fog on a gradient-based geometrical model of traffic signs. After analysing the tolerance of the algorithm to additive noise and blurring, its performance is measured under increasing level of fog. Its operating range is measured with regard to the fog density: we discuss the way the distance required to detect a sign increases with the meteorological visibility distance and its impact on safety.
{"title":"Impact of reduced visibility from fog on traffic sign detection","authors":"R. Belaroussi, D. Gruyer","doi":"10.1109/IVS.2014.6856535","DOIUrl":"https://doi.org/10.1109/IVS.2014.6856535","url":null,"abstract":"In camera-based Advance Driver Assistance System (ADAS) such as traffic sign recognition, some failure may be inferred by adverse meteorological conditions, in particular under foggy weather. This paper investigates the effects of reduced visibility from fog in an ADAS operating range, more specifically a traffic sign detection algorithm. For this purpose, we produced a database of synthetic images containing road signs with and without fog, that is intended to be shared with the scientific community. The database enables a study of the effects of reduced visibility from fog on a gradient-based geometrical model of traffic signs. After analysing the tolerance of the algorithm to additive noise and blurring, its performance is measured under increasing level of fog. Its operating range is measured with regard to the fog density: we discuss the way the distance required to detect a sign increases with the meteorological visibility distance and its impact on safety.","PeriodicalId":254500,"journal":{"name":"2014 IEEE Intelligent Vehicles Symposium Proceedings","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125933114","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 : 2014-06-08DOI: 10.1109/IVS.2014.6856472
A. R. A. Bacha, D. Gruyer, A. Lambert
This paper presents the Optimized Kalman Particle Swarm (OKPS) filter. This filter is a new robust data fusion approach adapted for ego-vehicle localization in degraded signal conditions. The OKPS is the improved version of the hybridization of the Particle Filter (PF) by Particle Swarm Optimization notions (PSO). Taking also some features from the Extended Kalman filter (EKF), the OKPS is designed for being more robust to noises such as GPS multipaths and also more reactive. The OKPS has the challenge of merging reactivity and resistance to noises. For high dynamic on-road vehicles localization, the balance between reactivity and robustness is critical. This paper introduces an intelligent collaborative localization algorithm inspired by PSO techniques that addresses this challenge. The OKPS filter outline integrates Particle Filter (PF) tracking, PSO evolutionary optimization and EKF self-diagnose. Using real world data, the OKPS is tested in comparison to the EKF and PF approaches performances. The comparison is done following new specific criteria, designed for ego-localization filter performances analysis. Competitive results are reached for a high dynamic on-road vehicle localization application.
{"title":"A performance test for a new reactive-cooperative filter in an ego-vehicle localization application","authors":"A. R. A. Bacha, D. Gruyer, A. Lambert","doi":"10.1109/IVS.2014.6856472","DOIUrl":"https://doi.org/10.1109/IVS.2014.6856472","url":null,"abstract":"This paper presents the Optimized Kalman Particle Swarm (OKPS) filter. This filter is a new robust data fusion approach adapted for ego-vehicle localization in degraded signal conditions. The OKPS is the improved version of the hybridization of the Particle Filter (PF) by Particle Swarm Optimization notions (PSO). Taking also some features from the Extended Kalman filter (EKF), the OKPS is designed for being more robust to noises such as GPS multipaths and also more reactive. The OKPS has the challenge of merging reactivity and resistance to noises. For high dynamic on-road vehicles localization, the balance between reactivity and robustness is critical. This paper introduces an intelligent collaborative localization algorithm inspired by PSO techniques that addresses this challenge. The OKPS filter outline integrates Particle Filter (PF) tracking, PSO evolutionary optimization and EKF self-diagnose. Using real world data, the OKPS is tested in comparison to the EKF and PF approaches performances. The comparison is done following new specific criteria, designed for ego-localization filter performances analysis. Competitive results are reached for a high dynamic on-road vehicle localization application.","PeriodicalId":254500,"journal":{"name":"2014 IEEE Intelligent Vehicles Symposium Proceedings","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126966810","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 : 2014-06-08DOI: 10.1109/IVS.2014.6856471
William P. Maddern, Alexander D. Stewart, P. Newman
Robust and reliable visual localisation at any time of day is an essential component towards low-cost autonomy for road vehicles. We present a method to perform online 6-DoF visual localisation across a wide range of outdoor illumination conditions throughout the day and night using a 3D scene prior collected by a survey vehicle. We propose the use of a one-dimensional illumination invariant colour space which stems from modelling the spectral properties of the camera and scene illumination in conjunction. We combine our previous work on Localisation with Appearance of Prior Structure (LAPS) with this illumination invariant colour space to demonstrate a marked improvement in our ability to localise throughout the day compared to using a conventional RGB colour space. Our ultimate goal is robust and reliable any-time localisation - an attractive proposition for low-cost autonomy for road vehicles. Accordingly, we demonstrate our technique using 32km of data collected over a full 24-hour period from a road vehicle.
