Multi-scale Conditional Random Fields for first-person activity recognition

2014 ◽  
Author(s):  
Kai Zhan ◽  
Steven Faux ◽  
Fabio Ramos
Keyword(s):  
Activity Recognition ◽  
Random Fields ◽  
Conditional Random Fields ◽  
First Person ◽  
Multi Scale

Semi-Markov conditional random fields for accelerometer-based activity recognition

2010 ◽  
Vol 35 (2) ◽  
pp. 226-241 ◽  
Author(s):  
La The Vinh ◽  
Sungyoung Lee ◽  
Hung Xuan Le ◽  
Hung Quoc Ngo ◽  
Hyoung Il Kim ◽  
...  
Keyword(s):  
Activity Recognition ◽  
Random Fields ◽  
Conditional Random Fields

scholarly journals Human activity recognition using conditional random fields and privileged information

2016 ◽  
Author(s):  
Μιχαήλ Βρίγκας
Keyword(s):  
Activity Recognition ◽  
Human Activity ◽  
Random Fields ◽  
Conditional Random Fields ◽  
Human Activity Recognition ◽  
Privileged Information

Η διατριβή ασχολείται με το πρόβλημα της αναγνώρισης της ανθρώπινης δραστηριότητας από εικονοσειρές και απλές εικόνες, το οποίο ανήκει στην ευρύτερη περιοχή της υπολογιστικής όρασης. Για την επίλυση του προβλήματος χρησιμοποιήθηκαν τα υπό συνθήκη τυχαία πεδία συνδυάζοντας δεδομένα από πολλαπλές πηγές. Επιπλέον, προτάθηκε μια καινούρια μέθοδος ταξινόμησης που βασίζεται στην προνομιακή πληροφορία, η oποία δίδεται ως επιπλέων είσοδος στο μοντέλο και είναι διαθέσιμη μόνο στην φάση της εκπαίδευσης αλλά όχι στην φάση του ελέγχου. Τα πειραματικά αποτελέσματα δείχνουν ότι αυτού του είδους η πληροφορία βοηθά στο να δημιουργήσουμε έναν ισχυρότερο ταξινομητή απ' ότι κάποιος θα μάθαινε χωρίς αυτήν, ενώ αυξάνει σημαντικά την ακρίβεια της αναγνώρισης του μοντέλου.

scholarly journals An Automatic Extraction Method for Hatched Residential Areas in Raster Maps Based on Multi-Scale Feature Fusion

2021 ◽  
Vol 10 (12) ◽  
pp. 831
Author(s):  
Jianhua Wu ◽  
Jiaqi Xiong ◽  
Yu Zhao ◽  
Xiang Hu
Keyword(s):  
Random Fields ◽  
Conditional Random Fields ◽  
Feature Fusion ◽  
Gabor Filter ◽  
Residential Areas ◽  
Change Analysis ◽  
Land Quality ◽  
Multi Scale ◽  
Raster Maps ◽  
Fully Connected

Extracting the residential areas from digital raster maps is beneficial for research on land use change analysis and land quality assessment. In traditional methods for extracting residential areas in raster maps, parameters must be set manually; these methods also suffer from low extraction accuracy and inefficiency. Therefore, we have proposed an automatic method for extracting the hatched residential areas from raster maps based on a multi-scale U-Net and fully connected conditional random fields. The experimental results showed that the model that was based on a multi-scale U-Net with fully connected conditional random fields achieved scores of 97.05% in Dice, 94.26% in Intersection over Union, 94.92% in recall, 93.52% in precision and 99.52% in accuracy. Compared to the FCN-8s, the five metrics increased by 1.47%, 2.72%, 1.07%, 4.56% and 0.26%, respectively and compared to the U-Net, they increased by 0.84%, 1.56%, 3.00%, 0.65% and 0.13%, respectively. Our method also outperformed the Gabor filter-based algorithm in the number of identified objects and the accuracy of object contour locations. Furthermore, we were able to extract all of the hatched residential areas from a sheet of raster map. These results demonstrate that our method has high accuracy in object recognition and contour position, thereby providing a new method with strong potential for the extraction of hatched residential areas.

Sign in / Sign up

Export Citation Format

Share Document