A generalized method for 3D object location from single 2D images

1992 ◽  
Vol 25 (8) ◽  
pp. 771-786 ◽  
Author(s):  
D. Daniel Sheu ◽  
Alan H. Bond
Keyword(s):  
Object Location ◽  
3D Object ◽  
2D Images

scholarly journals 3D Object Location Identification Using Finger Pointing and a Robot System for Tracking an Identified Object

2015 ◽  
Vol 24 (6) ◽  
pp. 703-709
Author(s):  
Dong-Gi Gwak ◽  
Soon-Chul Hwang ◽  
Seo-Won Ok ◽  
Jung-Sae Yim ◽  
Dong Hwan Kim
Keyword(s):  
Object Location ◽  
Robot System ◽  
3D Object ◽  
Location Identification

scholarly journals 2D images are not sufficient for testing 3D object recognition

2010 ◽  
Vol 8 (6) ◽  
pp. 514-514
Author(s):  
W. Hayward ◽  
A. Pasqualotto
Keyword(s):  
Object Recognition ◽  
3D Object Recognition ◽  
3D Object ◽  
2D Images

scholarly journals IMPROVING DEEP LEARNING BASED SEMANTIC SEGMENTATION WITH MULTI VIEW OUTLIER CORRECTION

2020 ◽  
Vol XLIII-B2-2020 ◽  
pp. 711-716
Author(s):  
T. Peters ◽  
C. Brenner ◽  
M. Song
Keyword(s):  
Deep Learning ◽  
Transfer Learning ◽  
Input Data ◽  
Semantic Segmentation ◽  
Object Point ◽  
Mobile Mapping ◽  
Convolutional Network ◽  
3D Object ◽  
The Mean ◽  
2D Images

Abstract. The goal of this paper is to use transfer learning for semi supervised semantic segmentation in 2D images: given a pretrained deep convolutional network (DCNN), our aim is to adapt it to a new camera-sensor system by enforcing predictions to be consistent for the same object in space. This is enabled by projecting 3D object points into multi-view 2D images. Since every 3D object point is usually mapped to a number of 2D images, each of which undergoes a pixelwise classification using the pretrained DCNN, we obtain a number of predictions (labels) for the same object point. This makes it possible to detect and correct outlier predictions. Ultimately, we retrain the DCNN on the corrected dataset in order to adapt the network to the new input data. We demonstrate the effectiveness of our approach on a mobile mapping dataset containing over 10’000 images and more than 1 billion 3D points. Moreover, we manually annotated a subset of the mobile mapping images and show that we were able to rise the mean intersection over union (mIoU) by approximately 10% with Deeplabv3+, using our approach.

3D object understanding from 2D images

1998 ◽  
Author(s):  
Patrick S. P. Wang
Keyword(s):  
3D Object ◽  
2D Images

3D ARTICULATED OBJECT UNDERSTANDING, LEARNING, AND RECOGNITION FROM 2D IMAGES

2000 ◽  
Vol 14 (07) ◽  
pp. 863-873 ◽  
Author(s):  
PATRICK S. P. WANG
Keyword(s):  
Virtual Reality ◽  
Linear Combination ◽  
Active Vision ◽  
New Method ◽  
Rigid Object ◽  
3D Object ◽  
Articulated Objects ◽  
Main Portion ◽  
2D Images ◽  
Topological Transformations

This paper is aimed at 3D object understanding from 2D images, including articulated objects in active vision environment, using interactive, and internet virtual reality techniques. Generally speaking, an articulated object can be divided into two portions: main rigid portion and articulated portion. It is more complicated that "rigid" object in that the relative positions, shapes or angles between the main portion and the articulated portion have essentially infinite variations, in addition to the infinite variations of each individual rigid portions due to orientations, rotations and topological transformations. A new method generalized from linear combination is employed to investigate such problems. It uses very few learning samples, and can describe, understand, and recognize 3D articulated objects while the objects status is being changed in an active vision environment.

Sign in / Sign up

Export Citation Format

Share Document