Novel Convolutional Neural Network-Based Roadside Unit for Accurate Pedestrian Localisation

dc.contributorAalto-yliopistofi
dc.contributorAalto Universityen
dc.contributor.authorOjala, Risto
dc.contributor.authorVepsäläinen, Jari
dc.contributor.authorHanhirova, Jussi
dc.contributor.authorHirvisalo, Vesa
dc.contributor.authorTammi, Kari
dc.contributor.departmentDepartment of Mechanical Engineering
dc.contributor.departmentHeljanko Keijo group
dc.contributor.departmentDepartment of Computer Scienceen
dc.date.accessioned2020-01-17T13:32:32Z
dc.date.available2020-01-17T13:32:32Z
dc.date.issued2020-09
dc.description.abstractHazardous situations may easily be caused by limited visibility at urban traffic intersections due to buildings, fences, flora, and other obstacles. Thus, drivers approaching an intersection have limited reaction time when other obscured road users, such as pedestrians and cyclists, appear unexpectedly. Previous research has been conducted on applications warning drivers of approaching out-of-sight vehicles. However, less focus has been on the detection and awareness applications revealing the presence of pedestrians. We propose a novel system that displays the driver real-time locations and types of hidden road users at traffic intersections. A roadside unit is installed in the infrastructure which sends safety-critical object data to the vehicle, supporting the real-time decision-making of the driver. The roadside unit consists of a monovision camera streaming video to a computing unit which performs object detection and distance measurements on the detected objects. This paper validates the capability of the proposed system of localizing a pedestrian, and also examines its sensitivity to installation and detection errors. The results show that the accuracy of the proposed system is suitable for the intended application. However, an error in the vertical angle of the roadside unit camera caused an exponential error in the distance approximation in respect to the measured distance. The detection accuracy was noticed to decrease at long distances and in dark surroundings. Moreover, in order to reduce the effect of the presented errors, the camera should be installed as high as possible without hindering its detection capabilities.en
dc.description.versionPeer revieweden
dc.format.extent10
dc.format.mimetypeapplication/pdf
dc.identifier.citationOjala , R , Vepsäläinen , J , Hanhirova , J , Hirvisalo , V & Tammi , K 2020 , ' Novel Convolutional Neural Network-Based Roadside Unit for Accurate Pedestrian Localisation ' , IEEE Transactions on Intelligent Transportation Systems , vol. 21 , no. 9 , 8793228 , pp. 3756-3765 . https://doi.org/10.1109/TITS.2019.2932802en
dc.identifier.doi10.1109/TITS.2019.2932802
dc.identifier.issn1524-9050
dc.identifier.otherPURE UUID: d6392432-6fdd-4ea9-8163-1c94e59e6e6f
dc.identifier.otherPURE ITEMURL: https://research.aalto.fi/en/publications/d6392432-6fdd-4ea9-8163-1c94e59e6e6f
dc.identifier.otherPURE LINK: http://www.scopus.com/inward/record.url?scp=85090415924&partnerID=8YFLogxK
dc.identifier.otherPURE FILEURL: https://research.aalto.fi/files/40386068/ENG_Ojala_et_al_Novel_convolutional_neural_network_based_IEEE_Transactions_on_intelligent_transportation_systems.pdf
dc.identifier.urihttps://aaltodoc.aalto.fi/handle/123456789/42579
dc.identifier.urnURN:NBN:fi:aalto-202001171694
dc.language.isoenen
dc.publisherIEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
dc.relation.ispartofseriesIEEE Transactions on Intelligent Transportation Systemsen
dc.rightsopenAccessen
dc.subject.keywordcameras
dc.subject.keywordintelligent transportation systems
dc.subject.keywordmachine vision
dc.subject.keywordneural networks
dc.subject.keywordobject detection
dc.subject.keywordvehicle safety
dc.titleNovel Convolutional Neural Network-Based Roadside Unit for Accurate Pedestrian Localisationen
dc.typeA1 Alkuperäisartikkeli tieteellisessä aikakauslehdessäfi
dc.type.versionacceptedVersion
Files