Abstract
Agriculture is considered to be the driving force of the Indian economy. Production of crops is considered to be one of the complex phenomena as they are influenced by the agro-climatic parameters. From novice to experienced farmers, at times, fail to figure out the suitable crop for their lands, leading to financial loss. This is because of the dynamic change in soil nutrient levels and climatic conditions. Hence, it is important to predict crops according to the presence of the nutrients in a land. Recommending the crops to a farm after considering the nutrients levels of the soil and predicting the yield will largely help the landowner in taking necessary steps for marketing and storage in the future. These results will further assist the industries to plan the logistics of their business who are working in partnership with these landowners. In this work, pH and other soil nutrients are estimated from the input ortho images to recommend crops that can grow well under the given circumstances.
TopBackground
Oliveira et al. (2018) proposed a method to detect areas that do not contain plant saplings in the coffee crops plantation using ortho-photos. To facilitate decisions, both the positions of failures and total failure length is obtained from the ortho-photos.
Ciriza et al. (2017) proposed a method to automatically detect uprooted orchards by using textural information from ortho-photos in order to reduce photo interpretation needed to update the agricultural database [AGDB]. Five textural features were selected based on GLCM and Wavelet planes. This methodology reduced the photo interpretation by 60-85% and achieved an accuracy of 85%.
Afrin et al. (2018) proposed a method to apply data mining techniques to predict the yields of staple crops of Bangladesh. Soil factors like pH, nutrients, organic substances and climatic data of the past six years were utilized to determine soil health. Tewari et al. (2013) proposed a method to estimate plant nitrogen content using digital image processing techniques. Observations include the average nitrogen consumption and the chlorophyll content. R,G,B and normalized R and G values were acquired and Regression models were built which had a correlation coefficient of 0.948.
Key Terms in this Chapter
Unsupervised Segmentation: Algorithms that understand the different bounded segments that are present in an image by itself without referring to the ground truth.
Soil Color: Soil color refers to the composition of the soil. It might be due to the minerals present in the soil. Soil exhibits different colors like black, red, brown, etc.
Crop Recommendation: Suggestions about crops that are given to agriculturalists based on the pH values, types of soil, the nutrient contents present in the soil and other characteristics. The crops planted based on the suggestions yield maximum profit.
Collaborative Filtering: This method can be used to predict the plantation of a suitable crop that can yield profit to the requesting user by collecting and analyzing relevant agricultural data in different types and from different sources.
Agriculture: It is the art of growing crops. Many families in India depend on agriculture.
Soil Nutrients: The three important nutrients present in the soil are Nitrogen (N), Phosphorous (P), and Potassium (K) which are popularly quoted together as NPK values.
Classification: Categorization of objects into groups based on the existing ground truth values. Artificial Intelligence based algorithms classify objects easily.
Image Segmentation: This technique is a pre-processing activity that is carried out in image processing. This partitions the image into multiple segments and identifies the different bounded regions present in the image using computer algorithms.