Weeds Detection and Classification using Convolutional Long-Short-Term Memory

Abstract

The smart agricultural robotic system can decrease the dependence on various traditional agriculture crop spraying methods such as pesticides, herbicides, and fertilizer. To meet the world population food requirements, conventional schemes are not sufficient for spraying agrochemicals to control the weeds and increase crop production. Therefore, a smart and intelligent farming system is introduced to increase the production of crops and to reach crop production target. In this paper, Deep Learning (DL) based algorithms is applied for the identification and classification of weed plants using combination of Convolutional Neural Networks (CNN) and Long-Short- Term Memory (LSTM). Convolutional Neural Networks (CNN) has a unique structure to get discriminative features for the input images, and LSTM allows to jointly optimize the classification. To validate the proposed scheme, nine kinds of weeds are classified using the proposed method such as vine weeds, three-leaf weeds, spiky weeds, and invasive creeping weeds. We carried out several extensive experiments and 99.36% of average classification accuracy is achieved. The obtained results show that the combination of CCN-LSTM has significantly higher classification capabilities in comparison to other existing prominent approaches.

An Adaptive Edge Detection Algorithm for Weed Image Analysis

“…However, in various growth phases against different environments, the struggle for CNN training along with plant species is massive that might need joint steps of several working groups [25]. Likewise, a state-of-the-art technique was developed by [26] which was based on deep learning for the classification of weeds. In this technique, the authors utilized CNN coupled with long-short term memory (LSTM).…”

“…T positive + T negative T positive + T negative + F positive + F negative (24) Precision (P) = T positive T positive + F positive (25) Recall (R) = T positive T positive + F negative (26) The average precision (A P ) and average recall (A R ) are respectively calculated in Eqs. ( 27) and (28).…”

Water Stress Identification of Winter Wheat Crop with State-of-the-Art AI Techniques and High-Resolution Thermal-RGB Imagery

“…Similarly, different DL techniques (AlexNet, GoogLeNet, and Inception V3) have also been used to classify non-stressed and water-stressed soybean, maize, and okra crops with digital RGB images [ 10 ]. Long Short Term Memory (LSTM) is a novel DL approach (DL-LSTM) that has been used for different field applications like time series forecasting of wheat yield and productivity [ 21 ], irrigation requirement [ 22 ], predicting agricultural product sale volumes based on seasonal and historical data [ 23 ], and identification and classification of weeds [ 24 ]. Most of the image processing studies have used RGB images (or visible range imagery) to classify crop water stress [ 25 , 26 ].…”