Faster R-CNN Towards Real-Time Object Detection with Region Proposal Networks

Faster R-CNN : Towards Real-Time Object Detection with Region Proposal Networks

State-of-the-art object detection networks depend on region proposal algorithms to hypothesize object locations. Advances like SPPnet [1] and Fast R-CNN [2] have reduced the running time of these detection networks, exposing region proposal computation as a bottleneck. In this work, we introduce a R...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 39(2017), 6 vom: 01. Juni, Seite 1137-1149
1. Verfasser: Ren, Shaoqing (VerfasserIn)
Weitere Verfasser: He, Kaiming, Girshick, Ross, Sun, Jian
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2017
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article
LEADER 01000naa a22002652 4500
001 NLM261341588
003 DE-627
005 20231224195341.0
007 cr uuu---uuuuu
008 231224s2017 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2016.2577031  |2 doi 
028 5 2 |a pubmed24n0871.xml 
035 |a (DE-627)NLM261341588 
035 |a (NLM)27295650 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Ren, Shaoqing  |e verfasserin  |4 aut 
245 1 0 |a Faster R-CNN  |b Towards Real-Time Object Detection with Region Proposal Networks 
264 1 |c 2017 
336 |a Text  |b txt  |2 rdacontent 
337 |a ƒaComputermedien  |b c  |2 rdamedia 
338 |a ƒa Online-Ressource  |b cr  |2 rdacarrier 
500 |a Date Completed 25.10.2018 
500 |a Date Revised 09.04.2022 
500 |a published: Print-Electronic 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a State-of-the-art object detection networks depend on region proposal algorithms to hypothesize object locations. Advances like SPPnet [1] and Fast R-CNN [2] have reduced the running time of these detection networks, exposing region proposal computation as a bottleneck. In this work, we introduce a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals. An RPN is a fully convolutional network that simultaneously predicts object bounds and objectness scores at each position. The RPN is trained end-to-end to generate high-quality region proposals, which are used by Fast R-CNN for detection. We further merge RPN and Fast R-CNN into a single network by sharing their convolutional features-using the recently popular terminology of neural networks with 'attention' mechanisms, the RPN component tells the unified network where to look. For the very deep VGG-16 model [3] , our detection system has a frame rate of 5 fps (including all steps) on a GPU, while achieving state-of-the-art object detection accuracy on PASCAL VOC 2007, 2012, and MS COCO datasets with only 300 proposals per image. In ILSVRC and COCO 2015 competitions, Faster R-CNN and RPN are the foundations of the 1st-place winning entries in several tracks. Code has been made publicly available 
650 4 |a Journal Article 
700 1 |a He, Kaiming  |e verfasserin  |4 aut 
700 1 |a Girshick, Ross  |e verfasserin  |4 aut 
700 1 |a Sun, Jian  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g 39(2017), 6 vom: 01. Juni, Seite 1137-1149  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnns 
773 1 8 |g volume:39  |g year:2017  |g number:6  |g day:01  |g month:06  |g pages:1137-1149 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2016.2577031  |3 Volltext 
912 |a GBV_USEFLAG_A 
912 |a SYSFLAG_A 
912 |a GBV_NLM 
912 |a GBV_ILN_350 
951 |a AR 
952 |d 39  |j 2017  |e 6  |b 01  |c 06  |h 1137-1149