Optical and Sonar Image Classification: Wavelet Packet Transform vs Fourier Transform

Tang, Xiaoou; Stewart, W.K.

doi:10.1006/cviu.2000.0843

Cited by 38 publications

(15 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The Fourier Transform is pop ular technique in the image processing research commu nity [17], [18], [19]. It highlights the dominant spatial fre quencies as well as the dominant orientations of the structures contained in the image.…”

Section: ) Fourier Transformationmentioning

confidence: 99%

Characterization of non-line-of-sight (NLOS) bias via analysis of clutter topology

Hussain

Aytar

Trigoni

et al. 2012

Proceedings of the 2012 IEEE/ION Position, Location and Navigation Symposium

View full text Add to dashboard Cite

Clutter-prone environments are challenging for range-based localization, where distances between anchors and the unlocalised node are estimated using wireless technologies like radio, ultrasound, etc. This is so due to the incidence of Non-Line-Of-Sight (NLOS) distance measurements as the direct path between the two is occluded by the presence of clutter.Thus NLOS distances, having large positive biases, can severely degrade localization accuracy. Till date, NLOS error has been modelled as various distributions including uniform, Gaussian, Poisson and exponential. In this paper, we show that clutter topology itself plays a vital role in the characterization of NLOS bias. We enumerate a feature-set for clutter topologies, including features that can be practically deduced without complete knowl edge of the clutter topology. We then analyze the significance of these features, both individually and in combination with each other, in the estimation of the NLOS rate as well as the NLOS bias distribution for arbitrary clutter topologies. We show that we can obtain the NLOS rate with an error of only 0.03 for a given clutter topology using only those clutter topology features that can be practically realized in a real deployment. We show that estimating the NLOS bias distribution is more challenging which give a small number of poor estimations. I. I NT RODUCTIONLocation awareness has become an integral part of the modern lifestyle. For example, GPS enabled smartphone and GPS receivers enable us to navigate to our destination or provide us information pertinent to our current location. Fleet managers are able to locate and monitor cargo moving in transit. Office and home areas are instrumented to furnish information relating to the time and area we are currently at. Most location services function with the help of anchors, nodes aware of their own positions, and distances measured to them. When there are obstacles in the environment, the accuracy of these measured distances, and thus the estimated position, suffers significantly. This degradation is caused by the existence of Non-Line-of-Sight (NLOS) distances which have large positive biases.Until now, a large body of research has been conducted to address this issue. Some techniques [1], [2] try to detect and separate these erroneous distances from the position estimation process, while others [3], [4], [5], [6] incorporate these distances in a way that mitigates their negative influence on the location accuracy. NLOS bias is hard to model accurately as it is shown to depend on the (arbitrary) underlying topology/arrangement of 978-1-4673-0387-3/12/$31.00 ©20 12 IEEE 1247 the obstacles in the environment [7], [8], [9], [10], [11], [12]. For this reason, it is typically assumed to be uniform [6], [5], [13], [1], Gaussian [14] or exponential [1], [15], [4] for the sake of convenience. Jourdan et al. [12] mention the use of empirically derived NLOS bias distributions in calculating the PEB error bound for localization in a cluttered environment.This paper addresses the p...

show abstract

Section: ) Fourier Transformationmentioning

confidence: 99%

Characterization of non-line-of-sight (NLOS) bias via analysis of clutter topology

Hussain

Aytar

Trigoni

et al. 2012

Proceedings of the 2012 IEEE/ION Position, Location and Navigation Symposium

View full text Add to dashboard Cite

show abstract

“…Se eligieron como variables características los primeros cuatro momentos estadísticos usualmente empleados en tratamiento de imágenes, sean ópticas o acústicas [20]; específicamente se tomaron: la media, la desviación estándar (en lugar de la varianza que es el 2º momento), el 3º momento y el 4º momento alrededor de la media. De otra parte, se tomaron dos puntos de vista para realizar el análisis: a) Tomando las muestras F(wn) del espectro de magnitud de Fourier de longitud /2 como observaciones estadísticas, en cuyo caso y a manera de ejemplo, la media estaría definida así: ( ) Características de las Envolventes Wavelet: para el análisis con la Transformada Wavelet Discreta (DWT) se trabajó con la wavelet Daubechies de orden 4 pues pertenece a una de las familias más usadas en aplicaciones acústicas, de acuerdo con la literatura consultada, y además proporciona una buena regularidad [22] y una buena resolución en el tiempo [23]; de otra parte, se definieron y utilizaron 7 niveles de descomposición de los ecos ultrasónicos: 6 niveles de detalle y el último (6º) nivel de aproximación (con los cuales podría reconstruirse la señal discreta original [20]).…”

