Curupira Project: A Platform for Intelligent Monitoring of Waste in Amazon Rivers

  • Rodrigo Choji de Freitas Universidade do Estado do Amazonas
  • Neide Ferreira Alves Universidade do Estado do Amazonas
  • Ramayana Assunção Menezes Universidade do Estado do Amazonas
  • Andrea Monicque dos Santos Silva Universidade do Estado do Amazonas
  • Beatriz Martires Paes Instituto Federal do Amazonas
  • Fabio Santos da Silva Universidade do Estado do Amazonas
  • Luiz Fabio Bailosa Alencar Universidade do Estado do Amazonas
  • Mario Guilherme Carvalho Instituto Federal do Amazonas
  • Matheus Miranda Matos Universidade do Estado do Amazonas
  • Tiago Ramos de Sá Universidade do Estado do Amazonas
  • Victor Brasil de Pina Universidade do Estado do Amazonas
  • Victor Yan Pereira Lima Universidade do Estado do Amazonas
  • Carlossandro Carvalho Albuquerque Universidade do Estado do Amazonas
  • José Reginaldo Hughes Carvalho Universidade Federal do Amazonas


Context: River pollution is a critical socio-environmental problem that has shown exponential growth over the last few years, causing numerous global problems.Problem: The inadequate disposal of garbage in the rivers located in the Amazon region has caused the worsening of the degradation of the environment, affecting from the urban population to the riverside.Solution: A solution based on Computer Vision techniques is proposed for intelligent monitoring of the degradation of tributaries in the Amazon, where methods for detecting and quantifying the incidence of surface garbage are contemplated.IS Theory: This work was conceived under the aegis of the General Theory of Systems, in particular with regard to the interactions between the parts of a system. In this case, the parts are system-environment, input, output, process, state, hierarchy, goal-direction and information.Method: Aerial image data is captured by a drone camera and the image classification is done through Digital Processing Images and CNN algorithms. Then, degradation data is displayed on a web plataform, with analytics tools such as dashboards and heatmaps.Summary of Results: From the results, it is possible to highlight the Curupira platform, which has a geographic and temporal mapping system for the location of garbage in streams, based on a CNN network with 97% accuracy in detecting garbage in aerial images.Contributions and Impact in the IS area: The use of emerging technologies in IS combats the inappropriate disposal of waste in rivers, also helping in decision-making by stakeholders in the problem. Methods are established to deal with IS challenges from the perspective of sustainability, technologically impacting the Sustainable Development Goals in Brazil, as well as promoting IS for a more Humane World.
Palavras-chave: Deep Learning, Computer Vision, Waste in Rivers


M.K.O. Ayomoh, S.A. Oke, W.O. Adedeji, and O.E. Charles-Owaba. 2008. An approach to tackling the environmental and health impacts of municipal solid waste disposal in developing countries. Journal of Environmental Management 88, 1 (2008), 108–114.

Sarah Barns. 2018. Smart cities and urban data platforms: Designing interfaces for smart governance. City, Culture and Society 12 (2018), 5–12. Innovation and identity in next generation smart cities.

Darrel John Beltran, Yves Kangleon, Ariel Kelly Balan, and Joel De Goma. 2021. Credit card sales performance dashboard. In Proceedings of the International Conference on Industrial Engineering and Operations Management. 1–12. 

Odemar Jose Santos Carmo, Adoréa Rebelo da Cunha Albuquerque, and Jean Claudio Campos Oliveira. 2021. Bacias hidrográficas urbanas: O reflexo da precarização do saneamento em Manaus, Amazonas–Brasil.Ateliê Geográfico 15, 2 (2021), 70–93. 

Rafael Carvalho and Claudia Melo. 2018. Tomada de decisão baseada em dados: avaliando a visualização de informação em dash boards. In Anais Estendidos do XIV Simpósio Brasileiro de Sistemas de Informação (Caxias do Sul). SBC, Porto Alegre, RS, Brasil, 24–27.

Paulina Chamorro. 2021. Poluição invisível nas águas amazônicas ameaça populações e biodiversidade. Retrieved Janeiro 20, 2022 from [link].

Yinghao Chu, Chen Huang, Xiaodan Xie, Bohai Tan, Shyam Kamal, and Xiaogang Xiong. 2018. Multilayer hybrid deep-learning method for waste classification and recycling. Computational Intelligence and Neuroscience 2018 (2018). 

Josiel de Alencar Guedes. 2011. Poluição de rios em áreas urbanas - DOI 10.5216/ag.v5i2.15488. Ateliê Geográfico 5, 2 (ago. 2011), 212–226.

Jungseok Hong, Michael Fulton, and Junaed Sattar. 2020. Trashcan: A semantically-segmented dataset towards visual detection of marine debris. arXiv preprint arXiv:2007.08097(2020). 

