RESEARCH ON A RANDOM FOREST-BASED UNDERWATER TARGET IMAGE RECOGNITION METHOD
Journal Title: Topics in Intelligent Computing and Industry Design (ICID) - Year 2017, Vol 1, Issue 3
Abstract
Aimed to solve the problem of the low recognition rate of underwater images in bad underwater environment, an underwater target images’ gray level pixel matrix has been employed as the feature matrices to train random forest classifier and get the final classification result from the votes of multi decision trees in this paper. The Gaussian noise with different variances are added into the underwater acoustic image to simulate the different levels of complexity in underwater environment, by which the recognition rate and false alarm rate of diver, fish, propeller, bubble and pipeline are obtained. Furthermore, the performance of this method by ROC curve and AUC are analyzed, and the simulation results show that if the SNR (Signal-to-noise ratio) of underwater target is not less than 2.62dB or the PSNR (Peak signal-to-noise ratio) is not less than 12.7dB, the method proposed in this paper can detect underwater target with weak signal, and achieve more than 90% of the target recognition rate.
Authors and Affiliations
Min Chen, Da Song, Weibo Liu, Xiaomei Xie
Keywords
Related Articles
- EP ID EP409162
- DOI 10.26480/iscsai.01.2017.40.44
- Views 86
- Downloads 0
A NEW METHOD OF CORRELATION REGION LEAST SQUARE ALGORITHM FOR EARTH SYSTEM PARAMETER IDENTIFICATION
In the earth exploration field, least square algorithm is one of the most commonly traditional methods for earth parameter system identification. Aiming at the problems of the traditional least square algorithm based on...
APPROXIMATE GROWTH CURVE OF FETUS PANCREAS BY MONOTONE SPLINES REGRESSION
This paper presents a new algorithm based on Novel Extension Rule for reasoning problems in Wumpus World. This algorithm describes these problems by propositional logic terms and solves them with Novel Extension Rule. In...
QUANTITATIVE COMPARATIVE ANALYSIS OF MULTILAYER METHOD, REAL SPACE METHOD AND BLOCH WAVE METHOD IN ANALOG CIRCUIT CALCULATION
The electron diffraction calculation is one of the most important methods of electron crystallography. It is very important to select the method of electron diffraction calculation for the study of electronic crystals. A...
ON ECONOMIC DATA PREDICTION BASED ON WAVELET ANALYSIS
Using the least square method to deal with the abnormal data will have a great influence on its coefficient, which will result in inadequate fitting of the overall model. In this paper, the wavelet analysis method is fir...
ALGORITHM RESEARCH ON CONFLICT DETECTION AND ELIMINATION IN COLLABORATIVE WORK
For cross-enterprise resource conflict problem in collaborative work plan, put forward a new kind of conflict detection and elimination of cross-enterprise project work model, based on the time of supply and demand plan...