A Comparison of Feature Extraction Algorithms Based on Sonar Sensor Data

Ismail, Hesham; Balachandran, Balakumar

doi:10.1115/imece2013-62989

Cited by 3 publications

(7 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This manuscript follows previous studies reported by the authors [13], [14]. The authors have organized the material into five sections.…”

Section: Indexmentioning

confidence: 87%

“…By selecting a low threshold value for the TBF algorithm, it was ensured that no important features were removed. In an earlier study of the authors [13], it was shown that by increasing the threshold to a value above 100, a considerable number of the important features were removed, whereas for a threshold below a value of 100, no important features were lost. This observation is consistent with the conclusion drawn by Wijk and Christensen [18]; they used a low threshold value to avoid the removal of important features.…”

Section: A Environment I: L-shaped Environmentmentioning

confidence: 98%

“…In an earlier work of the authors, a comparative study of the TBF, Hough transform, and THF algorithms has been undertaken [13]. From this earlier work, it was found that the THF algorithm provided better results than the Hough Transform, when applied to raw SONAR data.…”

Section: B Hough Transform Alogrithmmentioning

confidence: 99%

“…Also, the visited locations need to be appropriately separated (i.e., SONAR readings should not be grouped in one small area and so on). In an earlier work [13], the mobile vehicle visited 15 locations in a similar environment, with the visited locations being close to one corner only. In this prior work, the corner could be detected, but no other features in the environment could be identified.…”

Section: A Environment I: L-shaped Environmentmentioning

confidence: 99%

“…The actual environment with no interior features is placed over the SONAR data for comparison purpose only. For the limit constraint data, data below 50 cm and above 200 cm have been removed [13]. (a) Raw SONAR data for experimental environment without interior features.…”

Section: B Environment IImentioning

confidence: 99%

See 4 more Smart Citations

Algorithm Fusion for Feature Extraction and Map Construction From SONAR Data

Ismail¹,

Balachandran²

2015

IEEE Sensors J.

Self Cite

View full text Add to dashboard Cite

Feature extraction is an important aspect of simultaneous localization and mapping, a process, in which a mobile platform is used to create a map of an unknown environment, while simultaneously locating the platform's own position within the constructed map or environment. Geometric shapes or features, such as lines, circles, and interior and exterior corners, are determined as a part of this process, and these features may be used as landmarks. In this paper, an original feature extraction algorithm specific to distance measurements obtained through SONAR sensor data is presented. This algorithm has been put together by combining the SONAR salient feature extraction algorithm and the triangulation Hough-based fusion with the point-in-polygon detection. The reconstructed maps obtained through simulations and experimental data with the fusion algorithm are compared with the maps obtained with existing feature extraction algorithms. Based on the results, it is suggested that the proposed algorithm can be considered as an option for the data obtained from SONAR sensors in environments, where the other forms of sensing are not viable.

show abstract

“…This manuscript follows previous studies reported by the authors [13], [14]. The authors have organized the material into five sections.…”

Section: Indexmentioning

confidence: 87%

Section: A Environment I: L-shaped Environmentmentioning

confidence: 98%

Section: B Hough Transform Alogrithmmentioning

confidence: 99%

Section: A Environment I: L-shaped Environmentmentioning

confidence: 99%

Section: B Environment IImentioning

confidence: 99%

See 3 more Smart Citations

Algorithm Fusion for Feature Extraction and Map Construction From SONAR Data

Ismail¹,

Balachandran²

2015

IEEE Sensors J.

Self Cite

View full text Add to dashboard Cite

show abstract

Feature Extraction Algorithm Fusion for SONAR Sensor Data Based Environment Mapping

Ismail

Balachandran

2014

Volume 4A: Dynamics, Vibration, and Control

View full text Add to dashboard Cite

Mobile platforms that make use of concurrent localization and mapping algorithms have industrial applications for autonomous inspection and maintenance, such as the inspection of flaws and defects in oil pipelines and storage tanks. An important component of these algorithms is feature extraction, which involves detection of significant features that represent the environment. For example, points and lines can be used to represent features such as corners, edges, and walls. Feature extraction algorithms make use of relative position and angle data from sensor measurements gathered as the mobile vehicle traverses the environment. In this paper, sound navigation and ranging (SONAR) sensor data obtained from a mobile vehicle platform are considered for feature extraction and related algorithms are developed and studied. In particular, different combinations of commonly used feature extraction algorithms are examined to enhance the representation of the environment. The authors fuse the Triangulation Based Fusion (TBF), Hough Transfrom (HT), and SONAR salient feature extraction algorithms with the clustering algorithm. It is shown that the novel algorithm fusion can be used to capture walls, corners as well as features such as gaps in walls. This capability can be used to obtain additional information about the environment. Details of the algorithm fusion are discussed and presented along with results obtained through experiments.

show abstract

Feature Extraction and Mapping Construction for Mobile Robot via Ultrasonic MDP and Fuzzy Model

Long

et al. 2018

Sensors

View full text Add to dashboard Cite

This paper presents a modeling approach to feature classification and environment mapping for indoor mobile robotics via a rotary ultrasonic array and fuzzy modeling. To compensate for the distance error detected by the ultrasonic sensor, a novel feature extraction approach termed “minimum distance of point” (MDP) is proposed to determine the accurate distance and location of target objects. A fuzzy model is established to recognize and classify the features of objects such as flat surfaces, corner, and cylinder. An environmental map is constructed for automated robot navigation based on this fuzzy classification, combined with a cluster algorithm and least-squares fitting. Firstly, the platform of the rotary ultrasonic array is established by using four low-cost ultrasonic sensors and a motor. Fundamental measurements, such as the distance of objects at different rotary angles and with different object materials, are carried out. Secondly, the MDP feature extraction algorithm is proposed to extract precise object locations. Compared with the conventional range of constant distance (RCD) method, the MDP method can compensate for errors in feature location and feature matching. With the data clustering algorithm, a range of ultrasonic distances is attained and used as the input dataset. The fuzzy classification model—including rules regarding data fuzzification, reasoning, and defuzzification—is established to effectively recognize and classify the object feature types. Finally, accurate environment mapping of a service robot, based on MDP and fuzzy modeling of the measurements from the ultrasonic array, is demonstrated. Experimentally, our present approach can realize environment mapping for mobile robotics with the advantages of acceptable accuracy and low cost.

show abstract

A Comparison of Feature Extraction Algorithms Based on Sonar Sensor Data

Cited by 3 publications

References 0 publications

Algorithm Fusion for Feature Extraction and Map Construction From SONAR Data

Algorithm Fusion for Feature Extraction and Map Construction From SONAR Data

Feature Extraction Algorithm Fusion for SONAR Sensor Data Based Environment Mapping

Feature Extraction and Mapping Construction for Mobile Robot via Ultrasonic MDP and Fuzzy Model

Contact Info

Product

Resources

About