Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387006095> ?p ?o ?g. }
Showing items 1 to 96 of
96
with 100 items per page.
- W4387006095 abstract "Accurately assessing the speed of vehicles is important for traffic management systems. This is especially the case for heavy goods vehicles such as lorries/trucks, since they cannot easily stop at short notice. Previous work has shown that deep learning can be used for identifying and distinguishing trucks on the road from other vehicles, e.g., [1], however accurately estimating their speed from roadside cameras remains a challenge. One solution we employ is using video data from the roadside cameras, then extracting the speeds of vehicles in the video from the Infra-Red Traffic Logger (TIRTL) systems, which are provided by the Department of Transport, Victoria. The TIRTL system is very accurate but expensive and only deployed at a few key locations around Melbourne. A solution that works at the edge and uses lightweight Internet-of-Things devices to produce accurate speed data is thus highly desirable. In this paper, we propose a Convolutional Neural Network (CNN) model using a light-weight Siamese backbone and associated feature correlations to track and detect the speed of trucks. We build a dataset that contains images with speed and bounding-box annotations to train the proposed model. To enable the model to maintain a high degree of accuracy with different camera setups, we train and test the proposed model using image augmentation. The results show our model has an average speed estimation error of 4.92% and an average Intersection over Union (IoU) of 75.8% whilst incorporating different intrinsic and extrinsic parameters based on image augmentation. Such a capability has the potential to change the way services are deployed across the road network to record vehicle types and speeds." @default.
- W4387006095 created "2023-09-26" @default.
- W4387006095 creator A5006916283 @default.
- W4387006095 creator A5039872140 @default.
- W4387006095 creator A5084653483 @default.
- W4387006095 date "2023-10-09" @default.
- W4387006095 modified "2023-09-26" @default.
- W4387006095 title "Truck Speed Detection Through Video Streams" @default.
- W4387006095 cites W2049833148 @default.
- W4387006095 cites W2056341306 @default.
- W4387006095 cites W2064106408 @default.
- W4387006095 cites W2074671199 @default.
- W4387006095 cites W2093273191 @default.
- W4387006095 cites W2099051099 @default.
- W4387006095 cites W2112218350 @default.
- W4387006095 cites W2118238901 @default.
- W4387006095 cites W2127932676 @default.
- W4387006095 cites W2138792236 @default.
- W4387006095 cites W2155880278 @default.
- W4387006095 cites W2168038911 @default.
- W4387006095 cites W2252355370 @default.
- W4387006095 cites W2524986418 @default.
- W4387006095 cites W2560474170 @default.
- W4387006095 cites W2570343428 @default.
- W4387006095 cites W2590234360 @default.
- W4387006095 cites W2740444003 @default.
- W4387006095 cites W2810637760 @default.
- W4387006095 cites W2900327972 @default.
- W4387006095 cites W2936789839 @default.
- W4387006095 cites W2963534981 @default.
- W4387006095 cites W3013653931 @default.
- W4387006095 cites W3035571898 @default.
- W4387006095 cites W3047316113 @default.
- W4387006095 cites W3091603525 @default.
- W4387006095 cites W3099319035 @default.
- W4387006095 cites W3208253328 @default.
- W4387006095 cites W764651262 @default.
- W4387006095 doi "https://doi.org/10.1109/e-science58273.2023.10254943" @default.
- W4387006095 hasPublicationYear "2023" @default.
- W4387006095 type Work @default.
- W4387006095 citedByCount "0" @default.
- W4387006095 crossrefType "proceedings-article" @default.
- W4387006095 hasAuthorship W4387006095A5006916283 @default.
- W4387006095 hasAuthorship W4387006095A5039872140 @default.
- W4387006095 hasAuthorship W4387006095A5084653483 @default.
- W4387006095 hasConcept C108583219 @default.
- W4387006095 hasConcept C115961682 @default.
- W4387006095 hasConcept C127413603 @default.
- W4387006095 hasConcept C138885662 @default.
- W4387006095 hasConcept C147037132 @default.
- W4387006095 hasConcept C154945302 @default.
- W4387006095 hasConcept C162307627 @default.
- W4387006095 hasConcept C171146098 @default.
- W4387006095 hasConcept C22212356 @default.
- W4387006095 hasConcept C2776401178 @default.
- W4387006095 hasConcept C31972630 @default.
- W4387006095 hasConcept C41008148 @default.
- W4387006095 hasConcept C41895202 @default.
- W4387006095 hasConcept C52121051 @default.
- W4387006095 hasConcept C64543145 @default.
- W4387006095 hasConcept C79403827 @default.
- W4387006095 hasConcept C81363708 @default.
- W4387006095 hasConceptScore W4387006095C108583219 @default.
- W4387006095 hasConceptScore W4387006095C115961682 @default.
- W4387006095 hasConceptScore W4387006095C127413603 @default.
- W4387006095 hasConceptScore W4387006095C138885662 @default.
- W4387006095 hasConceptScore W4387006095C147037132 @default.
- W4387006095 hasConceptScore W4387006095C154945302 @default.
- W4387006095 hasConceptScore W4387006095C162307627 @default.
- W4387006095 hasConceptScore W4387006095C171146098 @default.
- W4387006095 hasConceptScore W4387006095C22212356 @default.
- W4387006095 hasConceptScore W4387006095C2776401178 @default.
- W4387006095 hasConceptScore W4387006095C31972630 @default.
- W4387006095 hasConceptScore W4387006095C41008148 @default.
- W4387006095 hasConceptScore W4387006095C41895202 @default.
- W4387006095 hasConceptScore W4387006095C52121051 @default.
- W4387006095 hasConceptScore W4387006095C64543145 @default.
- W4387006095 hasConceptScore W4387006095C79403827 @default.
- W4387006095 hasConceptScore W4387006095C81363708 @default.
- W4387006095 hasFunder F4320320974 @default.
- W4387006095 hasLocation W43870060951 @default.
- W4387006095 hasOpenAccess W4387006095 @default.
- W4387006095 hasPrimaryLocation W43870060951 @default.
- W4387006095 hasRelatedWork W2731899572 @default.
- W4387006095 hasRelatedWork W2999805992 @default.
- W4387006095 hasRelatedWork W3011074480 @default.
- W4387006095 hasRelatedWork W3116150086 @default.
- W4387006095 hasRelatedWork W3133861977 @default.
- W4387006095 hasRelatedWork W3192840557 @default.
- W4387006095 hasRelatedWork W4200173597 @default.
- W4387006095 hasRelatedWork W4291897433 @default.
- W4387006095 hasRelatedWork W4312417841 @default.
- W4387006095 hasRelatedWork W4321369474 @default.
- W4387006095 isParatext "false" @default.
- W4387006095 isRetracted "false" @default.
- W4387006095 workType "article" @default.