Integrating Driving Behavior and Traffic Context Through Signal Symbolization for Data Reduction and Risky Lane Change Detection
The DOI matches its Crossref record; 46 of the 47 references it cites were found in a registry or an index.
Abstract
A novel method for integrating driving behavior and traffic context through signal symbolization is presented in this paper. This symbolization framework is proposed as a data reduction method for naturalistic driving studies. Continuous sensor signals have been converted and reduced into sequences of symbols (chunks) using a sticky hierarchical Dirichlet process hidden Markov model and a nested Pitman-Yor language model. Then, co-occurrence chunking (COOC), the proposed integration method, has been applied to the driver behavior and the traffic context chunks. After the integration, COOC chunks have been associated with prototype driving scenes by using latent Dirichlet allocation. Finally, the translated sequence of chunks has been clustered into groups. Risky lane change detection experiments have been conducted with the symbolized data for evaluation purposes. A dataset comprised of 988 lane change scenes has been utilized for this process. Co-occurrence chunking with clustering provided the best risky lane change detection.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
(2003) · Journal of Machine Learning Research · doi:10.5555/944919.944937 · Cited by 32,337
Representation Learning: A Review and New Perspectives
Bengio, Y., Courville, A., & Vincent, P. (2013) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2013.50 · Cited by 13,001 · cited 1×
“In [19], the advantages of machine”
Dingus, T. A., Klauer, S. G., Neale, V. L., Petersen, A., Lee, S. E., Sudweeks, J., Perez, M. A., Hankey, J., Ramsey, D., Gupta, S., et al. (2006) · PsycEXTRA Dataset · doi:10.1037/e624282011-001 · Cited by 681
Segmenting motion capture data into distinct behaviors
Barbič, J., Safonova, A., Pan, J.-Y., Faloutsos, C., Hodgins, J. K., & Pollard, N. S. (2004) · Graphics Interface · Cited by 441
Motion texture: a two-level statistical model for character motion synthesis
Li, Y., Wang, T., & Shum, H.-Y. (2002) · Proceedings of the 29th annual conference on Computer graphics and interactive techniques · doi:10.1145/566570.566604 · Cited by 392
Driver Modeling Based on Driving Behavior and Its Evaluation in Driver Identification
Miyajima, C., Nishiwaki, Y., Ozawa, K., Wakita, T., Itou, K., Takeda, K., & Itakura, F. (2007) · Proceedings of the IEEE · doi:10.1109/jproc.2006.888405 · Cited by 339
Self-citationAutomated Derivation of Primitives for Movement Classification
Fod, A., Matarić, M. J., & Jenkins, O. C. (2002) · Autonomous Robots · doi:10.1023/a:1013254724861 · Cited by 318
Tani, J., & Nolfi, S. (1999) · Neural Networks · doi:10.1016/s0893-6080(99)00060-x · Cited by 259
Bayesian unsupervised word segmentation with nested Pitman-Yor language modeling
Mochihashi, D., Yamada, T., & Ueda, N. (2009) · Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP: Volume 1 - ACL-IJCNLP '09 · doi:10.3115/1687878.1687894 · Cited by 240 · cited 9×
“DAA assumes this semiotic structure exists in driving behavior. sHDP-HMM is used for primitive segmentation and NPYLM is utilized for chunking the segmented data.”
MethodInfluential(2010) · PsycEXTRA Dataset · doi:10.1037/e729232011-001 · Cited by 127
Driver's lane keeping ability with eyes off road: Insights from a naturalistic study
Peng, Y., Boyle, L. N., & Hallmark, S. L. (2012) · Accident Analysis & Prevention · doi:10.1016/j.aap.2012.06.013 · Cited by 104 · cited 1×
“Studies such as [12]–[15] proposed to employ trained annotators who use a reference dictionary to manually describe driving videos and segment them for the data reduction task.”
BackgroundDevelopment and testing of a fully Adaptive Cruise Control system
Bifulco, G. N., Pariota, L., Simonelli, F., & Pace, R. D. (2011) · Transportation Research Part C Emerging Technologies · doi:10.1016/j.trc.2011.07.001 · Cited by 100 · cited 1×
“[7] noted that recogniz-”
Drive Analysis Using Vehicle Dynamics and Vision-Based Lane Semantics
Satzoda, R. K., & Trivedi, M. M. (2014) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2014.2331259 · Cited by 90 · cited 2×
“In [16], vision and learning-based techniques are used for detecting a set of events which are then used to describe the dataset.”
BackgroundMethodInternational Large-Scale Vehicle Corpora for Research on Driver Behavior on the Road
Takeda, K., Hansen, J. H. L., Boyraz, P., Malta, L., Miyajima, C., & Abut, H. (2011) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2011.2167680 · Cited by 89 · cited 2×
“We used NUDrive corpus [5] in our experiments.”
BackgroundMethodSelf-citationThe Sticky HDP-HMM: Bayesian Nonparametric Hidden Markov Models with Persistent StatesPreprint
Fox, E. B., Sudderth, E. B., Jordan, M. I., & Willsky, A. S. (2009) · arXiv (Cornell University) · Cited by 70
A Dynamic HMM for On-line Segmentation of Sequential Data
Kohlmorgen, J., & Lemm, S. (2001) · Cited by 69
Benmimoun, M., Pütz, A., Zlocki, A., & Eckstein, L. (2013) · Lecture Notes in Electrical Engineering · doi:10.1007/978-3-642-33805-2_43 · Cited by 64
Tian, R., Li, L., Chen, M., Chen, Y., & Witt, G. J. (2013) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2013.2261988 · Cited by 60 · cited 2×
“[6] stated that detecting driver distraction and find-”
BackgroundMethodMovement extraction by detecting dynamics switches and repetitions
Chiappa, S., & Peters, J. (2011) · Max Planck Institute for Plasma Physics · Cited by 51
Sequence Prediction of Driving Behavior Using Double Articulation Analyzer
Taniguchi, T., Nagasaka, S., Hitomi, K., Chandrasiri, N. P., Bando, T., & Takenaka, K. (2015) · IEEE Transactions on Systems Man and Cybernetics Systems · doi:10.1109/tsmc.2015.2465933 · Cited by 49 · cited 1×
“Further studies such as [38], [39], [40] and [18] showed that symbolized data obtained with a DAA approach can be utilized for predicting driving behaviors with”
BackgroundSelf-citationUnsupervised drive topic finding from driving behavioral data
Bando, T., Takenaka, K., Nagasaka, S., & Taniguchi, T. (2013) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2013.6629467 · Cited by 46
Unsupervised Hierarchical Modeling of Driving Behavior and Prediction of Contextual Changing Points
Taniguchi, T., Nagasaka, S., Hitomi, K., Takenaka, K., & Bando, T. (2014) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2014.2376525 · Cited by 46 · cited 1×
“Further studies such as [38], [39], [40] and [18] showed that symbolized data obtained with a DAA approach can be utilized for predicting driving behaviors with”
BackgroundSelf-citationRubin, J. M., & Richards, W. A. (1985) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 43
Semiotic prediction of driving behavior using unsupervised double articulation analyzer
Taniguchi, T., Nagasaka, S., Hitomi, K., Chandrasiri, N. P., & Bando, T. (2012) · 2012 IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2012.6232243 · Cited by 43 · cited 3×
“DAA was considered as a naturalistic driving data reduction method first in [36] and [37].”
MethodSelf-citationContextual scene segmentation of driving behavior based on double articulation analyzer
Takenaka, K., Bando, T., Nagasaka, S., Taniguchi, T., & Hitomi, K. (2012) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2012.6385614 · Cited by 41 · cited 1×
“DAA was considered as a naturalistic driving data reduction method first in [36] and [37].”
MethodSelf-citationNaturalistic Driving Study: Field Data Collection
Blatt, A., Pierowicz, J., Flanigan, M., Lin, P.-S., Kourtellis, A., Jovanis, P., Jenness, J., Wilaby, M., Campbell, J., Richard, C., et al. (2014) · Transportation Research Board eBooks · doi:10.17226/22367 · Cited by 40 · cited 1×
“HUGE amounts of naturalistic driving data are being and have been collected by various projects such as [1]–[5].”
BackgroundEmergence of hierarchical structure mirroring linguistic composition in a recurrent neural network
Hinoshita, W., Arie, H., Tani, J., Okuno, H. G., & Ogata, T. (2011) · Neural Networks · doi:10.1016/j.neunet.2010.12.006 · Cited by 37
Experience-based imitation using RNNPB
Yokoya, R., Ogata, T., Tani, J., Komatani, K., & Okuno, H. G. (2007) · Advanced Robotics · doi:10.1163/156855307781746106 · Cited by 30
Taniguchi, T., Hamahata, K., & Iwahashi, N. (2011) · Advanced Robotics · doi:10.1163/016918611x594775 · Cited by 29 · cited 3×
“These methods are analyzed and the shortcomings of each are presented in [20].”
