485 Hits in 4.0 sec

Cyclist Intention Detection: A Probabilistic Approach [article]

Stefan Zernetsch, Hannes Reichert, Viktor Kress, Konrad Doll, Bernhard Sick
2021 arXiv   pre-print
This article presents a holistic approach for probabilistic cyclist intention detection.  ...  A basic movement detection based on motion history images (MHI) and a residual convolutional neural network (ResNet) are used to estimate probabilities for the current cyclist motion state.  ...  CONCLUSIONS AND FUTURE WORK In this article, we presented a new approach to perform probabilistic cyclist intention detection.  ... 
arXiv:2104.09176v1 fatcat:5ifvjnvnwnf6tlqaiwrmtuukrq

Pedestrian and Cyclist Detection and Intent Estimation for Autonomous Vehicles: A Survey

Sarfraz Ahmed, M. Nazmul Huda, Sujan Rajbhandari, Chitta Saha, Mark Elshaw, Stratis Kanarachos
2019 Applied Sciences  
Although there has been a growth in research surrounding the study of pedestrian detection using vision-based approaches, further attention should include focus on cyclist detection.  ...  This paper presents a review of recent developments in pedestrian and cyclist detection and intent estimation to increase the safety of autonomous vehicles, for both the driver and other road users.  ...  Deep Learning Architectures for Pedestrian and Cyclist Detection DL approaches for pedestrian and cyclist detection can be one of the following two categories: a two stages (region proposal approach) detector  ... 
doi:10.3390/app9112335 fatcat:55zsz77zcjblpg2lmutnubfpdm

Detecting Intentions of Vulnerable Road Users Based on Collective Intelligence [article]

Maarten Bieshaar, Günther Reitberger, Stefan Zernetsch, Bernhard Sick, Erich Fuchs, Konrad Doll
2018 arXiv   pre-print
In this article a holistic approach for detecting intentions of VRUs by cooperative methods is presented.  ...  To avoid accidents and achieve a highly efficient traffic flow, it is important to detect VRUs and to predict their intentions.  ...  A related collaborative VRU intention detection approach, which makes use of organic-and soft computing techniques, is presented in [21] .  ... 
arXiv:1809.03916v1 fatcat:gtc4v42cdbgyfjc4ddwgqriiie

Cooperative intention detection using machine learning. Advanced cyclist protection in the context of automated driving

Maarten Bieshaar, Universität Kassel
In this thesis, a holistic approach for detecting the intentions of cyclists using cooperative methods is presented.  ...  Cyclists will play an essential role in future traffic. It is crucial to detect cyclists and predict their intentions to avoid accidents and achieve a highly efficient traffic flow.  ...  Cooperative Cyclist Intention Detection using Probabilistic Trajectory Fusion In this section, we describe the approach to cooperative cyclist intention detection using probabilistic trajectory fusing.  ... 
doi:10.17170/kobra-202101263056 fatcat:ap3wdd24ivalhfzg24bnmvrf5e

Starting Movement Detection of Cyclists Using Smart Devices [article]

Maarten Bieshaar, Malte Depping, Jan Schneegans, Bernhard Sick
2018 arXiv   pre-print
This article presents a human activity recognition approach to detect the starting movement of cyclists wearing smart devices.  ...  Smart devices can be used to detect intentions, e.g., an occluded cyclist intending to cross the road, to warn vehicles of VRUs, and prevent potential collisions.  ...  A smart device worn by the cyclist can anticipate the starting movement and communicate the detected intention to the approaching vehicle to warn the driver or initiate a braking maneuver.  ... 
arXiv:1808.04449v1 fatcat:mhzdncmra5dwzeqvm5epmxsntm

Cooperative Starting Movement Detection of Cyclists Using Convolutional Neural Networks and a Boosted Stacking Ensemble [article]

Maarten Bieshaar and Stefan Zernetsch and Andreas Hubert and Bernhard Sick and Konrad Doll
2018 arXiv   pre-print
In this article we present a cooperative approach for starting movement detection of cyclists using a boosted stacking ensemble approach realizing feature- and decision level cooperation.  ...  The CNN is complemented by a smart device based starting movement detection originating from smart devices carried by the cyclist.  ...  For a more robust and yet fast starting intention detection we propose a cooperative approach.  ... 
arXiv:1803.03487v1 fatcat:bz5lco2mi5hfbasxw4xijcwe3a

Intentions of Vulnerable Road Users - Detection and Forecasting by Means of Machine Learning [article]

Michael Goldhammer, Sebastian Köhler, Stefan Zernetsch, Konrad Doll, Bernhard Sick, Klaus Dietmayer
2018 arXiv   pre-print
As especially pedestrians and cyclists are very agile and have a variety of movement options, modeling their behavior in traffic scenes is a challenging task.  ...  Both model types are also combined to enable the application of specifically trained motion predictors based on a continuously updated pseudo probabilistic state classification.  ...  With this approach, the trained classifier provides a pseudo-probabilistic rating for each state.  ... 
arXiv:1803.03577v1 fatcat:zbzs3othwfamzkadsnfm7mvc2m

Motion detection and classification: ultra-fast road user detection

Risto Ojala, Jari Vepsäläinen, Kari Tammi
2022 Journal of Big Data  
Similar problems are faced in many intelligent transportation applications, in which road users are detected with a roadside camera.  ...  The approach is computationally lightweight and capable of running in real-time on an inexpensive single-board computer.  ...  A motion detection-based multiclass detector for traffic environments has been proposed by Zhang et al. [45] , who detected pedestrians, cyclists and cars from a traffic camera view.  ... 
doi:10.1186/s40537-022-00581-8 fatcat:lomdylj6tvdwtj7wxll6kzpqsq

