Pedestrian detection is a canonical problem for safety and security applications, and it remains a challenging problem due to the highly variable lighting conditions in which pedestrians must be detected. This paper investigates several domain adaptation approaches to adapt RGB-trained detectors to the thermal domain. Building on our earlier work on domain adaptation for privacy-preserving pedestrian detection, we conducted an extensive experimental evaluation comparing top-down and bottom-up domain adaptation and also propose two new bottom-up domain adaptation strategies. For top-down domain adaptation we leverage a detector pre-trained on RGB imagery and efficiently adapt it to perform pedestrian detection in the thermal domain. Our bottom-up domain adaptation approaches include two steps: first, training an adapter segment corresponding to initial layers of the RGB-trained detector adapts to the new input distribution; then, we reconnect the adapter segment to the original RGB-trained detector for final adaptation with a top-down loss. To the best of our knowledge, our bottom-up domain adaptation approaches outperform the best-performing single-modality pedestrian detection results on KAIST, and outperform the state-of-the-art on FLIR.

Bottom-up and Layer-wise Domain Adaptation for Pedestrian Detection in Thermal Images / Bagdanov; My; Bertini. - In: ACM TRANSACTIONS ON MULTIMEDIA COMPUTING, COMMUNICATIONS AND APPLICATIONS. - ISSN 1551-6857. - ELETTRONICO. - (In corso di stampa), pp. 1-19.

Bottom-up and Layer-wise Domain Adaptation for Pedestrian Detection in Thermal Images

Bagdanov
;
Bertini
In corso di stampa

Abstract

Pedestrian detection is a canonical problem for safety and security applications, and it remains a challenging problem due to the highly variable lighting conditions in which pedestrians must be detected. This paper investigates several domain adaptation approaches to adapt RGB-trained detectors to the thermal domain. Building on our earlier work on domain adaptation for privacy-preserving pedestrian detection, we conducted an extensive experimental evaluation comparing top-down and bottom-up domain adaptation and also propose two new bottom-up domain adaptation strategies. For top-down domain adaptation we leverage a detector pre-trained on RGB imagery and efficiently adapt it to perform pedestrian detection in the thermal domain. Our bottom-up domain adaptation approaches include two steps: first, training an adapter segment corresponding to initial layers of the RGB-trained detector adapts to the new input distribution; then, we reconnect the adapter segment to the original RGB-trained detector for final adaptation with a top-down loss. To the best of our knowledge, our bottom-up domain adaptation approaches outperform the best-performing single-modality pedestrian detection results on KAIST, and outperform the state-of-the-art on FLIR.
In corso di stampa
1
19
Bagdanov; My; Bertini
File in questo prodotto:
File Dimensione Formato  
ACM_TOMM_Bottomup_Layerwise_DomainAdaptation_KieuMy.pdf

accesso aperto

Tipologia: Altro
Licenza: Tutti i diritti riservati
Dimensione 6.99 MB
Formato Adobe PDF
6.99 MB Adobe PDF

I documenti in FLORE sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificatore per citare o creare un link a questa risorsa: https://hdl.handle.net/2158/1221751
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact