scholarly journals Automated Agave Detection and Counting Using a Convolutional Neural Network and Unmanned Aerial Systems

Drones ◽  
2021 ◽  
Vol 5 (1) ◽  
pp. 4
Author(s):  
Donovan Flores ◽  
Iván González-Hernández ◽  
Rogelio Lozano ◽  
Jesus Manuel Vazquez-Nicolas ◽  
Jorge Luis Hernandez Toral
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Detection Method ◽  
Unmanned Aerial Systems ◽  
Simpler Algorithm ◽  
Computer Image Processing ◽  
Detection And Counting ◽  
Aerial Vehicle ◽  
High Level ◽  
Aerial Systems

We present an automatic agave detection method for counting plants based on aerial data from a UAV (Unmanned Aerial Vehicle). Our objective is to autonomously count the number of agave plants in an area to aid management of the yield. An orthomosaic is obtained from agave plantations, which is then used to create a database. This database is in turn used to train a Convolutional Neural Network (CNN). The proposed method is based on computer image processing, and the CNN increases the detection performance of the approach. The main contribution of the present paper is to propose a method for agave plant detection with a high level of precision. In order to test the proposed method in a real agave plantation, we develop a UAV platform, which is equipped with several sensors to reach accurate counting. Therefore, our prototype can safely track a desired path to detect and count agave plants. For comparison purposes, we perform the same application using a simpler algorithm. The result shows that our proposed algorithm has better performance reaching an F1 score of 0.96 as opposed to 0.57 for the Haar algorithm. The obtained experimental results suggest that the proposed algorithm is robust and has considerable potential to help farmers manage agave agroecosystems.

scholarly journals Unmanned Aerial System-Based Weed Mapping in Sod Production Using a Convolutional Neural Network

2021 ◽  
Vol 12 ◽  
Author(s):  
Jing Zhang ◽  
Jerome Maleski ◽  
David Jespersen ◽  
F. C. Waltz ◽  
Glen Rains ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Application Programming Interface ◽  
Image Resolution ◽  
Unmanned Aerial Systems ◽  
Weed Species ◽  
Persistent Problem ◽  
Weed Mapping ◽  
Chemical Inputs ◽  
High Level

Weeds are a persistent problem on sod farms, and herbicides to control different weed species are one of the largest chemical inputs. Recent advances in unmanned aerial systems (UAS) and artificial intelligence provide opportunities for weed mapping on sod farms. This study investigates the weed type composition and area through both ground and UAS-based weed surveys and trains a convolutional neural network (CNN) for identifying and mapping weeds in sod fields using UAS-based imagery and a high-level application programming interface (API) implementation (Fastai) of the PyTorch deep learning library. The performance of the CNN was overall similar to, and in some classes (broadleaf and spurge) better than, human eyes indicated by the metric recall. In general, the CNN detected broadleaf, grass weeds, spurge, sedge, and no weeds at a precision between 0.68 and 0.87, 0.57 and 0.82, 0.68 and 0.83, 0.66 and 0.90, and 0.80 and 0.88, respectively, when using UAS images at 0.57 cm–1.28 cm pixel–1 resolution. Recall ranges for the five classes were 0.78–0.93, 0.65–0.87, 0.82–0.93, 0.52–0.79, and 0.94–0.99. Additionally, this study demonstrates that a CNN can achieve precision and recall above 0.9 at detecting different types of weeds during turf establishment when the weeds are mature. The CNN is limited by the image resolution, and more than one model may be needed in practice to improve the overall performance of weed mapping.

scholarly journals A Real-time Driver Fatigue Detection Method Based on Two-Stage Convolutional Neural Network

2020 ◽  
Vol 53 (2) ◽  
pp. 15374-15379
Author(s):  
Hu He ◽  
Xiaoyong Zhang ◽  
Fu Jiang ◽  
Chenglong Wang ◽  
Yingze Yang ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Real Time ◽  
Detection Method ◽  
Driver Fatigue ◽  
Two Stage ◽  
Fatigue Detection

scholarly journals Spectral Convolution Feature-Based SPD Matrix Representation for Signal Detection Using a Deep Neural Network

Entropy ◽  
2020 ◽  
Vol 22 (9) ◽  
pp. 949
Author(s):  
Jiangyi Wang ◽  
Min Liu ◽  
Xinwu Zeng ◽  
Xiaoqiang Hua
Keyword(s):  
Neural Network ◽  
Signal Detection ◽  
Convolutional Neural Network ◽  
Deep Neural Network ◽  
Detection Method ◽  
Learning Algorithm ◽  
Simulated Data ◽  
Data Sets ◽  
Feature Maps ◽  
Simulated Data Sets

Convolutional neural networks have powerful performances in many visual tasks because of their hierarchical structures and powerful feature extraction capabilities. SPD (symmetric positive definition) matrix is paid attention to in visual classification, because it has excellent ability to learn proper statistical representation and distinguish samples with different information. In this paper, a deep neural network signal detection method based on spectral convolution features is proposed. In this method, local features extracted from convolutional neural network are used to construct the SPD matrix, and a deep learning algorithm for the SPD matrix is used to detect target signals. Feature maps extracted by two kinds of convolutional neural network models are applied in this study. Based on this method, signal detection has become a binary classification problem of signals in samples. In order to prove the availability and superiority of this method, simulated and semi-physical simulated data sets are used. The results show that, under low SCR (signal-to-clutter ratio), compared with the spectral signal detection method based on the deep neural network, this method can obtain a gain of 0.5–2 dB on simulated data sets and semi-physical simulated data sets.

Sign in / Sign up

Export Citation Format

Share Document