BackgroundMethodInfluentialKadone, H., & Nakamura, Y. (2006) · IEEE-RAS International Conference on Humanoid Robots (Humanoids) · doi:10.1109/ichr.2006.321355 · Cited by 28 · cited 1×
“text information with nonlinear predictors [28]–[32] and finding repeated segments in a continuous time series [33], [34].”
BackgroundSymbolization and imitation learning of motion sequence using competitive modules
Samejima, K., Katagiri, K.-I., Doya, K., & Kawato, M. (2006) · Electronics and Communications in Japan (Part III Fundamental Electronic Science) · doi:10.1002/ecjc.20267 · Cited by 27
Multiphase Learning for an Interval-Based Hybrid Dynamical System
宏彰, 川. (2005) · IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences · doi:10.1093/ietfec/e88-a.11.3022 · Cited by 21
Human-Robot Cooperation using Quasi-symbols Generated by RNNPB Model
Ogata, T., Matsumoto, S., Tani, J., Komatani, K., & Okuno, H. G. (2007) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/robot.2007.363640 · Cited by 20 · cited 1×
“text information with nonlinear predictors [28]–[32] and finding repeated segments in a continuous time series [33], [34].”
BackgroundDrive analysis using lane semantics for data reduction in naturalistic driving studies
Satzoda, R. K., Gunaratne, P., & Trivedi, M. M. (2014) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2014.6856609 · Cited by 19 · cited 1×
“Furthermore, categorizing data is usually very time consuming, as manual labor is required for labeling driving scenes throughout the continuous data [8].”
BackgroundAutomatic lane change extraction based on temporal patterns of symbolized driving behavioral data
Mori, M., Takenaka, K., Bando, T., Taniguchi, T., Miyajima, C., & Takeda, K. (2015) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2015.7225811 · Cited by 17 · cited 1×
“[45] improved the implementation of the algorithm and obtained good results with this approach for extracting specific driving behavior from driving data corpora.”
MethodSelf-citationAcoustic road-type estimation for intelligent vehicle safety applications
Boyraz, P. (2014) · International Journal of Vehicle Safety · doi:10.1504/ijvs.2014.060167 · Cited by 14 · cited 1×
“Studies such as [47] focuses on retrieval of environmental information.”
BackgroundGenerating contextual description from driving behavioral data
Bando, T., Takenaka, K., Nagasaka, S., & Taniguchi, T. (2014) · 2014 IEEE Intelligent Vehicles Symposium Proceedings · doi:10.1109/ivs.2014.6856476 · Cited by 14 · cited 7×
“The rest of this section is dedicated to the explanation of the following algorithms that we employed in our framework: Double Articulation Analyzer (DAA), for converting raw signals into symbols [36] Latent Dirichlet Allocation (LDA), for translating unsupervised symbols and associating them with prototype driving sc…”
BackgroundMethodInfluentialDetermining Utterance Timing of a Driving Agent With Double Articulation Analyzer
Taniguchi, T., Furusawa, K., Liu, H., Tanaka, Y. Z., Takenaka, K., & Bando, T. (2015) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2015.2484421 · Cited by 13 · cited 1×
“Further studies such as [38], [39], [40] and [18] showed that symbolized data obtained with a DAA approach can be utilized for predicting driving behaviors with”
BackgroundAnalysis of Existing Data: Prospective Views on Methodological Paradigms
Jovanis, P. P., Shankar, V. N., Agüero-Valverde, J., Wu, K.-F., Greenstein, A., & University of Washington (2012) · Transportation Research Board eBooks · doi:10.17226/22837 · Cited by 11 · cited 2×
“Recent studies, [9] and [10], suggested to use automatic tools for driving data reduction.”
BackgroundOKADA, M., Nakamura, D., & Nakamura, Y. (2005) · Transactions of the Japanese Society for Artificial Intelligence · doi:10.1527/tjsai.20.177 · Cited by 11 · cited 1×
“text information with nonlinear predictors [28]–[32] and finding repeated segments in a continuous time series [33], [34].”
BackgroundIntegrating driving behavior and traffic context through signal symbolization
Yamazaki, S., Miyajima, C., Yurtsever, E., Takeda, K., Mori, M., Hitomi, K., & Egawa, M. (2016) · 2016 IEEE Intelligent Vehicles Symposium (IV) · doi:10.1109/ivs.2016.7535455 · Cited by 11 · cited 1×
“Which is why we believe that the symbolization has to be carried independently [48].”
