Structure from motion using dense CNN features with keypoint relocalization

Widya, Aji Resindra; Torii, Akihiko; Okutomi, Masatoshi

doi:10.1186/s41074-018-0042-y

Cited by 31 publications

(16 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Since then, new and more robust methods have evolved. DenseSFM proposes a Structure from Motion (SfM) pipeline that uses dense CNN features with keypoint relocalization (Widya et al, 2018). Sarlin et al (2019) also use learned descriptors to improve localization robustness across large variations of appearance.…”

Section: Related Workmentioning

confidence: 99%

Performance Evaluation of a Mobile Mapping Application Using Smartphones and Augmented Reality Frameworks

Hasler

Blaser

Nebiker

2020

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. In this paper, we present a performance evaluation of our smartphone-based mobile mapping application based on an augmented reality (AR) framework in demanding outdoor environments. The implementation runs on Android and iOS devices and demonstrates the great potential of smartphone-based 3D mobile mapping. The application includes several functionalities such as device tracking, coordinate, and distance measuring as well as capturing georeferenced imagery. We evaluated our prototype system by comparing measured points from the tracked device with ground control points in an outdoor environment with four different campaigns. The campaigns consisted of open and closed-loop trajectories and different ground surfaces such as grass, concrete and gravel. Two campaigns passed a stairway in either direction. Our results show that the absolute 3D accuracy of device tracking with state-of-the-art AR framework on a standard smartphone is around 1% of the travelled distance and that the local 3D accuracy reaches sub-decimetre level.

show abstract

Section: Related Workmentioning

confidence: 99%

Performance Evaluation of a Mobile Mapping Application Using Smartphones and Augmented Reality Frameworks

Hasler

Blaser

Nebiker

2020

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

show abstract

“…As deep learning technologies are developing, some new approaches have been introduced into the fields of keypoint detection and matching by means of convolutional neural networks [32]- [34]. For example, A research by Ono et al [32] reported a deep neural network LF-Net that predicted keypoints.…”

Section: B Keypoint Matchingmentioning

confidence: 99%

“…35The intensity of this candidate superpixel would be significantly different from those around it. In (34) and (35), th (1) (or th (2) ) stands for the threshold. Int(•) is the integer-valued function.…”

Section: ) Saliency Superpixel Detectormentioning

confidence: 99%

“…We summarize the scale-space pyramid in Algorithm 2. Compute SL (t) by sub-sampling SL (t−1) 6: End if 7: Compute superpixel intensity image SI (t) of SL (t) using (32) 8: Compute superpixel Gaussian filtering image SF (t) of SI (t) using (33) 9: Compute saliency superpixel sets OS (t) of SF (t) using (34) and (35) 10: End for 11: Compute key-superpixel set KS using (36)…”

Section: ) Scale-space Saliency Superpixel Detectionmentioning

confidence: 99%

See 1 more Smart Citation

Content-Based Superpixel Matching Using Spatially Constrained Student’s-t Mixture Model and Scale-Invariant Key-Superpixels

2020

View full text Add to dashboard Cite

This paper addresses an image matching methodology designed for correspondence problem in computer vision. Firstly, a novel superpixel segmentation model driven by spatially constrained Student's-t mixture model (SMM) is proposed. The tails of Student's t-distribution are heavier than that of traditional Gaussian distribution, therefore, SMM is more insensitive to outliers and noise. In this model, a spatially constraint term based on Markov random field (MRF) is designed, so that good boundary adherence and intensity homogeneity would be achieved. Next, by constructing an adaptive superpixel Gaussian filter and a superpixel salient detector, this paper establishes an innovative key-superpixel detection method by building a superpixel scale-space pyramid. Different from conventional keypoint based detection, two images could then be matched directly in a superpixel-to-superpixel manner. During the matching process, a combinatorial feature descriptor that merges color, shape, gradient and texture features is set up to distinguish each considered key-superpixel. One main advantage of this approach is that implementation time would be largely reduced by less matching demand for key-superpixels and few corresponding local features. Some experiments on datasets at the end would demonstrate a relatively better performance of our model.

show abstract

“…Since then, new and more robust methods have evolved. DenseSFM proposes a Structure from Motion (SfM) pipeline that uses dense CNN features with keypoint relocalization (Widya, Torii, & Okutomi, 2018). Sarlin et al (2019) also use learned descriptors to improve localization robustness across large variations of appearance.…”

Section: Related Workmentioning

confidence: 99%

Implementation and First Evaluation of an Indoor Mapping Application Using Smartphones and Ar Frameworks

Hasler

Blaser

Nebiker

2019

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

Abstract. In this paper, we present the implementation of a smartphone-based indoor mobile mapping application based on an augmented reality (AR) framework and a subsequent performance evaluation in demanding indoor environments. The implementation runs on Android and iOS devices and demonstrates the great potential of smartphone-based 3D mobile mapping. The application includes several functionalities such as device tracking, coordinate, and distance measuring as well as capturing georeferenced imagery. We evaluate our prototype system by comparing measured points from the tracked device with ground control points in an indoor environment with two different campaigns. The first campaign consists of an open, one-way trajectory whereas the second campaign incorporates a loop closure. In the second campaign, the underlying AR framework successfully recognized the start location and correctly repositioned the device. Our results show that the absolute 3D accuracy of device tracking with a standard smartphone is around 1% of the travelled distance and that the local 3D accuracy reaches sub-decimetre level.

show abstract

Structure from motion using dense CNN features with keypoint relocalization

Cited by 31 publications

References 52 publications

Performance Evaluation of a Mobile Mapping Application Using Smartphones and Augmented Reality Frameworks

Performance Evaluation of a Mobile Mapping Application Using Smartphones and Augmented Reality Frameworks

Content-Based Superpixel Matching Using Spatially Constrained Student’s-t Mixture Model and Scale-Invariant Key-Superpixels

Implementation and First Evaluation of an Indoor Mapping Application Using Smartphones and Ar Frameworks

Contact Info

Product

Resources

About