Abstract
The motion behaviors of copepods has important scientific research value and there is very little research on recognition of their motion behaviors simultaneously. Recognition of the basic motion behaviors of copepods using deep learning methods can greatly reduce the time cost of distinguishing and statistics, as well as achieve the purpose of improving efficiency. Based on the characteristics of motion of copepods that bring challenges to the extraction of motion fragments from raw video and the establishment of data set, such as instantaneous moving, static status most time, small-scale and high-frequency, this article propose an improved Camshift algorithm for detection of moving targets to overcome these challenges and establish the motion behaviors image acquisition system and a standard data set of motion behaviors, which provides the experience and methods of marine zooplankton behaviors database. Finally, the LRCN network that combines the advantages of CNN and LSTM is adopted to study the impacts of different factors on the model performance, such as the number of frames of sample, preprocessing operations and sample dimensions. Experimental results show that the LRCN network has excellent potential in classification of motion behaviors of copepods, when the number of frames of sample reaches 7, the precison rate, recall rate, f1-score are 0.96, 0.95, 0.95, respectively. In addition, the rise in number of frames and preprocessing has a positive effect on the recognition, the 4D samples (image sequence) is more suitable for the LRCN model than 3D samples (trajectory image).
Highlights
Nowadays, the studies and applications of deep learning in marine zooplankton mostly stay in the field of image recognition of species, and there is little research on their behavior recognition
Shi et al.: Research on Recognition of Motion Behaviors of Copepods benchmarks: UCF101 and HMDB51, the results show that C2LSTM can acquire effectively spatial features and time dependencies
NUMBER OF FRAMES OF SAMPLE In order to test the impact of the number of frames of a single sample (T ) on the motion behaviors recognition of Long Term Recurrent Convolutional Network (LRCN) model, the experiment was divided into four groups according to the number of frames of sample, i. e., T = 3, T = 5, T = 7 and T = 9
Summary
The studies and applications of deep learning in marine zooplankton mostly stay in the field of image recognition of species, and there is little research on their behavior recognition. (4) Zooplanktons have a high frequency during motion but do not move most of the time The motion probability and the displacement present an step function relationship in a video fragment with fixed number of frames, but considering these previous point mentioned above, it may need to be modified at the initial scope (a mm), but the formula (2) is generally satisfied. E. DATA AUGMENTATION In this article, 530 original video samples of five types of motion behaviors are obtained through experiments and image processing. The structure of the LRCN network adopted in this paper
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
