Crowd Localization from Gaussian Mixture Scoped Knowledge and Scoped Teacher

Crowd localization is to predict each instance head position in crowd scenarios. Since the distance of pedestrians being to the camera are variant, there exists tremendous gaps among scales of instances within an image, which is called the intrinsic scale shift. The core reason of intrinsic scale sh...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - PP(2023) vom: 08. März
1. Verfasser: Wang, Juncheng (VerfasserIn)
Weitere Verfasser: Gao, Junyu, Yuan, Yuan, Wang, Qi
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2023
Zugriff auf das übergeordnete Werk:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Schlagworte:Journal Article
LEADER 01000naa a22002652 4500
001 NLM355330121
003 DE-627
005 20231226064123.0
007 cr uuu---uuuuu
008 231226s2023 xx |||||o 00| ||eng c
024 7 |a 10.1109/TIP.2023.3251727  |2 doi 
028 5 2 |a pubmed24n1184.xml 
035 |a (DE-627)NLM355330121 
035 |a (NLM)37028355 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Wang, Juncheng  |e verfasserin  |4 aut 
245 1 0 |a Crowd Localization from Gaussian Mixture Scoped Knowledge and Scoped Teacher 
264 1 |c 2023 
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 Revised 07.04.2023 
500 |a published: Print-Electronic 
500 |a Citation Status Publisher 
520 |a Crowd localization is to predict each instance head position in crowd scenarios. Since the distance of pedestrians being to the camera are variant, there exists tremendous gaps among scales of instances within an image, which is called the intrinsic scale shift. The core reason of intrinsic scale shift being one of the most essential issues in crowd localization is that it is ubiquitous in crowd scenes and makes scale distribution chaotic. To this end, the paper concentrates on access to tackle the chaos of the scale distribution incurred by intrinsic scale shift.We propose Gaussian Mixture Scope (GMS) to regularize the chaotic scale distribution. Concretely, the GMS utilizes a Gaussian mixture distribution to adapt to scale distribution and decouples the mixture model into sub-normal distributions to regularize the chaos within the sub-distributions. Then, an alignment is introduced to regularize the chaos among sub-distributions. However, despite that GMS is effective in regularizing the data distribution, it amounts to dislodging the hard samples in training set, which incurs overfitting. We assert that it is blamed on the block of transferring the latent knowledge exploited by GMS from data to model. Therefore, a Scoped Teacher playing a role of bridge in knowledge transform is proposed. What' s more, the consistency regularization is also introduced to implement knowledge transform. To that effect, the further constraints are deployed on Scoped Teacher to derive feature consistence between teacher and student end. With proposed GMS and Scoped Teacher implemented on four mainstream datasets of crowd localization, the extensive experiments demonstrate the superiority of our work. Moreover, comparing with existing crowd locators, our work achieves state-of-the-art via F1-measure comprehensively on four datasets 
650 4 |a Journal Article 
700 1 |a Gao, Junyu  |e verfasserin  |4 aut 
700 1 |a Yuan, Yuan  |e verfasserin  |4 aut 
700 1 |a Wang, Qi  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on image processing : a publication of the IEEE Signal Processing Society  |d 1992  |g PP(2023) vom: 08. März  |w (DE-627)NLM09821456X  |x 1941-0042  |7 nnns 
773 1 8 |g volume:PP  |g year:2023  |g day:08  |g month:03 
856 4 0 |u http://dx.doi.org/10.1109/TIP.2023.3251727  |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 PP  |j 2023  |b 08  |c 03