ABSTRACT
In 2020 Scaled-YOLOv4 was introduced. It is one of the best object detection models outclassing its peers in MS COCO test-dev. In this study, the proponents used Scaled-YOLOv4 as their object detection model. The model will be used in the environment of Pasig River, Philippines in detecting plastic and paper. The model's performance will be tested using a dilapidated trash dataset. Object detection models usually face difficulties in detecting the object because of deformation, occlusion, illumination conditions, and cluttered background. The proponents’ Scaled-YOLOv4 model produced 63% average precision, 67% precision for plastic, 59% precision for paper. The model can be used in detecting trash materials found on the surface of the Pasig River.
- Mia Rodriguez. 2020. The Revamped Pasig River Ferry System May Just Be the Secret to Beating Manila Traffic. https://www.spot.ph/newsfeatures/the-latest-news-features/80596/pasig-river-ferry-guide-a4362-20200116Google Scholar
- BusinessMirror. 2017. Pasig River 8th in Top 20 Polluting Rivers.Google Scholar
- https://businessmirror.com.ph/2017/09/17/pasig-river-8th-in-top-20-polluting-rivers/Google Scholar
- Pia Ranada. 2019. Duterte says Pasig River 'already clean,' wants river rehab body abolished. https://www.rappler.com/nation/duterte-wants-rehabilitation-body-abolished-pasig-river-already-cleanGoogle Scholar
- Mohbat Tharani, Abdul Wahab Amin, Mohammad Maaz and Murtaza Taj. 2020. Attention Neural Network For Trash Detection On Water Channels. https://arxiv.org/pdf/2007.04639.pdfGoogle Scholar
- Alexey Bochkovskiy, Chien-Yao Wang, Hong-Yuan Mark Liao. 2020. YOLOv4: Optimal Speed and Accuracy of Object Detection. https://arxiv.org/pdf/2004.10934.pdfGoogle Scholar
- Chien-Yao Wang, Alexey Bochkovskiy, Hong-Yuan Mark Liao. 2021. Scaled-YOLOv4: Scaling Cross Stage Partial Network. https://arxiv.org/pdf/2011.08036.pdfGoogle Scholar
- Harsh Panwar, P.K. Gupta, Mohammad Khubeb Siddiqui, Ruben Morales-Menendez, Prakhar Bhardwaj, Sudhansh Sharma, Iqbal H. Sarker. 2020. AquaVision: Automating the detection of waste in water bodies using deep transfer learning. Case Studies in Chemical and Environmental Engineering, Volume 2, 2020, 100026, ISSN 2666-0164, https://doi.org/10.1016/j.cscee.2020.100026.Google Scholar
- Joseph Redmon, Ali Farhadi. 2018. YOLOv3: An Incremental Improvement. arXiv:1804.02767Google Scholar
- van Lieshout, C., van Oeveren, K., van Emmerik, T., & Postma, E. 2020. Automated river plastic monitoring using deep learning and cameras. Earth and Space Science, 7, e2019EA000960. https://doi.org/10.1029/2019EA000960Google Scholar
- Lili Zhang, Yi Zhang, Zhen Zhang, Jie Shen, Huibin Wang. 2019. Real-Time Water Surface Object Detection Based on Improved Faster R-CNN. https://doi.org/10.3390/s19163523Google Scholar
- Mattis Wolf, Katelijn van den Berg, Shungudzemwoyo P Garaba, Nina Gnann, Klaus Sattler, Frederic Stahl and Oliver Zielinski. 2020. Machine learning for aquatic plastic litter detection, classification and quantification (APLASTIC-Q). https://doi.org/10.1088/1748-9326/abbd01Google Scholar
- Leah Sherwood. 2020. Applying Object Detection To Monitoring Marine Debris. https://dspace.lib.hawaii.edu/bitstream/10790/5298/Sherwood_hilo.hawaii_1418O_10183.pdfGoogle Scholar
- Sudan Jha, Changho Seo, Eunmok Yang & Gyanendra Prasad Joshi. 2020. Real time object detection and trackingsystem for video surveillance system. Multimed Tools Appl 80, 3981–3996 (2021). https://doi.org/10.1007/s11042-020-09749-xGoogle ScholarDigital Library
- Carolis, Berardina & Ladogana, Francesco & Macchiarulo, Nicola. 2020. YOLO TrashNet: Garbage Detection in Video Streams. 1-7. 10.1109/EAIS48028.2020.9122693.Google Scholar
- Rumana Sultana. 2020. Trash And Recyclable Material Identification Using Convolutional Neural Networks (Cnn). https://core.ac.uk/download/pdf/345094494.pdfGoogle Scholar
- Aghilan M, Arun Kumar M, Mohammed Aafrid TS, Nirmal Kumar A, S.Muthulakshmi. 2020. Garbage Waste Classification Using Supervised Deep Learning Techniques. IJETIE Vol. 6, Issue 3, March 2020, Available at SSRN: https://ssrn.com/abstract=3563564Google Scholar
- Anbang Ye, Bo Pang, Yucheng Jin, Jiahuan Cui. 2020. A YOLO-based Neural Network with VAE for Intelligent Garbage Detection and Classification. https://doi.org/10.1145/3446132.3446400Google ScholarDigital Library
- Minjun Yu, 2020. Study on yolov5 based on garbage target detection task.Google Scholar
- https://developpaper.com/study-on-yolov5-based-on-garbage-target-detection-task/Google Scholar
- L. Zheng, C. Fu and Y. Zhao. 2018. Extend the shallow part of single shot multibox detector via convolutional neural network. https://doi.org/10.1117/12.2503001Google Scholar
