TOD: Trash Object Detection Dataset
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
In this paper, we produce Trash Object Detection (TOD) dataset to solve trash detection problems. A wellorganizeddataset of sufficient size is essential to train object detection models and apply them to specific tasks. However, existing trash datasets have only a few hundred images, which are not sufficient to train deep neuralnetworks. Most datasets are classification datasets that simply classify categories without location information. In addition, existing datasets differ from the actual guidelines for separating and discharging recyclables becausethe category definition is primarily the shape of the object. To address these issues, we build and experiment withtrash datasets larger than conventional trash datasets and have more than twice the resolution. It was intendedfor general household goods. And annotated based on guidelines for separating and discharging recyclablesfrom the Ministry of Environment. Our dataset has 10 categories, and around 33K objects were annotated foraround 5K images with 1280×720 resolution. The dataset, as well as the pre-trained models, have been releasedat https://github.com/jms0923/tod.
Abstract
In this paper, we produce Trash Object Detection (TOD) dataset to solve trash detection problems. A wellorganizeddataset of sufficient size is essential to train object detection models and apply them to specific tasks. However, existing trash datasets have only a few hundred images, which are not sufficient to train deep neuralnetworks. Most datasets are classification datasets that simply classify categories without location information. In addition, existing datasets differ from the actual guidelines for separating and discharging recyclables becausethe category definition is primarily the shape of the object. To address these issues, we build and experiment withtrash datasets larger than conventional trash datasets and have more than twice the resolution. It was intendedfor general household goods. And annotated based on guidelines for separating and discharging recyclablesfrom the Ministry of Environment. Our dataset has 10 categories, and around 33K objects were annotated foraround 5K images with 1280×720 resolution. The dataset, as well as the pre-trained models, have been releasedat https://github.com/jms0923/tod.
참고문헌 (20)
- G. E. Sakr, "Comparing deep learning and support vector machines for autonomous waste sorting", Proceedings of 2016 IEEE International Multidisciplinary Conference on Engineering Technology (IMCET), pp.207~212 (2016)
- Yinghao Chu, "Multilayer Hybrid Deep-Learning Method for Waste Classification and Recycling", Computational Intelligence and Neuroscience, 2018, pp.1~9 (2018), Hindawi Limited[DOI]
- Y. Liao, "A web-based dataset for garbage classification based on Shanghai’s rule", International Journal of Machine Learning and Computing, 10(4), pp.599~604 (2020)
- P. Zhang, "Urban street cleanliness assessment using mobile edge computing and deep learning", IEEE Access, 7, pp.63550~63563 (2019)
- G. Mittal, "Spotgarbage: smartphone app to detect garbage using deep learning", Proceedings of the 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing, pp.940~945 (2016)
- M. S. Rad, "Computer Vision Systems", pp.195~204 (2017), Springer
- W. Liu, "SSD: single shot multibox detector", Computer Vision – ECCV 2016, pp.21~37 (2016)
- "Very deep convolutional networks for large-scale image recognition" (2014)[URL]
- "YOLOv3: an incremental improvement" (2018)[URL]
- J. Redmon, "You only look once: unified, real-time object detection", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.779~788 (2016)
- J. Redmon, "YOLO9000 : better, faster, stronger", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.6517~6525 (2017)
- Z. Cai, "Cascade R-CNN : delving into high quality object detection", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.6154~6162 (2018)
- S. Ren, "Faster R-CNN : towards real-time object detection with region proposal networks", Advances in Neural Information Processing Systems, 28, pp.91~99 (2015)
- Kisang Kim, "Object detection using ensemble of linear classifiers with fuzzy adaptive boosting", EURASIP Journal on Image and Video Processing, 2017(1) (2017), Springer Science and Business Media LLC[DOI]
- Jinlong Zhu, "Classroom Roll-Call System Based on ResNet Networks", JIPS(Journal of Information Processing Systems), 16(5), pp.1145~1157 (2020), 한국정보처리학회[DOI]
- Divakar Yadav, "Optical Character Recognition for Hindi Language Using a Neural-network Approach", JIPS(Journal of Information Processing Systems), 9(1), pp.117~140 (2013), 한국정보처리학회[DOI]
- Junqiu Wang, "Shadow extraction and application in pedestrian detection", EURASIP Journal on Image and Video Processing, 2014(1) (2014), Springer Science and Business Media LLC[DOI]
- Wan Mimi Diyana Bt Wan Zaki, "Moving object detection using keypoints reference model", EURASIP Journal on Image and Video Processing, 2011(1) (2011), Springer Science and Business Media LLC[DOI]
- T. Y. Lin, "Microsoft coco: common objects in context", computer vision – ECCV 2014, pp.740~755 (2014)
- K. He, "Deep residual learning for image recognition", Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.770~778 (2016)