The agriculture sector plays a vital role in the Indian Economy and is known
as one of the key areas where automation is emerging to enable farmers to increase the
yield, prevent damage to the crop, reduce harvesting cost, etc. Artificial Intelligence
(AI) offers a large number of direct applications across various sectors and it can bring
a paradigm shift in the Indian farming sector. According to the report of the United
Nations, the land area for cultivation will be 4% by the year 2050 so smart farming
processes are the need of the hour and AI can help in finding solutions to increase the
yield of crops and ensure food security. The chapter focuses on the role of solarpowered robots in the agriculture sector with the application of computer vision which
is capable of recognizing the physical properties of vegetables and helps in monitoring
the yield. We analyse a vegetable image data set with mass and dimension values
collected using a computer vision system and accurate measuring devices. After
successful detection and instance-wise segmentation, we extract the real-world
dimensions of the selected vegetable. After monitoring the health of vegetables, the
robot shares the profile through IoT in real-time and thus with low labour cost and
without exhaustive search, the crop can be prevented from damage by weeds which can
be identified at an early stage. Initial evaluation of the developed prototype exhibited a
noteworthy potential of this system in the area of effective control of weeds and crop
damage and assisting in harvesting.
Keywords: Plant disease detection, Pearl millet leaves, Deep learning, Machine learning, Convolutional neural network.
