Aiming at the problem of low accuracy of underwater target recognition due to the introduction of non-uniform illumination during underwater optical detection, this paper proposes an underwater target recognition algorithm under the influence of non-uniform illumination. The algorithm firstly uses the illumination invariant extraction algorithm based on Nonsubsampled Contourlet Transform (NSCT) to extract the essential features of underwater images. Then, the extracted underwater image is used as the input of the Convolutional Neural Network (CNN) to perform target recognition. The experimental results show that the recognition accuracy of the underwater target is 9% higher than the source image, reaching 96%.
Aiming at the problem of image distortion caused by light refraction and the limitations of existing solutions, we propose a three-dimensional information extraction algorithm based on spatial mapping. Main procedures of the algorithm are as follows. First, we obtain the pixel coordinate information of the underwater image. Then, we convert the target underwater image into the equivalent air image through the pixel-pixel spatial mapping relationship. At last, the three-dimensional information is extracted from the equivalent air image. The algorithm can be applied to extract three-dimensional information of multiple underwater targets. Experiment results show that compared with the actual three-dimensional information of the target, the average error rate of the distance extracted by the proposed algorithm is 1.475%, and the average error of the attitude angle extracted by the proposed algorithm is 2.559°, which means the three-dimensional information of the target can be accurately extracted by the proposed algorithm.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.