Section: Extracción De Característicasunclassified

“…De otra parte, se tomaron dos puntos de vista para realizar el análisis: a) Tomando las muestras F(wn) del espectro de magnitud de Fourier de longitud /2 como observaciones estadísticas, en cuyo caso y a manera de ejemplo, la media estaría definida así: ( ) Características de las Envolventes Wavelet: para el análisis con la Transformada Wavelet Discreta (DWT) se trabajó con la wavelet Daubechies de orden 4 pues pertenece a una de las familias más usadas en aplicaciones acústicas, de acuerdo con la literatura consultada, y además proporciona una buena regularidad [22] y una buena resolución en el tiempo [23]; de otra parte, se definieron y utilizaron 7 niveles de descomposición de los ecos ultrasónicos: 6 niveles de detalle y el último (6º) nivel de aproximación (con los cuales podría reconstruirse la señal discreta original [20]). Con los coeficientes Wavelet resultantes se generaron envolventes Wavelet al tomar sus valores absolutos, y a partir de ellas se calcularon los mismos cuatro momentos estadísticos citados anteriormente.…”

Section: Extracción De Característicasunclassified

Ultrasonic System for Shape Recognition based on Frequency Analysis and Computational Intelligence

Restrepo¹,

Loaiza²,

Caicedo³

2008

Int. Artif.

View full text Add to dashboard Cite

ResumenEstudiando algunos de los principales trabajos sobre reconocimiento de formas básicas de objetos en un ambiente estructurado, puede concluirse que la mayoría utiliza características en el tiempo de los ecos captados. Si bien, el análisis en frecuencia ha sido bastante útil en el procesamiento de señales acústicas en la banda audible, no ha representado igual papel en la ultrasónica aplicada a la robótica debido al uso de transductores de reducido ancho de banda. Por otro lado, la utilización creciente de la Transformada Wavelet, como herramienta que permite realizar un análisis en el tiempo de las componentes de frecuencia de una señal, no tiene aún un nicho amplio en los desarrollos con ultrasonido. En el presente artículo se propone entonces un sistema de procesamiento de señales ultrasónicas captadas a través de una estructura de 2 Transmisores y 2 Receptores, de tal manera que extrayendo diferentes características del espacio temporal, de los espectros de Fourier y de los coeficientes Wavelet, eligiendo las más adecuadas mediante Análisis en Componentes Principales (ACP), y usándolas posteriormente para el entrenamiento de Redes euronales (R A) Especializadas, sea posible el reconocimiento de planos, esquinas, filos y cilindros, en una sola exploración y con un alto porcentaje de aciertos.

show abstract

“…In computer vision, several approaches have been proposed in the past for texture analysis [7,8]. It was shown that different transforms like Fourier transform is a valuable tool for seabed texture analysis [9]. However, in transforming to the frequency domain using Fourier analysis, the drawback is that time information is lost.…”

Section: Introductionmentioning

confidence: 99%

Wavelet-based acoustic seabed discrimination system

Javidan

2010

2010 2nd International Conference on Image Processing Theory, Tools and Applications

View full text Add to dashboard Cite

In almost any underwater operation that takes place on or under the seafloor, it is necessary to have an understanding of the makeup of the seabed below the silt and sediment. Sonar is an acoustic system extensively used for underwater inspection as well as seabed classification. In this paper, the problem of automatic segmentation and classification of seafloor using automatic acoustic seabed discrimination systems is discussed and a new split and merge algorithm based on the concept of standard wavelet transform is presented. Experimental results on true prototype data indicate the robustness and effectiveness of the proposed algorithm.

show abstract

Optical and Sonar Image Classification: Wavelet Packet Transform vs Fourier Transform

Cited by 38 publications

References 29 publications

Characterization of non-line-of-sight (NLOS) bias via analysis of clutter topology

Characterization of non-line-of-sight (NLOS) bias via analysis of clutter topology

Ultrasonic System for Shape Recognition based on Frequency Analysis and Computational Intelligence

Wavelet-based acoustic seabed discrimination system

Contact Info

Product

Resources

About