A comparison of methods for detecting atypical trajectories

Saul, Hagen; Kozempel, Karsten; Haberjahn, Mathias

doi:10.2495/ut140331

Cited by 4 publications

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After training the trajectories were clustered taking into account their driving relation (entry and exit-lane). A score for measuring "atypicality" of a probe trajectory is computed by summing and normalizing the PDM-probabilities encountered at each trajectory position (refer to Saul et al [17] for more details).…”

Section: Atypical Traffic Situationsmentioning

confidence: 99%

Wide-area based traffic situation detection at an ungated level crossing

Junghans¹,

Leich²,

Kozempel³

et al. 2016

Int. J. SAFE

Self Cite

View full text Add to dashboard Cite

The automated detection of atypical and critical traffic situations is essentially important to help to understand driver behaviour, to find functional correlations between traffic conflicts and real accidents, and eventually, to prevent, particularly severe accidents. In this paper, a tool chain is introduced that enables fully automated traffic situation detection in wide-area traffic on the basis of a single camera. The tool chain takes into account novel powerful methods for object detection, classification and tracking on the basis of robust regression with preconditioning. Moreover, the tool chain considers methods for traffic situation detection and classification on the basis of probabilistic approaches and eventually, traffic event recording. The approach was tested at an ungated level crossing in the small town Bienrode, which is a district of Brunswick, Germany. It is shown that atypical situations, e.g. overtaking, braking, stopping, inadequate speeds, and accelerations, as well as critical situations, e.g. tailgating, can be detected within a range of up to 120 m distance of the camera automatically. The approach enables new ways of analysing traffic areas with regard to traffic safety and performance. The results shown in this paper were obtained in the project OptiSiLK, whose abbreviation means "Optimisation of the safety and the performance at intersections of different traffic modes". OptiSiLK was funded by the Ministry for Science and Culture of the State of Lower Saxony (MWK).

show abstract

Section: Atypical Traffic Situationsmentioning

confidence: 99%

Wide-area based traffic situation detection at an ungated level crossing

Junghans¹,

Leich²,

Kozempel³

et al. 2016

Int. J. SAFE

Self Cite

View full text Add to dashboard Cite

show abstract

“…Schreck et al [37] developed a framework to classify trajectories using SOMs, scaling the paths into unit square values and sampling them in a predefined number of parts. Saul et al [35] compared map-based trajectory analysis with SOM to detect unusual behaviour of traffic objects, where the network achieves better results in abrupt avoidance detection. Andrew et al [22] explore the use of a SOM to visualize patterns of urban social change.…”

Section: Case Of Study: Individual Human Behaviour Analysismentioning

confidence: 99%

Constrained self-organizing feature map to preserve feature extraction topology

Azorín-López

Saval-Calvo

Fuster-Guilló

et al. 2016

Neural Comput & Applic

View full text Add to dashboard Cite

In many classification problems, it is necessary to consider the specific location of an n-dimensional space from which features have been calculated. For example, considering the location of features extracted from specific areas of a two-dimensional space, as an image, could improve the understanding of a scene for a video surveillance system. In the same way, the same features extracted from different locations could mean different actions for a 3D HCI system. In this paper, we present a self-organizing feature map able to preserve the topology of locations of an n-dimensional space in which the vector of features have been extracted. The main contribution is to implicitly preserving the topology of the original space because considering the locations of the extracted features and their topology could ease the solution to certain problems. Specifically, the paper proposes the n-Dimensional constrained SelfOrganizing Map Preserving the Input Topology (nD-SOM-PINT). Features in adjacent areas of the n-dimensional space, used to extract the feature vectors, are explicitly in adjacent areas of the nD-SOM-PINT constraining the neural network structure and learning. As a study case, the neural network has been instantiate to represent and classify features as trajectories extracted from a sequence of images into a high level of semantic understanding. Experiments have been thoroughly carried out using the CAVIAR datasets (Corridor, Frontal and Inria) taken into account the global behaviour of an individual in order to validate the ability to preserve the topology of the two-dimensional space to obtain high performance classification for trajectory classification in contrast of non-considering the location of features. Moreover, a brief example

show abstract

“…accidents and near-misses Saul et al, 2014) ). Furthermore, the development and test of wireless communication technologies for journey time measurements (like Wi-Fi, TPMS and Bluetooth sni ers) can be and has been be performed at the UTRaLab ( Savić et al, 2014)).…”

Section: Project Application Examplesmentioning

confidence: 99%

UTRaLab – Urban Traffic Research Laboratory

Kozempel

Luber

Junghans

2017

JLSRF

View full text Add to dashboard Cite

The Urban Tra c Research Laboratory (UTRaLab) is a research and test track for tra c detection methods and sensors. It is located at the Ernst-Ruska-Ufer, in the southeast of the city of Berlin (Germany). The UTRaLab covers 1 km of a highly-frequented urban road and is connected to a motorway. It is equipped with two gantries with distance of 850 m in between and has several outstations for data collection. The gantries contain many di erent tra c sensors like inductive loops, cameras, lasers or wireless sensors for tra c data acquisition. Additionally a weather station records environmental data. The UTRaLab's main purposes are the data collection of tra c data on the one hand and testing newly developed sensors on the other hand.

show abstract

A comparison of methods for detecting atypical trajectories

Cited by 4 publications

References 20 publications

Wide-area based traffic situation detection at an ungated level crossing

Wide-area based traffic situation detection at an ungated level crossing

Constrained self-organizing feature map to preserve feature extraction topology

UTRaLab – Urban Traffic Research Laboratory

Contact Info

Product

Resources

About