Matches in SemOpenAlex for { <https://semopenalex.org/work/W2792490509> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W2792490509 abstract "Many multi-object tracking methods have been developed to solve the computer vision problem which has been attracting significant attentions. In this paper, a novel convolutional neural networks with frame-pair input method for multi-object tracking is presented. It is found that our object tracking methods trained using two successive frames tend to predict the centers of searching windows as the locations of tracked targets. CNN features and color histogram features are extracted as appearance features to measure similarities between objects which used for Tracklets. Kalman Filter and Hungarian algorithm are used to create tracklets association which indicates the location of tracked targets. Specifically, we construct a novel sampling strategy for off-line training. Experiments on the popular challenging datasets show that the proposed tracking system performs on par with recently developed generic multi-object tracking methods, but with much less memory. In addition, our tracking system can run in a speed of over 80 (30) fps with a GPU (CPU), much faster than most deep neural networks based trackers. We found that simply improving detection performance can lead to much better multiple object tracking results." @default.
- W2792490509 created "2018-03-29" @default.
- W2792490509 creator A5046520540 @default.
- W2792490509 creator A5052276737 @default.
- W2792490509 creator A5059755489 @default.
- W2792490509 creator A5086314842 @default.
- W2792490509 date "2017-12-01" @default.
- W2792490509 modified "2023-09-23" @default.
- W2792490509 title "Fast multi-object tracking using convolutional neural networks with tracklets updating" @default.
- W2792490509 cites W2117539524 @default.
- W2792490509 cites W2126302311 @default.
- W2792490509 cites W2244956674 @default.
- W2792490509 cites W2400262625 @default.
- W2792490509 cites W2509359898 @default.
- W2792490509 cites W2586957942 @default.
- W2792490509 cites W2625728734 @default.
- W2792490509 cites W343636949 @default.
- W2792490509 doi "https://doi.org/10.1109/spac.2017.8304296" @default.
- W2792490509 hasPublicationYear "2017" @default.
- W2792490509 type Work @default.
- W2792490509 sameAs 2792490509 @default.
- W2792490509 citedByCount "3" @default.
- W2792490509 countsByYear W27924905092019 @default.
- W2792490509 countsByYear W27924905092020 @default.
- W2792490509 countsByYear W27924905092021 @default.
- W2792490509 crossrefType "proceedings-article" @default.
- W2792490509 hasAuthorship W2792490509A5046520540 @default.
- W2792490509 hasAuthorship W2792490509A5052276737 @default.
- W2792490509 hasAuthorship W2792490509A5059755489 @default.
- W2792490509 hasAuthorship W2792490509A5086314842 @default.
- W2792490509 hasConcept C153180895 @default.
- W2792490509 hasConcept C154945302 @default.
- W2792490509 hasConcept C15744967 @default.
- W2792490509 hasConcept C19417346 @default.
- W2792490509 hasConcept C202474056 @default.
- W2792490509 hasConcept C2775936607 @default.
- W2792490509 hasConcept C2781238097 @default.
- W2792490509 hasConcept C31972630 @default.
- W2792490509 hasConcept C41008148 @default.
- W2792490509 hasConcept C81363708 @default.
- W2792490509 hasConceptScore W2792490509C153180895 @default.
- W2792490509 hasConceptScore W2792490509C154945302 @default.
- W2792490509 hasConceptScore W2792490509C15744967 @default.
- W2792490509 hasConceptScore W2792490509C19417346 @default.
- W2792490509 hasConceptScore W2792490509C202474056 @default.
- W2792490509 hasConceptScore W2792490509C2775936607 @default.
- W2792490509 hasConceptScore W2792490509C2781238097 @default.
- W2792490509 hasConceptScore W2792490509C31972630 @default.
- W2792490509 hasConceptScore W2792490509C41008148 @default.
- W2792490509 hasConceptScore W2792490509C81363708 @default.
- W2792490509 hasLocation W27924905091 @default.
- W2792490509 hasOpenAccess W2792490509 @default.
- W2792490509 hasPrimaryLocation W27924905091 @default.
- W2792490509 hasRelatedWork W2040965325 @default.
- W2792490509 hasRelatedWork W2352586926 @default.
- W2792490509 hasRelatedWork W2385949326 @default.
- W2792490509 hasRelatedWork W2422898642 @default.
- W2792490509 hasRelatedWork W2510317309 @default.
- W2792490509 hasRelatedWork W2534746541 @default.
- W2792490509 hasRelatedWork W2789220062 @default.
- W2792490509 hasRelatedWork W2820058250 @default.
- W2792490509 hasRelatedWork W4307010368 @default.
- W2792490509 hasRelatedWork W2185534064 @default.
- W2792490509 isParatext "false" @default.
- W2792490509 isRetracted "false" @default.
- W2792490509 magId "2792490509" @default.
- W2792490509 workType "article" @default.