An analysis of the effect of different image preprocessing techniques on the performance of SURF: Speeded Up Robust Features

Kalia, Robin; Lee, Keundong; Bhamidipati, Samir; Je, Sungkwan; Oh, Wangrok

doi:10.1109/fcv.2011.5739756

Cited by 27 publications

(10 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Descriptors of local features usually have high dimensionality, including 128 dimensions for SIFT feature [14] and 64 dimensions for SURF feature in [15] and [16]. In dealing with a small quantity of images, the high feature dimensionality is not a concern.…”

Section: Related Workmentioning

confidence: 99%

Large-scale Structure-from-Motion Reconstruction with small memory consumption

Kambhamettu

2013

Proceedings of International Conference on Advances in Mobile Computing &Amp; Multimedia - MoMM '13

View full text Add to dashboard Cite

Structure-from-Motion reconstruction is to recover the 3 dimensional structure from 2 dimensional images. Recent research in this field demonstrates the ability to reconstruct cities based on images extracted from a photo collection website; SIFT feature is typically extracted to detect correspondences between images. For the reconstruction of large scale unsorted images, the system is required to store all features and points information in the memory to search for correspondences. As SIFT feature is a 128 dimensional real-valued vector, storing each descriptor would consume a significant amount of memory. Due to this limitation, we propose to project the highdimensional feature into a lower-dimensional space by using a new learned projection matrix while still maintaining the property of the original features. Hence, the result of this projection will shorten the distance among descriptors of the same point while lengthening the distance among descriptors of different points. These projected descriptors use Hellinger distance for calculation of the similarity between features. Furthermore, we learn a mapping function, which will map the real-valued descriptor into binary code coping with the variation of correspondence searching method. Experiments demonstrate that our method achieve excellent results with limited memory requirement.

show abstract

Section: Related Workmentioning

confidence: 99%

Large-scale Structure-from-Motion Reconstruction with small memory consumption

Kambhamettu

2013

Proceedings of International Conference on Advances in Mobile Computing &Amp; Multimedia - MoMM '13

View full text Add to dashboard Cite

show abstract

“…Many high level descriptors contain high dimensionality, such as 128-dimension SIFT feature [12] and 64-dimensions SURF feature [13], [14]. The high feature dimensionality would not be a big concern for dealing with small number of features.…”

Section: Related Workmentioning

confidence: 99%

Structure-from-Motion reconstruction based on weighted Hamming descriptors

Kambhamettu

2014

2014 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

We propose a pipelined methods to reduce memory consumption of large-scale Structure-from-Motion reconstruction with the use of unsorted images extracted from photo collection websites. Recent research is able to reconstruct cities based on extracted images from photo collection websites. SIFT feature is used to find the correspondences between two images. For the large-scale reconstruction with unsorted images, the system needs to store all the descriptors and feature points information in memory to search for correspondences. As each SIFT descriptor is a 128 dimensional real-value vector, storing all the descriptors would consume a significant amount of memory. Based on this limitation, we project the high dimensional features into a low-dimensional space using a learned projection matrix. After projection, the distance of the descriptors belonging to the same point in 3D space is decreased; the distance of the descriptors belonging to the different points is increased. Furthermore, we learn a mapping function, which maps the real-value descriptor into binary code. As Hamming descriptors contain only two value options per bit and the length of the descriptor is limited, there are usually multiple descriptors having the same Hamming distance to the query descriptor. In dealing with this problem, we give different weights to each dimension and rank each bit of the Hamming descriptor based on each dimensions discriminant power; this contributes to reduce the ambiguity in matching the descriptors. The experiments show that our method achieves dense reconstruction results with less than 10 percent of the original memory consumption.

show abstract

“…14.3 Photographs of the wreck Arles-Rhône 13 (photo Olivier Bianchimani, all rights reserved), before (a) and after (b) the enhancement by ACE method. (Chambah et al 2004) Kalia et al (Kalia et al 2011) investigated the effects of different image preprocessing techniques which can affect or improve the performance of the SURF detector (Bay et al 2008). And they proposed new method named IACE 'ImageAdaptive Contrast Enhancement'.…”

Section: Underwater Image Processing: State Of Artmentioning

confidence: 99%

Underwater Seascapes

2014

View full text Add to dashboard Cite

An analysis of the effect of different image preprocessing techniques on the performance of SURF: Speeded Up Robust Features

Cited by 27 publications

References 10 publications

Large-scale Structure-from-Motion Reconstruction with small memory consumption

Large-scale Structure-from-Motion Reconstruction with small memory consumption

Structure-from-Motion reconstruction based on weighted Hamming descriptors

Underwater Seascapes

Contact Info

Product

Resources

About