BackgroundSelf-citationTraffic trajectory history and drive path generation using GPS data cloud
Yurtsever, E., Takeda, K., & Miyajima, C. (2015) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2015.7225691 · Cited by 8 · cited 1×
“mation signals [46].”
Self-citationSafe maneuverability zones & metrics for data reduction in naturalistic driving studies
Satzoda, R. K., & Trivedi, M. M. (2016) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2016.7535513 · Cited by 4 · cited 1×
“[17] formulated a set of metrics for describing driving scenes automatically with respect to the threat posed by the surrounding vehicles on the ego vehicle.”
BackgroundYurtsever, E., Miyajima, C., Selpi, S., & Takeda, K. (2015) · Chalmers Publication Library (Chalmers University of Technology) · Cited by 3
Self-citationFuchida, Y., Taniguchi, T., Takano, T., Mori, T., Takenaka, K., & Bando, T. (2016) · IEEE Intelligent Vehicles Symposium · doi:10.1109/ivs.2016.7535560 · Cited by 2 · cited 2×
“Further studies such as [38], [39], [40] and [18] showed that symbolized data obtained with a DAA approach can be utilized for predicting driving behaviors with”
Background
Research works printed but not linked: 4
- klauer, 2010, An analysis of driver inattention using a case-crossover approach on 100-car data, Tech Rep HS-811 334
- ebe, 2012, Development of distracted driving database, Proc 3rd Int Symp Naturalistic Driving Res, 1
- leblanc, 2006, Road departure crash warning system field operational test: Methodology and results, Tech Rep UMTRI-2006-9-1
- brach, 2012, Shrp 2 naturalistic driving study what we have learned so far, Proc 3rd Int Symp Naturalistic Driving Res, 1
Cited by
A Survey of Autonomous Driving: Common Practices and Emerging Technologies
Yurtsever, E., Lambert, J., Carballo, A., & Takeda, K. (2020) · IEEE Access · doi:10.1109/access.2020.2983149 · Cited by 1,889
“In [229]–[231] driving style was categorized into three and into two in [74], [209], [217], [218], [222].”
BackgroundMethodSelf-citationScene-Graph Augmented Data-Driven Risk Assessment of Autonomous Vehicle Decisions
Yu, S.-Y., Malawade, A. V., Muthirayan, D. R. P., Khargonekar, P. P., & Faruque, M. A. A. (2021) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2021.3074854 · Cited by 147
Reversible Data Hiding By Using CNN Prediction and Adaptive Embedding
Hu, R., & Xiang, S. (2021) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2021.3131250 · Cited by 103
“in computer vision [12], natural language processing [13], recommendation systems [14], image super-resolution [15], autopilot [16], target detection [17], information hiding [18], [19], [20], etc.”
BackgroundAhmed, M. M., Khan, M. N., Das, A., & Dadvar, S. (2022) · Accident Analysis & Prevention · doi:10.1016/j.aap.2022.106568 · Cited by 54
Al-Hussein, W. A., Por, L. Y., Kiah, M. L. M., & Zaidan, B. B. (2022) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph19031470 · Cited by 58
“Finally, researchers in [43] aimed to detect risky lane-changes during maneuvers.”
Background
Metadata
- Authors
- Yurtsever, E., Yamazaki, S., Miyajima, C., Takeda, K., Mori, M., Hitomi, K., & Egawa, M.
- Affiliations
- Nagoya University (JP)
- Denso (Japan) (JP)
- Venue
- IEEE Transactions on Intelligent Vehicles
- Published
- 2018-09
- Volume
- 3
- Issue
- 3
- Pages
- 242-253
- ISSN
- 2379-8858 (ISSN-L)
- 2379-8904
- OpenAlex
- W2806943411
- Cited by
- 30
- References
- 47
- Citations by year
- 2025: 1 · 2024: 2 · 2023: 7 · 2022: 6 · 2021: 5 · 2020: 5 · 2019: 4
- FWCI
- 4.24
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- IEEE Transactions on Intelligent Vehicles (publishedVersion)
- Funders
- DENSO
- Ritsumeikan University
- Topics
- Physical Sciences › Engineering › Safety, Risk, Reliability and Quality › Traffic and Road Safety
- Physical Sciences › Engineering › Automotive Engineering › Autonomous Vehicle Technology and Safety
- Social Sciences › Human Factors and Ergonomics › Human-Automation Interaction and Safety
- Keywords
- driver behavior, data reduction, naturalistic driving study, latent Dirichlet allocation
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.