Technical report: Underwater feature extraction and pillar mapping
نویسندگان
چکیده
A mechanicaly scanned imaging sonar, MSIS, produces a 2D image of the range and bearing of return intensities. The pattern produced in this image depends on the enviormental feature that caused it. These features are very useful for underwater navigation but the inverse mapping of sonar image pattern to environmental feature can be ambiguous. We investigate problems associated with using MSIS for navigation. In particular we show that support vector machines can be used to classify the existance and types of feature in a sonar image. We develop a sonar processing pipleline that can be used for navigation. This is tested on two sonar datasets collected from ROV’s.
منابع مشابه
An Efficient Underwater Image Enhancement Using Color Constancy Deskewing Algorithm
The objective of image enhancement is to recover the perception of information in underwater images for human viewers, or to provide recovered input for other automated image processing techniques. In underwater conditions, the image clarities are corrupted by light inclusion and diffusion. This causes one colour to dominate the image. In order to enhance the observation of underwater images, w...
متن کاملFeature extraction and classification for underwater target signals based on Hilbert-Huang transform theory
In order to realize feature extraction and classification for underwater target signals, instead of the empirical mode decomposition (EMD) method, a new Ensemble EMD (EEMD) is used in the Hilbert-Huang transform when underwater target signals are analyzed. By the EEMD and Hilbert-huang transform, some feature parameters are extracted and applied to the classification of underwater target signal...
متن کاملPoint Features Extraction: towards Slam for an Autonomous Underwater Vehicle
Simultaneous Localisation and Mapping (SLAM) is a process by which a mobile robot maps the environment and concurrently localises itself within the map. Feature extraction is a technique by which sensor data is processed to obtain well defined entities (features) which are recognisable and can be repeatedly detected. These features are then used to aid navigation. In this paper, Mechanically Sc...
متن کاملUnderwater SLAM in man-made structured environments
This paper describes a navigation system for autonomous underwater vehicles (AUVs) in partially structured environments, such as dams, harbors, marinas, and marine platforms. A mechanically scanned imaging sonar is used to obtain information about the location of vertical planar structures present in such environments. A robust voting algorithm has been developed to extract line features, toget...
متن کاملClassification of ships using autocorrelation technique for feature extraction of the underwater acoustic noise
The paper applies spectral analysis to the underwater acoustic noise radiated by ships. A frequency band is specified to characterize the sound produced by different platforms. Hence the paper proposes a new technique for feature extraction by applying autocorrelation technique and discrete cosine transform. The features extracted are employed by a recognition engine that uses Gaussian mixture ...
متن کامل