Structural indexing of satellite images using automatic classification

Gebril, Mohamed; Buaba, Ruben; Homaifar, Abdollah; Kihn, E. A.

doi:10.1109/aero.2011.5747406

Cited by 3 publications

(3 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The input file contains about 1.6 million texture feature vectors of images extracted from Defense Meteorological Satellite Program satellite imagery archives (about 123MB). A detailed discussion of the texture feature extraction approach could be found in [40].…”

Section: Hash Table Creationmentioning

confidence: 99%

Randomized Algorithm for Approximate Nearest Neighbor Search in High Dimensions

Buaba¹,

Homaifar²,

Hendrix

et al. 2014

JPRR

Self Cite

View full text Add to dashboard Cite

A randomized algorithm employs a degree of randomness as part of its logic with uniform random bits as an auxiliary input to guide its behavior, in the hope of achieving good average runtime performance over all possible choices of the random bits. In this paper, we formulate a randomized algorithm capable of finding approximate nearest neighbors, specifically in high dimensional datasets. The random bits of this algorithm are sets of kernels chosen from the Gaussian normal distribution, which are used to create a data structure that guarantees sublinear runtime complexity and retrieval accuracy. The algorithm focuses on selecting the optimal cardinalities of the kernels and their members. These cardinalities influence computational, memory and runtime complexities of the algorithm. We demonstrate that using the cardinality of the kernels to determine the kernel size guarantees the highest provable lower bound of the probability of collision of related items; thus accurate retrieval of nearest neighbors. When implemented on Cray XE6 machine using 76 processes, our algorithm achieves speedup of 69 and approximately 48x performance gain in average query runtime with the retrieval accuracy of 90.5%.

show abstract

Section: Hash Table Creationmentioning

confidence: 99%

Randomized Algorithm for Approximate Nearest Neighbor Search in High Dimensions

Buaba¹,

Homaifar²,

Hendrix

et al. 2014

JPRR

Self Cite

View full text Add to dashboard Cite

show abstract

“…These features are based on normalized central moments of wavelet edges after multi-resolution decomposition of each image. A detailed discussion of the texture feature extraction approach could be found in [42].…”

Section: Datasetmentioning

confidence: 99%

Optimal Load Factor for Approximate Nearest Neighbor Search under Exact Euclidean Locality Sensitive Hashing

Buaba¹,

Homaifar²,

Kihn³

2013

IJCA

Self Cite

View full text Add to dashboard Cite

Locality Sensitive Hashing (LSH) is an index-based data structure that allows spatial item retrieval over a large dataset. The performance measure, ρ, has significant effect on the computational complexity and memory space requirement to create and store items in this data structure respectively. The minimization of ρ at a specific approximation factor c, is dependent on the load factor, α. Over the years, = 4has been used by researchers. In this paper, we demonstratethat the choice of = 4does not guarantee low computational complexity and low memory space of the data structure under the LSH scheme.To guarantee low computational complexity and low memory space, we propose = 5. Experiments on the Defense Meteorological Satellite Program imagery datasethave shown that = 5saves more than 75%on memory space; cuts the computational complexity by more than 70%andanswers query two times faster on the average compared to that of = 4.

show abstract

“…In conventional texture features used for CBIR, there is a gray level co-occurrence matrix [25], [20], [11], Wavelet transforms [21], Local Binary Pattern [5], Tamura's texture [9], Gabor's Filters [9], Markov Random Field [36], [34].…”

Section: Figure 1: Categories Of the Low Level Featuresmentioning

confidence: 99%

Development of Nanosatellite based Image Retrieval system

Gashayija¹,

Bierman²

2014

IJCA

View full text Add to dashboard Cite

Rapid development of nanosatellites has led to many unique and innovative space applications. These tiny satellites have come a long way since Sputnik, the first satellite that was launched in 1957, weighing 83 kg. The success of the CubeSat has revolutionized space technology. Typically, these CubeSat fall into categories of nanosatellites weighing no more than 1.33 Kg and using less power than a five watt light bulb. Mostly, CubeSat has one or more payloads such as Imaging Payload, Scientific payload and High Frequency (HF) Radio Beacon.With the Imaging payload their task is to capture low or high resolution images of the earth observation missions. With the steadily increasing demand for CubeSat imaging payload missions, several nano-satellites have been launched, and thousands of low/high resolution images are acquired every day and transmitted to ground stations. This leads to an exponential increase in the number of low/high resolution images in databases. Therefore, how to retrieve useful images quickly and accurately from a huge and unstructured image database becomes a challenge.In this project, it proposes the use of a content-based image retrieval (CBIR) system relying on a combination of the three low level features such as color, shape and texture features. In order to accurately classify and retrieve useful information in a huge image database. The evaluation performance of the proposed system when compared to other existing systems provides a precision value of 1 or 100%. It can be concluded that the proposed system is able to classify images and retrieve results in a reasonable time of at least 15 seconds.

show abstract

Structural indexing of satellite images using automatic classification

Cited by 3 publications

References 16 publications

Randomized Algorithm for Approximate Nearest Neighbor Search in High Dimensions

Randomized Algorithm for Approximate Nearest Neighbor Search in High Dimensions

Optimal Load Factor for Approximate Nearest Neighbor Search under Exact Euclidean Locality Sensitive Hashing

Development of Nanosatellite based Image Retrieval system

Contact Info

Product

Resources

About