Technological advances in the development of precision agriculture machinery and software
will then prove to be cheaper and faster than on-ground human intervention and data
collection. Advancements in both image processing routines and communication systems
now (literally) change the picture for farmers. The amount of image processing applications
in precise agriculture is growing steadily with the availability of higher quality
measurements coupled with modern algorithms and increased possibility to fuse multiple
sources of information from satellite imagery and sensors positioned in fields. This article
focuses on the applications of image processing in precision agriculture. Major concerns in
agriculture are water stress, quality of yields, and the use of pesticides. Providing data and
monitoring irrigation, whether artificial or natural, is possible by tracking satellite imaging of
fields over time. Applications in precision agriculture allow mapping of irrigated lands at
lower costs. Water also affects the thermal properties of plants. Therefore, processing
infrared imaging provides additional means to analyze and monitor irrigation. The analysis
from infrared imaging can then be used in pre-harvesting operations, to decide whether or
not or even where to harvest.
Foreign plants (weeds) growing in farms can also be detected by combining image processing
and machine learning techniques. Edge based machine learning classifiers can identify
weeds in color images. In addition, classification based on plant color features can be added
and information regarding the texture of plants integrated to enhance classification
accuracy. The partial success of these algorithms has motivated further development in
herbicide applications. Fuzzy algorithms based on green color analysis of plants have
provided weed coverage estimation and allowed for the integration of this knowledge into
farm management plans.The quality of yield is another concern of farmers. Automated
quality analysis of food products is a great money and labor saving process, especially in
light of heavy regulations on fruit quality and safety standards. Image processing is an
accurate and reliable method for sorting and grading fresh products (fruits, grains, bakery
products, etc.) characterized by color, size and shape. By combining analysis of these
features, RSIP Vision has developed algorithms for sorting and grading that are currently
embedded within industrial production machinery.
There are various image processing methods:- Image Acquisition, Image Enhancement,
Image Analysis, Object Recognition. The main applications of image processing are as:-
A. Plant disease identification
B. Fruit Sorting and Classification
C. Plant species Identification
D. Precision farming
E. Precision farming
F. Crop and Land Assessment using Remote Sensing
G. Weed recognition
Image enhancement and image segmentation method are an inevitable method in varied
applications and it determines the accuracy of the automation. Appropriate selection of
image processing modules paves the way for higher accuracy in the higher level process for
decision making. Image processing holds an effective set of tools for the analysis of imagery
used in precise agriculture.
- Teena Wawre
(ELECTRONICS 4th year)