Browse > Article
http://dx.doi.org/10.7780/kjrs.2022.38.3.2

A Study on Biomass Estimation Technique of Invertebrate Grazers Using Multi-object Tracking Model Based on Deep Learning  

Bak, Suho (Research Institute, IREM tech. Co., Ltd.)
Kim, Heung-Min (Research Institute, IREM tech. Co., Ltd.)
Lee, Heeone (Research Institute, IREM tech. Co., Ltd.)
Han, Jeong-Ik (Research Institute, IREM tech. Co., Ltd.)
Kim, Tak-Young (Remote Sensing Department, IREM tech. Co., Ltd.)
Lim, Jae-Young (IREM tech. Co., Ltd.)
Jang, Seon Woong (IREM tech. Co., Ltd.)
Publication Information
Korean Journal of Remote Sensing / v.38, no.3, 2022 , pp. 237-250 More about this Journal
Abstract
In this study, we propose a method to estimate the biomass of invertebrate grazers from the videos with underwater drones by using a multi-object tracking model based on deep learning. In order to detect invertebrate grazers by classes, we used YOLOv5 (You Only Look Once version 5). For biomass estimation we used DeepSORT (Deep Simple Online and real-time tracking). The performance of each model was evaluated on a workstation with a GPU accelerator. YOLOv5 averaged 0.9 or more mean Average Precision (mAP), and we confirmed it shows about 59 fps at 4 k resolution when using YOLOv5s model and DeepSORT algorithm. Applying the proposed method in the field, there was a tendency to be overestimated by about 28%, but it was confirmed that the level of error was low compared to the biomass estimation using object detection model only. A follow-up study is needed to improve the accuracy for the cases where frame images go out of focus continuously or underwater drones turn rapidly. However,should these issues be improved, it can be utilized in the production of decision support data in the field of invertebrate grazers control and monitoring in the future.
Keywords
Whitening; ROV; Underwater remote sensing; Deep learning; Multi-object tracking;
Citations & Related Records
Times Cited By KSCI : 4  (Citation Analysis)
연도 인용수 순위
1 Choi, C.G., M. Ohno, and C.H. Sohn, 2002. Seaweed Succession on Artificial Reefs Placed in Different Depths at Ikata, Japan, Journal of Fisheries Science and Technology, 5(4): 281-286. https://doi.org/10.5657/fas.2002.5.4.281   DOI
2 Choi, I.H., 2021. A Study on the Managements and Distribution Characteristics of the Barren Ground in the Coastal Waters of East Sea, Korea, Chonnam National University, Gwangju, Korea.
3 Hwang, S.I., D.K. Kim, B.J. Sung, S.K. Jun, J.I. Bae, and B.H. Jeon, 2017. Effects of Climate Change on Whitening Event Proliferation the Coast of Jeju, Korean Journal of Environment and Ecology, 31(6): 529-536. https://doi.org/10.13047/KJEE.2017.31.6.529   DOI
4 Kim, C.S., Y.S. Kim, H.G. Choi, and K.W. Nam, 2014. Variations of Seaweed Community Structure and Distribution of Crustose Coralline Algae at Gallam, Samchuk, Eastern Coast of Korea, Korean Journal of Environment and Ecology, 28(1): 10-23. https://doi.org/10.13047/KJEE.2014.28.1.10   DOI
5 Ludvigsen, M., T. Thorsnes, R.E. Hansen, A.J. Sorensen, G. Johnsen, P.A. Lagstad, O. Odegard, M. Candeloro, S.M. Nornesm, and C. Malmquist, 2015. Underwater vehicles for environmental management in coastal areas, Proc. of OCEANS 2015-Genova, Genova, Italy, May 19-21, pp. 1-6. https://doi.org/10.1109/OCEANS-Genova.2015.7271728   DOI
6 Qiu, Z., Y. Yao, and M. Zhong, 2019. Underwater sea cucumbers detection based on pruned SSD, Proc. of 2019 IEEE 3rd Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC), Chongqing, China, Oct. 11-13, pp. 738-742. https://doi.org/10.1109/IMCEC46724.2019.8983935   DOI
7 Wojke, N., A. Bewley, and D. Paulus, 2017. Simple online and realtime tracking with a deep association metric, Proc. of 2017 IEEE International Conference on Image Processing (ICIP), Beijing, China, Sep. 17-20, pp. 3645-3649. https://doi.org/10.1109/ICIP.2017.8296962   DOI
8 Jocher, G., 2020. Ultralytics/yolov5, https://github.com/ultralytics/yolov5.git, Accessed on May 17, 2022.
9 Korea Fisheries Resources Agency, 2016. Investigation of the cause of barren ground and establishment of countermeasures: barren ground restoration advancement project by sea area, Korea Fisheries Resources Agency, Busan, Korea.
10 Gao, M., Y. Bai, Z. Li, S. Li, B. Zhang, and Q. Chang, 2021. Real-Time Jellyfish Classification and Detection Based on Improved YOLOv3 Algorithm, Sensors, 21(23): 8160. https://doi.org/10.3390/s21238160   DOI
11 Jung, S.W., B.H. Jeon, and C.G. Choi, 2019. Characteristics of Summer Marine Algal Community and Barren Ground in the Southern Coast of Jeju, Korea, Journal of the Korean Society of Marine Environment & Safety, 25(2): 212-219. https://doi.org/10.7837/kosomes.2019.25.2.212   DOI
12 Kim, J.A., J.Y. Sung, and S.H. Park, 2020. Comparison of Faster-RCNN, YOLO, and SSD for real-time vehicle type recognition, Proc. of 2020 IEEE International Conference on Consumer Electronics-Asia (ICCE-Asia), Seoul, Korea, Nov. 1-3, pp. 1-4. https://doi.org/10.1109/ICCE-Asia49877.2020.9277040   DOI
13 Kwon, H.O., 2008. Manual of seaweed restoration in whitening coastal area, Pukyong National University, Busan, Korea.
14 Buscher, E., D.L. Mathews, C. Bryce, K. Bryce, D. Joseph, and N.C. Ban, 2020. Applying a low cost, mini Remotely Operated Vehicle (ROV) to assess an ecological baseline of an indigenous seascape in Canada, Frontiers in Marine Science, 7: 669. https://doi.org/10.3389/fmars.2020.00669   DOI
15 Lambertini, A., M. Menghini, J. Cimini, A. Odetti, G. Bruzzone, M. Bibuli, E. Mandanici, L. Vittuari, P. Castaldi, M. Caccia, and L. De Marchi, 2022. Underwater Drone Architecture for Marine Digital Twin: Lessons Learned from SUSHI DROP Project, Sensors, 22(3): 744. https://doi.org/10.3390/s22030744   DOI
16 Lin, T.Y., P. Goyal, R. Girshick, K. He, and P. Dollar, 2017. Focal loss for dense object detection, Proc. of 2017 IEEE International Conference on Computer Vision (ICCV), Venice, Italy, Oct. 22-29, pp. 2980-2988. https://doi.org/10.1109/ICCV.2017.324   DOI
17 Wozniak, B. and J. Dera, 2007. Light absorption in sea water, Springer-Verlag, New York, NY, USA.