Effects of feature selection on lane-change maneuver recognition: an analysis of naturalistic driving data

Li, Xiaohan; Wang, Wenshuo; Zhang, Zhang; Rötting, Matthias

doi:10.1108/jicv-09-2018-0010

Cited by 7 publications

(3 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, it is important to note that not all features contribute equally to the recognition of LC risks. In fact, some redundant features may introduce noise and diminish the accuracy of the model [47]. Additionally, incorporating too many features may result in an excessive increase in the dimensionality of the LC risk feature dataset, potentially leading to overfitting.…”

Section: Lc Features Importance Ranking Based On Lightgbmmentioning

confidence: 99%

A Comprehensive Investigation of Lane-Changing Risk Recognition Framework of Multi-Vehicle Type Considering Key Features Based on Vehicles’ Trajectory Data

Zheng,

Liu

2024

Electronics

View full text Add to dashboard Cite

To comprehensively investigate the key features of lane-changing (LC) risk for different vehicle types during left and right LC, and to improve the accuracy of LC risk recognition, this paper proposes a key feature selection and risk recognition model based on vehicle trajectory data. Based on a HighD high-precision vehicle trajectory dataset, the trajectory data of LC vehicles and surrounding vehicles of each vehicle type are extracted. SDI (stop distance index) and CI (crash index) are selected as surrogate indicators to calculate the risk exposure level (REL) and risk severity level (RSL). The K-means algorithm is used to cluster the REL and RSL to obtain the LC risk level, which is divided into three levels. The combination of basic features and interaction features of LC vehicles and surrounding vehicles with LC risk levels is constructed as the LC risk feature dataset. Based on the LightGBM (light gradient boosting machine) algorithm, the importance of features is sorted. Finally, a CNN-BiLSTM-Attention model is established to recognize the LC risk of each vehicle type during left and right LC. The results indicate that significant differences exist among different vehicle types and LC directions. Compared with CNNs (convolutional neural networks), LSTM (long short-term memory), and BiLSTM (bi-directional long short-term memory), CNN-BiLSTM-Attention performs best in recognizing the risk of LC in all cases. Moreover, the key feature groups that have the optimal result of recognizing the risk of LC in different cases are obtained.

show abstract

Section: Lc Features Importance Ranking Based On Lightgbmmentioning

confidence: 99%

A Comprehensive Investigation of Lane-Changing Risk Recognition Framework of Multi-Vehicle Type Considering Key Features Based on Vehicles’ Trajectory Data

Zheng,

Liu

2024

Electronics

View full text Add to dashboard Cite

show abstract

“…Moreover, the binary-state occupancy cells attached to the ego vehicle were used to represent surrounding scenarios [7], [10]. Some works were trying to figure out the influence of feature selection on lane change behaviors in terms of behavior recognition and decision-making, thus offering cues of selecting and constructing efficient features [20], [21]. The features mentioned above and their combinations can be directly measured using sensors; however, the dimension of all these selected features is sensitive to the number of traffic agents in the environment.…”

Section: B Representation Learning For Multi-vehicle Interactionsmentioning

confidence: 99%

Spatiotemporal Learning of Multivehicle Interaction Patterns in Lane-Change Scenarios

Zhang,

Zhu,

Wang

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Interpretation of common-yet-challenging interaction scenarios can benefit well-founded decisions for autonomous vehicles. Previous research achieved this using their prior knowledge of specific scenarios with predefined models, which limits their adaptive capabilities. This paper describes a Bayesian nonparametric approach that leverages continuous (i.e., Gaussian processes) and discrete (i.e., Dirichlet processes) stochastic processes to reveal underlying interaction patterns of the ego vehicle with other nearby vehicles. Our model relaxes dependency on the number of surrounding vehicles by developing an accelerationsensitive velocity field based on Gaussian processes. The experiment results demonstrate that the velocity field can represent the spatial interactions between the ego vehicle and its surroundings. Then, a discrete Bayesian nonparametric model, integrating Dirichlet processes and hidden Markov models, is developed to learn the interaction patterns over the temporal space by segmenting and clustering the sequential interaction data into interpretable granular patterns automatically. We then evaluate our approach in the highway lane-change scenarios using the highD dataset, which was collected from real-world settings. Results demonstrate that our proposed Bayesian nonparametric approach provides an insight into the complicated lane-change interactions of the ego vehicle with multiple surrounding traffic participants based on the interpretable interaction patterns and their transition properties in temporal relationships. Our proposed approach sheds light on efficiently analyzing other kinds of multi-agent interactions, such as vehicle-pedestrian interactions.

show abstract

“…Deep CNN can directly learn feature representations with multiple levels of abstraction from raw images (LeCun et al, 2015). Accurate feature representations are important for object detection (Li et al, 2018).…”

Section: Introductionmentioning

confidence: 99%

Scale Variant Vehicle Object Recognition by CNN Module of Multi-Pooling-PCA Process

Guo,

Kumazawa,

Kaku

2023

J. Int. Con. Veh.

View full text Add to dashboard Cite

The moving vehicles present different scales in the image due to the perspective effect of different viewpoint distances. The premise of advanced driver assistance system (ADAS) system for safety surveillance and safe driving is early identification of vehicle targets in front of the ego vehicle. The recognition of the same vehicle at different scales requires feature learning with scale invariance. Unlike existing feature vector methods, the normalized PCA eigenvalues calculated from feature maps are used to extract scale-invariant features. This study proposed a convolutional neural network (CNN) structure embedded with the module of multi-pooling-PCA for scale variant object recognition. The validation of the proposed network structure is verified by scale variant vehicle image dataset. Compared with scale invariant network algorithms of Scale-invariant feature transform (SIFT) and FSAF as well as miscellaneous networks, the proposed network can achieve the best recognition accuracy tested by the vehicle scale variant dataset. To testify the practicality of this modified network, the testing of public dataset ImageNet is done and the comparable results proved its effectiveness in general purpose of applications.

show abstract

Effects of feature selection on lane-change maneuver recognition: an analysis of naturalistic driving data

Cited by 7 publications

References 36 publications

A Comprehensive Investigation of Lane-Changing Risk Recognition Framework of Multi-Vehicle Type Considering Key Features Based on Vehicles’ Trajectory Data

A Comprehensive Investigation of Lane-Changing Risk Recognition Framework of Multi-Vehicle Type Considering Key Features Based on Vehicles’ Trajectory Data

Spatiotemporal Learning of Multivehicle Interaction Patterns in Lane-Change Scenarios

Scale Variant Vehicle Object Recognition by CNN Module of Multi-Pooling-PCA Process

Contact Info

Product

Resources

About