Browse > Article
http://dx.doi.org/10.7780/kjrs.2021.37.3.1

A Study on Field Compost Detection by Using Unmanned AerialVehicle Image and Semantic Segmentation Technique based Deep Learning  

Kim, Na-Kyeong (Division of Earth Environmental System Science, Major of Spatial Information Engineering, Pukyong National University)
Park, Mi-So (Division of Earth Environmental System Science, Major of Spatial Information Engineering, Pukyong National University)
Jeong, Min-Ji (Division of Earth Environmental System Science, Major of Spatial Information Engineering, Pukyong National University)
Hwang, Do-Hyun (Division of Earth Environmental System Science, Major of Spatial Information Engineering, Pukyong National University)
Yoon, Hong-Joo (Division of Earth Environmental System Science, Major of Spatial Information Engineering, Pukyong National University)
Publication Information
Korean Journal of Remote Sensing / v.37, no.3, 2021 , pp. 367-378 More about this Journal
Abstract
Field compost is a representative non-point pollution source for livestock. If the field compost flows into the water system due to rainfall, nutrients such as phosphorus and nitrogen contained in the field compost can adversely affect the water quality of the river. In this paper, we propose a method for detecting field compost using unmanned aerial vehicle images and deep learning-based semantic segmentation. Based on 39 ortho images acquired in the study area, about 30,000 data were obtained through data augmentation. Then, the accuracy was evaluated by applying the semantic segmentation algorithm developed based on U-net and the filtering technique of Open CV. As a result of the accuracy evaluation, the pixel accuracy was 99.97%, the precision was 83.80%, the recall rate was 60.95%, and the F1-Score was 70.57%. The low recall compared to precision is due to the underestimation of compost pixels when there is a small proportion of compost pixels at the edges of the image. After, It seems that accuracy can be improved by combining additional data sets with additional bands other than the RGB band.
Keywords
Compost; UAV; Semantic Segmentation; Deep Learning;
Citations & Related Records
Times Cited By KSCI : 4  (Citation Analysis)
연도 인용수 순위
1 Choi, J.K., J.G. Son, K.S. Yoon, H.J. Lee, and Y.J. Kim, 2012. Runoff Characteristics in Paddy Field using Cow Manure Compost Fertilizer, Journal of the Korean Society of Agricultural Engineers, 54(3): 29-36 (in Korean with English abstract).   DOI
2 Jeon, E.-I., S.-H. Kim, B.-S. Kim, and K.-H. Park, and O.-I. Choi, 2020. Semantic Segmentation of Drone Imagery Using Deep Learning for Seagrass Habitat Monitoring, Korean Journal of Remote Sensing, 36(2-1): 199-215 (in Korean with English abstract) .   DOI
3 Konkuk University, 2016. Nonpoint source pollution monitoring and control measure for agricultural and livestock areas, Ministry of Agriculture, Seoul, KOR.
4 Park, G.-U., K.-H. Park, B.-H. Moon, and B.-G. Song, 2019. Monitoring of non-point Pollutant Sources: Management Status and Load Change of Composting in a Rural Area based on UAV, Journal of the Korean Association of Geographic Information Studies, 22(2): 01-14 (in Korean with English abstract).   DOI
5 Yang, Q., M. Liu, Z. Zhang, S. Yang , J. Ning, and W. Han, 2019. Mapping Plastic Mulched Farmland for High Resolution Images of Unmanned Aerial Vehicle Using Deep Semantic Segmentation, Remote Sensing, 11(17): 2008.   DOI
6 Hong, S. and J. Kim, 2011. Assessment of leachate characteristics of manure compost under rainfall simulation, Journal of Korean Society of Rural Planning, 7(2): 65-73 (in Korean with English abstract).
7 Ha, R., G. Nam, S. Park, T. Kang, H. Shin, K. Kim, D. Rhew, and H. Lee, 2017. Improvement of Model based on Inherent Optical Properties for Remote Sensing of Cyanobacterial Bloom, Korean Journal of Remote Sensing, 33(2): 111-123 (in Korean with English abstract).   DOI
8 Bhatnagar, S., L. Gill, and B. Ghosh, 2020. Drone Image Segmentation Using Machine and Deep Learning for Mapping Raised Bog Vegetation Communities, Remote Sensing, 12(16): 2602.   DOI
9 Fu, G., C. Liu, R. Zhou, T. Sun, and Q. Zhang, 2017. Classification for high resolution remote sensing imagery using a fully convolutional network, Remote Sensing, 9(5): 498.   DOI
10 Gyeongsangnam-do, 2015. Phase3 Basic plan for Total Pollution Loads Management System in Gyeong sangnam-do, Gyeongsangnam-do Province, KOR.
11 Howard, A.G., M. Zhu, B. Chen, D. Kalenichenko, W. Wang, T. Weyand, M. Andreetto, and H. Adam, 2017. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications, arXiv e-prints, arXiv(1704.04861): 1-9.
12 Kim, H.-M., H. Yoon, S.W. Jang, and Y.H. Chung, 2017. Detection Method of River Floating Debris Using Unmanned Aerial Vehicle and Multispectral Sensors, Korean Journal of Remote Sensing, 33(5-1): 537-546 (in Korean with English abstract).   DOI
13 Bak, S.-H., H.-M. Kim, D.-H. Hwang, H.-J. Yoon, and W.-C. Seo, 2016. Detection technique of Red Tide Using GOCI Level 2 Data, Korean Journal of Remote Sensing, 32(6): 673-679 (in Korean with English abstract).   DOI
14 Krizhevsky, A., I. Sutskever, and G.E. Hinton, 2012. ImageNet Classification with Deep Convolutional Neural Networks, Proc. of the 25th International Conference on Neural Information Processing Systems, Nevada, USA, Dec. 3-8, vol. 1, pp. 1097-1105.
15 Lee, Y.-S., H.-J. Lee, S.-C. Hong, and D.-M. Oh, 2009. Effect of Non-Point Sources from Livestock composted Land - A case of cows manure -, Journal of Wetlands Research, 11(3): 81-88.
16 Na, S., C. Park, K. So, H. Ahn, and K. Lee, 2019. Photochemical Reflectance Index (PRI) Mapping using Drone-based Hyperspectral Image for Evaluation of Crop Stress and its Application to Multispectral Imagery, Korean Journal of Remote Sensing, 35(5-1): 637-647 (in Korean with English abstract).   DOI
17 Zhang, X., Y. Zhou1, J. Jin , Y. Wang, M. Fan, N. Wang, and Y. Zhang, 2021. ICENETv2: A Fine-Grained River Ice Semantic Segmentation Network Based on UAV Images, Remote Sensing, 13(4): 633.   DOI
18 Ronneberger, O., P. Fischer, and T. Brox, 2015. U-net: Convolutional networks for biomedical image segmentation, Proc. of International Conference on Medical Image Computing and Computer assisted Intervention, Munich, DE, Oct. 5-9, pp. 234-241.
19 Won, C.H., Y.H. Choi, M.H. Shin, J.Y. Seo, and J.D. Choi, 2011. Analysis of Livestock Resources on NPS Pollution Characteristics by Rainfall Simulation, Journal of the Korean Society of Agricultural Engineers, 53(2): 67-74 (in Korean with English abstract).   DOI