Matches in SemOpenAlex for { <https://semopenalex.org/work/W4287079282> ?p ?o ?g. }
Showing items 1 to 78 of
78
with 100 items per page.
- W4287079282 abstract "Geo-localizing static objects from street images is challenging but also very important for road asset mapping and autonomous driving. In this paper we present a two-stage framework that detects and geolocalizes traffic signs from low frame rate street videos. Our proposed system uses a modified version of RetinaNet (GPS-RetinaNet), which predicts a positional offset for each sign relative to the camera, in addition to performing the standard classification and bounding box regression. Candidate sign detections from GPS-RetinaNet are condensed into geolocalized signs by our custom tracker, which consists of a learned metric network and a variant of the Hungarian Algorithm. Our metric network estimates the similarity between pairs of detections, then the Hungarian Algorithm matches detections across images using the similarity scores provided by the metric network. Our models were trained using an updated version of the ARTS dataset, which contains 25,544 images and 47.589 sign annotations ~cite{arts}. The proposed dataset covers a diverse set of environments gathered from a broad selection of roads. Each annotaiton contains a sign class label, its geospatial location, an assembly label, a side of road indicator, and unique identifiers that aid in the evaluation. This dataset will support future progress in the field, and the proposed system demonstrates how to take advantage of some of the unique characteristics of a realistic geolocalization dataset." @default.
- W4287079282 created "2022-07-25" @default.
- W4287079282 creator A5001816279 @default.
- W4287079282 creator A5015816708 @default.
- W4287079282 creator A5021345648 @default.
- W4287079282 creator A5035882521 @default.
- W4287079282 creator A5040792965 @default.
- W4287079282 creator A5070775744 @default.
- W4287079282 date "2021-07-13" @default.
- W4287079282 modified "2023-10-16" @default.
- W4287079282 title "Object Tracking and Geo-localization from Street Images" @default.
- W4287079282 doi "https://doi.org/10.48550/arxiv.2107.06257" @default.
- W4287079282 hasPublicationYear "2021" @default.
- W4287079282 type Work @default.
- W4287079282 citedByCount "0" @default.
- W4287079282 crossrefType "posted-content" @default.
- W4287079282 hasAuthorship W4287079282A5001816279 @default.
- W4287079282 hasAuthorship W4287079282A5015816708 @default.
- W4287079282 hasAuthorship W4287079282A5021345648 @default.
- W4287079282 hasAuthorship W4287079282A5035882521 @default.
- W4287079282 hasAuthorship W4287079282A5040792965 @default.
- W4287079282 hasAuthorship W4287079282A5070775744 @default.
- W4287079282 hasBestOaLocation W42870792821 @default.
- W4287079282 hasConcept C115961682 @default.
- W4287079282 hasConcept C124101348 @default.
- W4287079282 hasConcept C127413603 @default.
- W4287079282 hasConcept C134306372 @default.
- W4287079282 hasConcept C139676723 @default.
- W4287079282 hasConcept C147037132 @default.
- W4287079282 hasConcept C154504017 @default.
- W4287079282 hasConcept C154945302 @default.
- W4287079282 hasConcept C175291020 @default.
- W4287079282 hasConcept C176217482 @default.
- W4287079282 hasConcept C199360897 @default.
- W4287079282 hasConcept C21547014 @default.
- W4287079282 hasConcept C2983860417 @default.
- W4287079282 hasConcept C31972630 @default.
- W4287079282 hasConcept C33923547 @default.
- W4287079282 hasConcept C41008148 @default.
- W4287079282 hasConcept C60229501 @default.
- W4287079282 hasConcept C63584917 @default.
- W4287079282 hasConcept C76155785 @default.
- W4287079282 hasConceptScore W4287079282C115961682 @default.
- W4287079282 hasConceptScore W4287079282C124101348 @default.
- W4287079282 hasConceptScore W4287079282C127413603 @default.
- W4287079282 hasConceptScore W4287079282C134306372 @default.
- W4287079282 hasConceptScore W4287079282C139676723 @default.
- W4287079282 hasConceptScore W4287079282C147037132 @default.
- W4287079282 hasConceptScore W4287079282C154504017 @default.
- W4287079282 hasConceptScore W4287079282C154945302 @default.
- W4287079282 hasConceptScore W4287079282C175291020 @default.
- W4287079282 hasConceptScore W4287079282C176217482 @default.
- W4287079282 hasConceptScore W4287079282C199360897 @default.
- W4287079282 hasConceptScore W4287079282C21547014 @default.
- W4287079282 hasConceptScore W4287079282C2983860417 @default.
- W4287079282 hasConceptScore W4287079282C31972630 @default.
- W4287079282 hasConceptScore W4287079282C33923547 @default.
- W4287079282 hasConceptScore W4287079282C41008148 @default.
- W4287079282 hasConceptScore W4287079282C60229501 @default.
- W4287079282 hasConceptScore W4287079282C63584917 @default.
- W4287079282 hasConceptScore W4287079282C76155785 @default.
- W4287079282 hasLocation W42870792821 @default.
- W4287079282 hasLocation W42870792822 @default.
- W4287079282 hasOpenAccess W4287079282 @default.
- W4287079282 hasPrimaryLocation W42870792821 @default.
- W4287079282 hasRelatedWork W1564558219 @default.
- W4287079282 hasRelatedWork W2369744843 @default.
- W4287079282 hasRelatedWork W2489489317 @default.
- W4287079282 hasRelatedWork W2540960825 @default.
- W4287079282 hasRelatedWork W2766547489 @default.
- W4287079282 hasRelatedWork W2897576080 @default.
- W4287079282 hasRelatedWork W2999938717 @default.
- W4287079282 hasRelatedWork W3015973434 @default.
- W4287079282 hasRelatedWork W3175877121 @default.
- W4287079282 hasRelatedWork W3211653591 @default.
- W4287079282 isParatext "false" @default.
- W4287079282 isRetracted "false" @default.
- W4287079282 workType "article" @default.