{"title":"LAPS-II: 6-DoF day and night visual localisation with prior 3D structure for autonomous road vehicles","authors":"William P. Maddern, Alexander D. Stewart, P. Newman","doi":"10.1109/IVS.2014.6856471","DOIUrl":"https://doi.org/10.1109/IVS.2014.6856471","url":null,"abstract":"Robust and reliable visual localisation at any time of day is an essential component towards low-cost autonomy for road vehicles. We present a method to perform online 6-DoF visual localisation across a wide range of outdoor illumination conditions throughout the day and night using a 3D scene prior collected by a survey vehicle. We propose the use of a one-dimensional illumination invariant colour space which stems from modelling the spectral properties of the camera and scene illumination in conjunction. We combine our previous work on Localisation with Appearance of Prior Structure (LAPS) with this illumination invariant colour space to demonstrate a marked improvement in our ability to localise throughout the day compared to using a conventional RGB colour space. Our ultimate goal is robust and reliable any-time localisation - an attractive proposition for low-cost autonomy for road vehicles. Accordingly, we demonstrate our technique using 32km of data collected over a full 24-hour period from a road vehicle.","PeriodicalId":254500,"journal":{"name":"2014 IEEE Intelligent Vehicles Symposium Proceedings","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122299726","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 : 2014-06-08DOI: 10.1109/IVS.2014.6856584
Alexandre Constantin, Junghee Park, K. Iagnemma
In this paper we present a new approach to the threat assessment problem for semi-autonomous and fully autonomous vehicles, based on the estimation of the control freedom afforded to a vehicle. Given sensor information available about the surrounding environment, an algorithm is described for identifying fields of safe travel through which the vehicle can safely navigate. Within each candidate field, we then characterize the level of threat, to influence autonomous navigation or driver support inputs. To characterize threat, the fields of safe travel are associated with sets of feasible trajectories generated from a lattice sampled in the vehicle's input space. A planner then computes a metric associated with available control freedom from these sampled trajectories. This method potentially allows a semi-autonomous control system to honor safe driver inputs while ensuring safe and robust navigation properties. It could also serve as an input to an autonomous decision-making layer.
{"title":"A margin-based approach to threat assessment for autonomous highway navigation","authors":"Alexandre Constantin, Junghee Park, K. Iagnemma","doi":"10.1109/IVS.2014.6856584","DOIUrl":"https://doi.org/10.1109/IVS.2014.6856584","url":null,"abstract":"In this paper we present a new approach to the threat assessment problem for semi-autonomous and fully autonomous vehicles, based on the estimation of the control freedom afforded to a vehicle. Given sensor information available about the surrounding environment, an algorithm is described for identifying fields of safe travel through which the vehicle can safely navigate. Within each candidate field, we then characterize the level of threat, to influence autonomous navigation or driver support inputs. To characterize threat, the fields of safe travel are associated with sets of feasible trajectories generated from a lattice sampled in the vehicle's input space. A planner then computes a metric associated with available control freedom from these sampled trajectories. This method potentially allows a semi-autonomous control system to honor safe driver inputs while ensuring safe and robust navigation properties. It could also serve as an input to an autonomous decision-making layer.","PeriodicalId":254500,"journal":{"name":"2014 IEEE Intelligent Vehicles Symposium Proceedings","volume":"187 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122670624","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 : 2014-06-08DOI: 10.1109/IVS.2014.6856541
C. Jang, Chansoo Kim, Dongchul Kim, Minchae Lee, M. Sunwoo
This paper proposes a multiple exposure images based traffic light recognition method. For traffic light recognition, color segmentation is widely used to detect traffic light signals; however, the color in an image is easily affected by various illuminations and leads to incorrect recognition results. In order to overcome the problem, we propose the multiple exposure technique which enhances the robustness of the color segmentation and recognition accuracy by integrating both low and normal exposure images. The technique solves the color saturation problem and reduces false positives since the low exposure image is exposed for a short time. Based on candidate regions selected from the low exposure image, the status of six three and four bulb traffic lights in a normal image are classified utilizing a support vector machine with a histogram of oriented gradients. Our algorithm was finally evaluated in various urban scenarios and the results show that the proposed method works robustly for outdoor environments.
{"title":"Multiple exposure images based traffic light recognition","authors":"C. Jang, Chansoo Kim, Dongchul Kim, Minchae Lee, M. Sunwoo","doi":"10.1109/IVS.2014.6856541","DOIUrl":"https://doi.org/10.1109/IVS.2014.6856541","url":null,"abstract":"This paper proposes a multiple exposure images based traffic light recognition method. For traffic light recognition, color segmentation is widely used to detect traffic light signals; however, the color in an image is easily affected by various illuminations and leads to incorrect recognition results. In order to overcome the problem, we propose the multiple exposure technique which enhances the robustness of the color segmentation and recognition accuracy by integrating both low and normal exposure images. The technique solves the color saturation problem and reduces false positives since the low exposure image is exposed for a short time. Based on candidate regions selected from the low exposure image, the status of six three and four bulb traffic lights in a normal image are classified utilizing a support vector machine with a histogram of oriented gradients. Our algorithm was finally evaluated in various urban scenarios and the results show that the proposed method works robustly for outdoor environments.","PeriodicalId":254500,"journal":{"name":"2014 IEEE Intelligent Vehicles Symposium Proceedings","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121897051","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：