John Paul Q. Tomas
ABSTRACT
YOLO is one of the most efficient algorithms that can be used for object detection in computer vision. In this study, the researchers used the YOLOv7 model to detect water hyacinths and other non-living things found in the Pasig River, Philippines. The performance of the model was trained and tested using the water hyacinths dataset. To further improve the ability of the model, the researchers applied augmentations, which enhanced the capacity and accuracy of the model in detecting the target object. Furthermore, the researchers optimized the capability of the YOLOv7 model in detecting floating objects on water surface through hyperparameter tuning. The researchers' optimized YOLOv7 model produced 91% mAP@50, 62% [email protected]:.95, 90% precision, 89% recall, and 90% F1 score. Given the results, the model can be integrated into devices to decrease the spread of water hyacinths and non-living things that can be found in every aquatic environment.
- Cris Gel Loui A. Arcadio 2022. Microplastics in surface water of laguna de bay: First documented evidence on the largest lake in the Philippines - environmental science and pollution research. (November 2022). Retrieved April 19, 2023 from https://link.springer.com/article/10.1007/s11356-022-24261-5Sam Anzaroot and Andrew McCallum. 2013. UMass Citation Field Extraction Dataset. Retrieved May 27, 2019 from http://www.iesl.cs.umass.edu/data/data-umasscitationfieldGoogle Scholar
- Drew Rabadon. 2022. Pasig River and the expressway: From the perspective of history. (May 2022). Retrieved January 23, 2023 from https://mb.com.ph/2022/05/21/pasig-river-and-the-expressway-from-the-perspective-of-history/Google Scholar
- B.R. MURPHY. Ecological and socio‐economic impacts of invasive water hyacinth . Retrieved April 19, 2023 from https://onlinelibrary.wiley.com/doi/full/10.1111/j.1365-2427.2009.02294.xGoogle Scholar
- Anon. Environmental impact. Retrieved January 23, 2023 from https://jacintoandlirio.com/pages/environmental-impactGoogle Scholar
- Mariclaire Miguel. Govph. Retrieved January 23, 2023 from https://www.denr.gov.ph/index.php/news-events/press-releases/1917-denr-tapping-fisherfolk-to-address-water-hyacinth-pollutionGoogle Scholar
- Minychl Dersseh. Water hyacinth. Retrieved January 23, 2023 from https://www.sciencedirect.com/topics/earth-and-planetary-sciences/water-hyacinth#:∼:text=Water%20hyacinth%20can%20completely%20cover,damage%20bridges%2C%20and%20clog%20dams.\Google Scholar
- Abdullah M. Algamdi and Hammam M. Alghamdi, "Instant Counting & Vehicle Detection during HajjUsing Drones," Journal of Image and Graphics, Vol. 11, No. 2, pp. 204-211, June 2023.Google Scholar
- Ying Liu, Luyao Geng, Weidong Zhang, Yanchao Gong, and Zhijie Xu, "Survey of Video Based Small Target Detection," Journal of Image and Graphics, Vol. 9, No. 4, pp. 122-134, December 2021. doi:10.18178/joig.9.4.122-134Google ScholarCross Ref
- Florian Spiess, Lucas Reinhart, Norbert Strobel, Dennis Kaiser, Samuel Kounev, and Tobias Kaupp, "People Detection with Depth Silhouettes and Convolutional Neural Networks on a Mobile Robot," Journal of Image and Graphics, Vol. 9, No. 4, pp. 135-139, December 2021. doi:10.18178/joig.9.4.135-139Google ScholarCross Ref
- Edisanter Lo, "Target Detection Algorithms in Hyperspectral Imaging Based on Discriminant Analysis," Journal of Image and Graphics, Vol. 7, No. 4, pp. 140-144, December 2019. doi: 10.18178/joig.7.4.140-144Google ScholarCross Ref
- Fitri Utaminingrum, Renaldi P. Prasetya, and Rizdania, "Combining Multiple Feature for Robust Traffic Sign Detection," Journal of Image and Graphics, Vol. 8, No. 2, pp. 53-58, June 2020. doi: 10.18178/joig.8.2.53-58Google ScholarCross Ref
- Ryo Hasegawa, Yutaro Iwamoto, and Yen-Wei Chen, "Robust Japanese Road Sign Detection and Recognition in Complex Scenes Using Convolutional Neural Networks," Journal of Image and Graphics, Vol. 8, No. 3, pp. 59-66, September 2020. doi: 10.18178/joig.8.3.59-66Google ScholarCross Ref
- Yukun Qian 2022. Real-time detection of Eichhornia crassipes based on efficient Yolov5. Machines 10, 9 (2022), 754. DOI:http://dx.doi.org/10.3390/machines10090754Google ScholarCross Ref
- Bingbing Zhang, Xiaojun Qian, Rui Yang, and Zhen Xu. 2021. Water surface target detection based on improved yolov3 in UAV images. 2021 9th International Conference on Communications and Broadband Networking (2021). DOI:http://dx.doi.org/10.1145/3456415.3456424Google ScholarDigital Library