K. Kylili, I. Kyriakides, A. Artusi, and C. Hadjistassou. 2019. Identifying floating plastic marine debris using a deep learning approach. Environmental Science and Pollution Research 2019 (2019). 

Ricardo Matheus, Marijn Janssen, and Devender Maheshwari. 2020. Data science empowering the public: Data-driven dashboards for transparent and accountable decision-making in smart cities. Government Information Quarterly 37, 3 (2020), 101284.

Fernandes Mayra, Fernanda Teodoro, Isabella Araújo, Renata Paschoalini, Maria Macedo, and Araújo. 2019. Descarte inadequado de lixo e seu impacto no meio ambiente e na saúde da comunidade. Anais Colóquio Estadual de Pesquisa Multidisciplinar & Congresso Nacional de Pesquisa Multidisciplinar (Nov 2019).

Guanchong Niu, Jie Li, Sheng Guo, Man-On Pun, Leo Hou, and Lujian Yang. 2019. SuperDock: A deep learning-based automated floating trash monitoring system. In 2019 IEEE international conference on robotics and biomimetics (ROBIO). IEEE, 1035–1040. 

Antônia Gomes Neta Pinto, Adriana Maria Coimbra Horbe, Maria do Socorro Rocha da Silva, Sebastião Atila Fonseca Miranda, Domitila Pascoaloto, and Helder Manuel da Costa Santos. 2009. Efeitos da ação antrópica sobre a hidrogeoquímica do rio Negro na orla de Manaus/AM. Acta amazonica 39(2009), 627–638. 

Pedro F. Proenca and Pedro Simoes. 2020. TACO: Trash Annotations in Context for Litter Detection. (2020). arxiv:2003.06975 [cs.CV] 

Joseph Redmon and Ali Farhadi. 2017. YOLO9000: better, faster, stronger. In Proceedings of the IEEE conference on computer vision and pattern recognition. 7263–7271. 

Olga Russakovsky, Jia Deng, Hao Su, Jonathan Krause, Sanjeev Satheesh, Sean Ma, Zhiheng Huang, Andrej Karpathy, Aditya Khosla, Michael Bernstein, Alexander C. Berg, and Li Fei-Fei. 2015. ImageNet Large Scale Visual Recognition Challenge. International Journal of Computer Vision (IJCV) 115, 3 (2015), 211–252.

Isabella Siqueira/ Semulsp. 2021. Mais de 20 toneladas de lixo são retiradas do igarapé do São Jorge, pela prefeitura. Retrieved Janeiro 20, 2022 from [link].

Ayushi Shukla and Saru Dhir. 2016. Tools for data visualization in business intelligence: case study using the tool Qlikview. In Information Systems Design and Intelligent Applications. Springer, 319–326. 

Christian Szegedy, Wei Liu, Yangqing Jia, Pierre Sermanet, Scott Reed, Dragomir Anguelov, Dumitru Erhan, Vincent Vanhoucke, and Andrew Rabinovich. 2015. Going deeper with convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition. 1–9. 

Mohbat Tharani, Abdul Wahab Amin, Mohammad Maaz, and Murtaza Taj. 2020. Attention Neural Network for Trash Detection on Water Channels. arXiv preprint arXiv:2007.04639(2020). 

Roman A. Vila, Elsa Estevez, and Pablo R. Fillottrani. 2018. The Design and Use of Dashboards for Driving Decision-Making in the Public Sector. In Proceedings of the 11th International Conference on Theory and Practice of Electronic Governance (Galway, Ireland) (ICEGOV ’18). Association for Computing Machinery, New York, NY, USA, 382–388.

Jinwang Wang, Wei Guo, Ting Pan, Huai Yu, Lin Duan, and Wen Yang. 2018. Bottle Detection in the Wild Using Low-Altitude Unmanned Aerial Vehicles. In 2018 21st International Conference on Information Fusion (FUSION). 439–444.

Wikipedia contributors. 2022. F-score — Wikipedia, The Free Encyclopedia. [Online; accessed 19-March-2022].

Wikipédia. 2017. Precisão e revocação — Wikipédia, a enciclopédia livre. [link]. [Online; accessed 22-julho-2017].

Wikipédia. 2020. Validação cruzada — Wikipédia, a enciclopédia livre. [link]. [Online; accessed 8-agosto-2020].

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). Environmental Research Letters 15, 11 (2020), 114042. 
Como Citar

Selecione um Formato
DE FREITAS, Rodrigo Choji et al. Curupira Project: A Platform for Intelligent Monitoring of Waste in Amazon Rivers. In: SIMPÓSIO BRASILEIRO DE SISTEMAS DE INFORMAÇÃO (SBSI), 18. , 2022, Curitiba. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2022 .

Artigos mais lidos do(s) mesmo(s) autor(es)