Let’s create a ripple effect of change by harnessing the power of AI to protect our rivers and water bodies. Participate in this exciting AI Hackathon and help us positively impact the environment. The goal of this Hackathon is to create new technologies and strategies to reduce plastic waste and create healthier and more sustainable rivers and oceans. This Hackathon is aligned with Sustainable Development Goals – SDG 14 life below water, conserving and sustainably using marine resources.
Hackathon Winners
WIN BIG!
Cash prizes and Exciting Swags
Our hackathon offers a chance to not only showcase your skills, but also win big!
NOTE: TDS & currency exchange rates will be in accordance with the prevailing regulations and rates at the time of payment.
Plastic Pandemic: How Plastics Are Invading Our Environment?
Plastic pollution has become a major environmental issue, as it can take decades or even centuries to decompose. This poses a serious threat to our water supplies and quality, as plastic waste from discarded water bottles, polystyrene coffee cups, grocery bags, and synthetic clothing fibres breaks down into tiny microplastics that can contaminate water sources.
BE AN ECO WARRIOR!
Save the rivers by participating in this Hackathon.
The challenge is to detect, classify, and segment the plastics in the given dataset and propose a viable and architecturally sound AI solution to curtail the plastic menace choking our rivers. The solutions must have actionable insights where the stakeholders, like the government and local support groups, can take preventive and proactive measures.
The dataset for this challenge is extracted from the images taken by drones across the river Saigon*. Large patches of several meters of water weeds (hyacinths) can entrain and aggregate large amounts of floating debris, including plastic items. The participants have to build an AI based end-to-end solution to detect the plastic menace. Your solution will help the local authorities to know the plastic density in planning the cleaning schedules and resources.
Check out an alarming video on the Great Pacific Garbage Patch covering an estimated surface area of 1.6 million square kilometres posted by The Ocean Cleanup group.
*Citation: Schreyers, L. (Creator), Bui, T. K. L. (Creator), van Emmerik, T. (Creator) (1 Dec 2022). Drone images over the Saigon river – Hyacinth & Plastic patches. Wageningen University & Research. 10.4121/21648152
Hackathon Timeline
This Hackathon has two phases culminating in a grand finale. Phase I is to build AI models to detect and counting the plastic in the given images. In Phase II, the shortlisted entries must submit the final prototype and architecture to detect the plastic. Shortlisted 10 entries would receive mentorship from industry thought leaders leading to a grand finale.
Registration Opens
9th June 2023
Phase I
Model Building
9th June to 9th July 2023
Phase I Results
20th July 2023
Phase II
Prototype Submission
25th July to 05th August 2023
Phase II Results
10th August 2023
Mentorship to
the Top 10
16th August to 5th September 2023
Grand Finale
8th September 2023
Phase I: Model building
Detection and Counting of Plastic
- Label the images for plastic. Accurate labeling is part of the Hackathon challenge.
- AI-based object detection and counting of plastic in the images.
- Geotagging and mapping of plastic.
- Submit the results.
Phase II: Prototype submission
Feasible Solution and System Architecture
- Demonstrate and deploy a feasible solution with system architecture for implementation. Show tech stack, dashboards and downstream actions which trigger a set of events for the detection and estimation of plastic and weeds.
- Submit a prototype or an MVP.
Open Innovation Challenge
For special jury award
- Build a spatiotemporal model capturing the metadata available in the images, including Latitude and Longitude, to detect moving and stationary plastic, weeds and other debris in the images.
- You may use any state-of-the-art algorithms to build efficient solutions to detect and curb the plastic menace, which can help local authorities to take intelligent actions. Build a solution to identify the severity of the menace and develop an early intervention and warning system.
Who can Participate?
AI Developers | AI Architects | Data Scientists |
AI Enthusiasts | ML Engineers | Programmers |
Freelancers | Students.
NOTE: Individuals and teams of maximum 4 members can participate.
Related Videos
Judging Criteria
Technical Criteria:
- Evaluation metric: Mean Average Precision (mAP) confidence interval for the validation data set or any other equivalent metrics.
- Code quality – Codes must be well-commented and clear.
- Optimisation – The code must be efficient, use the least possible memory or disk space, and minimise resources like GPU and network bandwidth.
Non-technical Criteria:
- Replicable –The solutions must be easily replicable by the evaluation team.
- Clarity – The architecture and the solution presented must be clear and comprehensive.
- Impact – A solution that provides actionable solutions to control the plastic menace in scale is appreciated.
Our Judges
About us
Kyndryl (NYSE: KD) is the world’s largest IT infrastructure services provider, serving thousands of enterprise customers in more than 60 countries. The company designs, builds, manages and modernizes the complex, mission-critical information systems that the world depends on every day. For more information, visit www.kyndryl.com.
For information on Data and AI Services visit https://www.kyndryl.com/in/en/services/data.
REVA Academy for Corporate Excellence (RACE) aims to develop visionary enterprise leaders for corporates through progressive and integrated learning capabilities. RACE offers best in class, specialized, techno-functional and interdisciplinary programs designed to suit the needs of working professionals.
Each of the programs is planned, designed and delivered by renowned corporate leaders and trainers and combines latest tools, technologies and skill sets which are in sync with the futuristic demands of the industry.