- Y. Pang, T. Wang, R. M. Anwer, F. S. Khan, and L. Shao. 2019. Efficient featurized image pyramid network for single shot detector. IEEE/CVF Conference on Computer Vision and Pattern Recognition. https://ezproxy.mapua.edu.ph:2068/document/8953326Google Scholar
- Shu Liu, Lu Qi, Haifang Qin, Jianping Shi, and Jiaya Jia. Path aggregation network for instance segmentation. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 8759–8768, 2018.Google ScholarCross Ref
- Jacob Solawetz, Joseph Nelson, Matt Brems. 2020. Scaled-YOLOv4 is Now the Best Model for Object Detection. https://blog.roboflow.com/scaled-yolov4-tops-efficientdet/Google Scholar
- Google. What kinds of GPUs are available in Colab Pro and Pro+? https://colab.research.google.com/signupGoogle Scholar
- Jacob Solawetz. 2020. How to Train Scaled-YOLOv4 to Detect Custom Objects. https://towardsdatascience.com/how-to-train-scaled-yolov4-to-detect-custom-objects-13f9077ebc89Google Scholar
- Kin-Yiu, Wong. 2020. Scaled YOLOv4. https://github.com/WongKinYiu/ScaledYOLOv4Google Scholar
- 6 Obstacles to Robust Object Detection. 2020. https://towardsdatascience.com/6-obstacles-to-robust-object-detection-6802140302efGoogle Scholar
- Tripathi, Akash & Kumar, T.V. & Dhansetty, Tarun & Kumar, J.. 2018. Real Time Object Detection using CNN. International Journal of Engineering and Technology(UAE). 7. 33-36. 10.14419/ijet.v7i2.24.11994.Google ScholarCross Ref
- Sai Krishna Chadalawada. 2020. Real Time Object Detection and Recognition Using Deep Learning Methods. https://www.diva-portal.org/smash/get/diva2:1414033/FULLTEXT02Google Scholar
- P. Devaki, S. Shivavarsha, G. Bala Kowsalya, M. Manjupavithraa, E.A. Vima. 2019. Real-Time Object Detection using Deep Learning and Open CV. International Journal of Innovative Technology and Exploring Engineering. .https://www.ijitee.org/wp-content/uploads/papers/v8i12S/L110310812S19.pdfGoogle Scholar
- Queensland Government. 2018. Garbage Pollution. https://www.msq.qld.gov.au/Marine-pollution/Garbage-pollutionGoogle Scholar
- Division of Boating and Waterways. 2018. Trash and Marine Debris. https://dbw.parks.ca.gov/?page_id=29246#:∼:text=Marine%20debris%20can%20wrap%20around,cause%20suffocation%20and%2For%20starvation.Google Scholar
- Ayesha Younis, Li Shixin, Shelembi Jn, and Zhang Hai. 2020. Real-Time Object Detection Using Pre-Trained Deep Learning Models MobileNet-SSD. Proceedings of 2020 the 6th International Conference on Computing and Data Engineering. Association for Computing Machinery, New York, NY, USA, 44–48. DOI:https://ezproxy.mapua.edu.ph:2062/10.1145/3379247.3379264Google ScholarDigital Library
- Roboflow. https://docs.roboflow.com/Google Scholar
- Google. Classification: True vs. False and Positive vs. Negative. https://developers.google.com/machine-learning/crash-course/classification/true-false-positive-negativeGoogle Scholar
- The University of Waikato Te Whare Wānanga o Waikato. Reflection of light. https://www.sciencelearn.org.nz/resources/48-reflection-of-lightGoogle Scholar
- Felix Abramovich, Marianna Pensky. 2019. Classification with many classes: challenges and pluses. DOI: https://arxiv.org/pdf/1506.01567.pdfGoogle Scholar
- Alex Thevenot. 2020. Image Augmentation Mastering: 15+ Techniques and Useful Functions with Python Codes. https://towardsdatascience.com/image-augmentation-mastering-15-techniques-and-useful-functions-with-python-codes-44c3f8c1ea1fGoogle Scholar
- Koo Ping Shung. 2018. Accuracy, Precision, Recall or F1?. https://towardsdatascience.com/accuracy-precision-recall-or-f1-331fb37c5cb9Google Scholar
Recommendations
Trash Detection on Water Channels
Neural Information ProcessingAbstractRivers and canals flowing through cities are often used illegally for dumping trash that contaminates freshwater channels, causes blockage in sewerage leading to urban flooding. The dumped trash is often found floating on the water surface. We ...
Computer Vision Based Method to Detect Fire with Color Variation in Temporal Domain
SITIS '14: Proceedings of the 2014 Tenth International Conference on Signal-Image Technology and Internet-Based SystemsBecause of false detection rate, many fire detection algorithm cannot easily become a part of alarm monitoring system, so in this paper, we proposed to detect fire precisely with color variation in temporal domain to reduce false detection rate. By ...
Introduction to Computer Vision and Realtime Deep Learning-based Object Detection
CIKM '20: Proceedings of the 29th ACM International Conference on Information & Knowledge ManagementThe main focus of object detection, one of the most challenging problems in computer vision (CV), is to predict a set of bounding boxes and category labels for each object of interest in an image or in a point cloud. As such, object detection has a ...
Comments