Metrological investigation of the localization uncertainty of object detection methodologies

Andrea Mannella; Vittorio Sala; Davide M. Fabris

doi:10.1117/12.2593286

20 June 2021 Metrological investigation of the localization uncertainty of object detection methodologies

Andrea Mannella, Vittorio Sala, Davide M. Fabris

Proceedings Volume 11785, Multimodal Sensing and Artificial Intelligence: Technologies and Applications II; 117850R (2021) https://doi.org/10.1117/12.2593286
Event: SPIE Optical Metrology, 2021, Online Only

Abstract

The application of Deep Learning Neural Networks to Object Detection grants the localization of object instances from several classes within images. The inference of the locations of the items is not always precise and the positional error of bounding boxes can result being in the pixel range. This research aims at analysing the object localization uncertainty of Deep Convolutional Neural Networks (DCNNs), by considering MVTec HALCON and open-source Neural Networks. The metrological outcomes are presented. Since matching algorithms are still used to identify shapes, contours and edges, a comparison with them sounds like an obligation. The results of both Deep Learning and Shape-Based Matching (SBM) algorithms are compared with a sub-pixel precise reference labelling. The labelling consists of specific bounding boxes around the objects of each image of the dataset. It was obtained manually performing rectangular boxes on a single image and propagating them to the entire dataset according to the camera pose, precisely determined by keeping the target fixed and moving the camera with a measuring machine. The intent of this work is to establish the best detection methodology with respect to different testing conditions, considering also the effect of possible Gaussian noise and imprecise labelling.

Conference Presentation

Citation Download Citation

Andrea Mannella, Vittorio Sala, and Davide M. Fabris "Metrological investigation of the localization uncertainty of object detection methodologies", Proc. SPIE 11785, Multimodal Sensing and Artificial Intelligence: Technologies and Applications II, 117850R (20 June 2021); https://doi.org/10.1117/12.2593286

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available