Frequently Asked Questions
- Anyone, corporate teams, individuals, startups, veterans, and academia with a promising idea towards plastic menace and the tenacity to implement their concept can apply.
- It is an online hackathon, and you can participate from anywhere.
- The hackers must register in a team of a maximum of four members (no minimum). While registering, all members must share their profiles.
- All participants/team are expected to submit their final ideas in a PowerPoint Presentation (PPT) format along with code. Refer to the submission rules mentioned.
- The Idea (Phase I) of this hackathon will be open from the 9th of June 2023 till the 9th of July 2023. The submission window will close by 11.59 PM on the 9th of July 2023.
- This hackathon’s prototype (Phase II) will be open to only short-listed submissions (watch out for the website and corresponding mail for intimation). The timeline to submit the final prototype with code and slide deck is 11.59 PM on 30th July 2023.
- The submitted solution must be original; if found plagiarised, the submission will be disqualified.
- The teams may use open-source libraries and other freely available systems like labeling tools, GPU with Google Collab, Data Bricks, etc.
- If any of the Teams would want GPU support from the University, you may approach us.
- For labeling the images, you may use free tools like labelImg or CVAT.
- The intellectual property of your submissions belongs to Kyndryl.
- AI Developers, AI Enthusiasts, Data Scientists, ML Engineers, Programmers, freelancers, students etc, can participate.
- Participants must have experience with object detection models and frameworks, such as YOLO, TensorFlow Object Detection API, or OpenCV.
- Participants must have a good understanding of image processing techniques and deep learning algorithms.
- Participants should demonstrate their ability to implement and fine-tune object detection models for real-world applications.
- Participants must be familiar with data annotation and cleaning techniques.
- Participants should have experience in programming languages such as Python.
- They must be able to work collaboratively in teams and communicate effectively.
- They must be able to submit a detailed report, codes, and relevant files.
- Participants should have a strong passion for creating innovative solutions to tackle the global plastic waste problem.
AI Solutions to Tackle the Plastic Menace: The Hackathon is on detecting plastic in water bodies like rivers of select locales. The participants of the Hackathon would have to detect, classify, and segment the plastics in the given dataset and propose a viable and architecturally sound AI solution to curtail the plastic menace choking the water bodies like rivers, preventing them to be taken into the sea and contributing to some of the garbage patches like Pacific Patch. The solutions must have actionable insights where the stakeholders, like the government and local support groups, can take preventive or proactive measures.
The problem statement of this hackathon is to develop a reliable and efficient AI-based object detection algorithm using images captured via drones to detect plastic waste in rivers and other water bodies and, in turn, to reduce the negative impact of plastic pollution on the environment and human health.
The metadata of the UAV images includes geo-location information. The images are taken at an elevation approximately 10m above the water level.
Guidelines for Building an AI Model on Object Detection
- Participants are required to label the data on their local system before training. You will need to annotate the images using an annotation tool such as Labelimg/CVAT.
- You may use any open GPU systems like Google Colab/Data Bricks/Cloud platforms for training the models.
- Train and test datasets are provided, and it is important to use the training set exclusively for training the model, while the test set should be used for testing the model. Register here to download the data set.
- Organize your object detection algorithm’s folder structure, including folders for training, testing, and any data configuration files that may be necessary while submitting.
- Maintain clean coding practices, including proper inline comments, which must be followed.
- The code should effectively detect plastic waste and provide its geo-location as a URL link.
- The model’s mean average precision, commonly referred to as mAP, needs to be a minimum of 65%.
- The estimated effort to tackle this data challenge is around 40 hours.
Instructions for Submission:
- Submit the complete model with a folder structure that adheres to the instructions
- Include Jupyter Notebook or Python file used for training, as well as a requirements.txt file, also in ONNX format
- Zip and submit all in the given link.
- Submit the presentation deck as per the template given.
- Submit the video explaining the approach and solution.
Dataset information
Citation: Schreyers, L. (Creator), Bui, T. K. L. (Creator), van Emmerik, T. (Creator) (1 Dec 2022). Drone images over the Saigon river – Hyacinth & Plastic patches. Wageningen University & Research. 10.4121/21648152
- UAV (Unmanned Aerial Vehicle) images taken over the Saigon river, Vietnam, between December 2020 and January 2021
- The dataset is comprised of a total of 3,688 UAV images, all in a .jpg format
- Contact: Louise Schreyers, Wageningen University and Research, louise.schreyers@wur.nl
Methodological information
All UAV images were taken over the Saigon river, Vietnam. UAV images were taken across the river channel, with a frequency of one to four flights per measurement day. Each flight consisted of two overpasses across the Saigon river, with a range of 41 to 65 images taken per flight. UAV surveys were carried at a constant elevation of approximately 10 m above the water level.
The dataset is organized in subfolders by date and flight.
Sharing and access information
This dataset is placed under the license Attribution-ShareAlike 4.0 International (CC BY-SA 4.0).
You are free to: Share — copy and redistribute the material in any medium or format, Adapt — remix, transform, and build upon the material for any purpose, even commercially.
Under the following terms:
Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
ShareAlike — If you remix, transform, or build upon the material, you must distribute your contributions under the same license as the original.
Still have queries?
Contact Us on Discord, a dedicated channel to communicate with other participants, mentors and AI experts.
You can also reach out to us at AIHackathon@race.reva.edu.in or +91 89040 58866