A Review and Comparative Study on Probabilistic Object Detection in Autonomous Driving [article]

Di Feng, Ali Harakeh, Steven Waslander, Klaus Dietmayer
2020 arXiv   pre-print
In recent years, deep learning has become the de-facto approach for object detection, and many probabilistic object detectors have been proposed.  ...  Next, we present a strict comparative study for probabilistic object detection based on an image detector and three public autonomous driving datasets.  ...  The LiDAR-based networks often deal with 3D detection for single object class or a few object classes, such as "Car", "Cyclist" and "Pedestrian".  ... 
arXiv:2011.10671v1 fatcat:a7exswrvjfczpln7xojouzklby

Towards Multi-Object Detection and Tracking in Urban Scenario under Uncertainties

Achim Kampker, Mohsen Sefati, Arya S. Abdul Rachman, Kai Kreisköther, Pascual Campoy
2018 Proceedings of the 4th International Conference on Vehicle Technology and Intelligent Transport Systems  
Our approach combines sensor occlusion-aware detection method with computationally efficient heuristics rule-based filtering and adaptive probabilistic tracking to handle uncertainties arising from sensing  ...  We present a real-time integrated framework of multi-target object detection and tracking using 3D LIDAR geared toward urban use.  ...  approach to enhance detection and tracking result while simultaneously doing classification.  ... 
doi:10.5220/0006706101560167 dblp:conf/vehits/KampkerSRKC18 fatcat:qg6jkobg2vgq3kfruwuwosfpju

Analysis of the Relationship between Turning Signal Detection and Motorcycle Driver's Characteristics on Urban Roads; A Case Study

Micucci, Mantecchini, Sangermano
2019 Sensors  
indicators aspect and some of the variables considered (e.g., age, being habitual cyclist or car driver and the presence of a car occluding the views), suggesting the opportunity to further investigate  ...  vehicles and if the motorcyclist are also habitual car or bicycle drivers) in a stepwise logistic regression that modelled the odds of detecting the turn signal turned on as a function of significant  ...  Impact of Being Habitual Cyclist on Turning Signal Detection  ... 
doi:10.3390/s19081802 fatcat:yvsnzhypljhjdl5ea7przgngey

Early detection of the Pedestrian's intention to cross the street

Sebastian Kohler, Michael Goldhammer, Sebastian Bauer, Konrad Doll, Ulrich Brunsmann, Klaus Dietmayer
2012 2012 15th International IEEE Conference on Intelligent Transportation Systems  
While MCHOG in special cases indicates detection of the intention before the whole body moves, on average it allows for detection of the movement within 6 frames at a frame rate of 50 Hz and an accuracy  ...  This paper focuses on monocular-video-based stationary detection of the pedestrian's intention to enter the traffic lane.  ...  recognizes a vehicle approaching.  ... 
doi:10.1109/itsc.2012.6338797 dblp:conf/itsc/0001GBDBD12 fatcat:t3etuyy2bfc3hbayhlaq2s6xze

PAIDS: toward pedestrian high-precision position and attribute information detection

Shunya Yamada, Hiroaki Takada, Yousuke Watanabe, Saya Kitamura, Zhengshu Zhou
2021 International Journal of Mechatronics and Automation  
In this paper, the authors propose a pedestrian position and attribute information detecting system to extract both pedestrian high-precision position and attribute information in real-time based on LiDAR  ...  Pedestrian detection sensors in road infrastructure and smartphone's built-in sensors have been used to detect and track pedestrians for road safety.  ...  Zhao et al. (2019) presented a modified naive Bayes approach to conduct probabilistic prediction of pedestrian crossing intention using roadside LiDAR data.  ... 
doi:10.1504/ijma.2021.10043870 fatcat:um3swugfefcwpgsgjmcqpkuyfe

3D Object Detection for Autonomous Driving: A Survey [article]

Rui Qian, Xin Lai, Xirong Li
2022 arXiv   pre-print
Despite existing efforts, 3D object detection for autonomous driving is still in its infancy. Recently, a large body of literature have been investigated to address this 3D vision task.  ...  We therefore aim to fill this gap in a comprehensive survey, encompassing all the main concerns including sensors, datasets, performance metrics and the recent state-of-the-art detection methods, together  ...  Usually two leaderboard is considered, i.e. 3D detection and Bird's Eye View (BEV) detection. 3D detection evaluates 3 | 11 with a rotated 3 threshold of 0.7, 0.5, 0.5 for Car, Pedestrian and Cyclist  ... 
arXiv:2106.10823v2 fatcat:z2lytpximjeyzmnrtlltklvk5a

Automatic Event Detection for Signal-based Surveillance [article]

Jingxin Xu, Clinton Fookes, Sridha Sridharan
2016 arXiv   pre-print
This article provides an overview of automatic surveillance event detection techniques .  ...  Despite it's popularity in research, it is still too challenging a problem to be realised in a real world deployment.  ...  group with a level of variation which reflects the person's own destination, and the intention of keeping a comfortable distance from each other.  ... 
arXiv:1612.01611v1 fatcat:bv57e3k2qbaxle3hy2pdehovxq
« Previous Showing results 1 — 15 out of 485 results