- Feng Lin, Tian Hou, Qiannan Jin, and Aiju You. 2021. Improved yolo based detection algorithm for floating debris in waterway. Entropy 23, 9 (2021), 1111. DOI:http://dx.doi.org/10.3390/e23091111Google ScholarCross Ref
- Chien-Yao Wang, Alexey Bochkovskiy, and Hong-Yuan Mark Liao. 2022. Yolov7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors. (July 2022). Retrieved January 19, 2023 from https://arxiv.org/abs/2207.02696Google Scholar
- Delin Wu 2022. Detection of camellia oleifera fruit in complex scenes by using Yolov7 and data augmentation. Applied Sciences 12, 22 (2022), 11318. DOI:http://dx.doi.org/10.3390/app122211318Google ScholarCross Ref
- Yunhe Zhou 2022. Adaptive active positioning of Camellia oleifera fruit picking points: Classical image processing and Yolov7 Fusion algorithm. Applied Sciences 12, 24 (2022), 12959. DOI:http://dx.doi.org/10.3390/app122412959Google ScholarCross Ref
- Ignazio Gallo, Anwar Ur Rehman, Ramin Heidarian Dehkordi, Nicola Landro, Riccardo La Grassa, and Mirco Boschetti. 2023. Deep object detection of crop weeds: Performance of Yolov7 on a real case dataset from UAV images. Remote Sensing 15, 2 (2023), 539. DOI:http://dx.doi.org/10.3390/rs15020539Google ScholarCross Ref
- Irina Harun, Hafizah Pushiri, Ahmad Juhari Amirul-Aiman, and Zufarzaana Zulkeflee. 2021. Invasive water hyacinth: Ecology, impacts and prospects for the rural economy. Plants 10, 8 (2021), 1613. DOI:http://dx.doi.org/10.3390/plants10081613Google ScholarCross Ref
- Opeyemi I. Ayanda, Tolulope Ajayi, and Femi P. Asuwaju. 2020. eichhornia crassipes (mart.) Solms: Uses, challenges, threats, and prospects. The Scientific World Journal 2020 (2020), 1–12. DOI:http://dx.doi.org/10.1155/2020/3452172Google ScholarCross Ref
- Louise Schreyers 2021. Plastic plants: Water hyacinths as driver of plastic transport in Tropical Rivers. (2021). DOI:http://dx.doi.org/10.31223/x5gp5jGoogle ScholarCross Ref
- Bhakti Suprapto, Kelvin Kurniawan, Muhammad Ardela, Hera Hikmarika, Zainal Husin, and Suci Dwijayanti. 2021. Identification of garbage in the river based on the Yolo algorithm. (2021). Retrieved January 22, 2023 from https://www.journals.pan.pl/Content/121912/PDF/100_3225_Suprapto_skl1.pdf?handler=pdfGoogle Scholar
- Connor Shorten and Taghi M. Khoshgoftaar. 2019. A survey on image data augmentation for Deep Learning. Journal of Big Data 6, 1 (2019). DOI:http://dx.doi.org/10.1186/s40537-019-0197-0Google ScholarCross Ref
- Brahim Jabir, Noureddine Falih, and Khalid Rahmani. 2021. Accuracy and efficiency comparison of object detection open-source models. International Journal of Online and Biomedical Engineering (iJOE) 17, 05 (2021), 165. DOI:http://dx.doi.org/10.3991/ijoe.v17i05.21833Google ScholarCross Ref
Index Terms
- Detection of Water Hyacinth (Eichhornia crassipes) on the Water Surface of Pasig River, Philippines, through YOLOv7
Recommendations
Pantura Water Quality: Comparing the Pollution Distribution Model of Comal River and Garang River
ICBBB '18: Proceedings of the 2018 8th International Conference on Bioscience, Biochemistry and BioinformaticsSea is the estuary of rivers on land. In the sea all kind of pollutions carried by the river flow will be accumuated, which make the sea water quality worse than the river itself. Comal river and Garang river is two of the few river that flows into the ...
Water Environmental Capacity and Pollutant Sharing Rate Calculation Based on Water Diversion of Qinhuai River
IEEA '18: Proceedings of the 7th International Conference on Informatics, Environment, Energy and ApplicationsIn consideration the factors of hydrology, water quality and pollution sources, the pollution source area, which affect the water quality of basin, is divided into various control units. Based on the establishment of the water environmental model in ...
Water Quality Management Scenarios for the Love River in Taiwan
CESCE '10: Proceedings of the 2010 International Conference on Challenges in Environmental Science and Computer Engineering - Volume 01The Love River with a length of 16 km along the main stream and a catchment area of 62 km2 is an urban-type tidal stream and its estuary locates at the Kaohsiung Harbor in southern Taiwan. The majority of municipal wastewater directly discharged into ...
Comments