Abstract

1. Introduction

The agricultural sector nowadays is facing a lot of manpower issues as it has a lower income compared with other sectors. By using AI/ML in agriculture we can eliminate financial losses and increase agricultural yield. For every crop, farmers have to bear a larger amount of loss due to pests, animal intervention with the crops, as well as the inaccurate choice of crop. Every time a farmer cannot identify the diseases with naked eyes accurately. Approaching agriculture experts is not always financially feasible.

One of the most important tasks in agriculture is the proper identification of plant diseases and the timely application of the necessary pesticide, but not every farmer has the financial means to consult an agricultural specialist or can they themselves detect the disease accurately. But with the help of AI/ML techniques we can identify the disease at the earliest stage possible and by using certain features we have trained a ML model which can predict the proper crop for the available conditions. By using AR which is the emerging technology we can showcase the visuals of future developments.

2. Background   

3. Project Work

Agriculture, which provides the majority of the world's food, faces challenges due to population growth and modernization. Inconsistent income has led many people to switch to other occupations, impacting agricultural production. Demand for food is expected to continue growing, with projections of 3 billion tons of cereal demand by 2050. Cereal and meat production will need to increase significantly to meet this demand, with 72 percent of meat consumed in developing countries. The predicted population growth will lead to a massive food shortage worldwide.

We've integrated a border surveillance system, crop prediction system, plant disease detection system, and for visualizing futuristic developments we have implemented augmented reality using Raspberry Pi-4.

Tools Used 
1.CNN based mobilenetv1 neural network for BORDER SURVEILLANCE
2.The Random Forest algorithm for crop prediction
3.CNN based Keras Sequential models for disease detection

4. Result

5. Conclusion

AR is an unexplored subject yet we know there are many uses with every field. Disease detection and crop recommendation are already explored fields, but with automation we can reduce human intervention. In near future we can explore water level in plants and warn farmer for watering the plants.

Integration of multi-modal data: Agricultural drones can benefit from the integration of multi-modal data from various sources, such as satellite imagery, weather data, and ground-based sensors. AI algorithms can be developed to effectively fuse and analyze these data streams, providing farmers with a comprehensive and holistic view of their crops. AR overlays can then be generated based on these integrated data, providing farmers with actionable insights and recommendations for optimizing their farming operations

6. Acknowledgement

7. References

I would like to thank my teachers, Prashant Pal, Shashank Kumar, Surya Charan, and Saurabh Bhansod, for their guidance and support in completing my project and research paper on "AI, AR Enabling on Embedded systems for Agricultural Drones" Their expertise and encouragement were invaluable in shaping my understanding of the topic. I am also grateful to my colleagues and peers who provided feedback and suggestions, improving the project's quality. Lastly, I thank the institutions and organizations that provided resources and infrastructure for the research. Thank you all for contributing to the successful completion of this project and the publication of the research paper. 

1. S. Shilaskar et al., "Artificial Intelligence based Crop Recommendation and Plant Leaf Disease Detection System," 2022 3rd International Conference for Emerging Technology (INCET), 2022, pp. 1-6, doi: 10.1109/INCET54531.2022.9824002.
2. G. Chauhan and A. Chaudhary, "Crop Recommendation System using Machine Learning Algorithms," 2021 10th International Conference on System Modeling & Advancement in Research Trends (SMART), 2021, pp. 109-112, doi: 10.1109/SMART52563.2021.9676210.
3. S. M. PANDE, P. K. RAMESH, A. ANMOL, B. R. AISHWARYA, K. ROHILLA and K. SHAURYA, "Crop Recommender System Using Machine Learning Approach," 2021 5th International Conference on Computing Methodologies and Communication (ICCMC), 2021, pp. 1066-1071, doi: 10.1109/ICCMC51019.2021.9418351.
4. D. P. C. Peters, A. Rivers, J. L. Hatfield, D. G. Lemay, S. Liu and B. Basso, "Harnessing AI to Transform Agriculture and Inform Agricultural Research," in IT Professional, vol. 22, no. 3, pp. 16-21, 1 May-June 2020, doi: 10.1109/MITP.2020.2986124.
5. N. Fatima, S. A. Siddiqui and A. Ahmad, "IoT based Border Security System using Machine Learning," 2021 International Conference on Communication, Control and Information Sciences (ICCISc), 2021, pp. 1-6, doi: 10.1109/ICCISc52257.2021.9484934

8. Developed by