UAV based wilt detection system via convolutional neural networks

Dang, L. Minh; Hassan, Syed Ibrahim; Im, Sungbin; Sangaiah, Arun Kumar; Mehmood, Irfan; Rho, Seungmin; Seo, Sanghyun; Moon, Hyeonjoon

doi:10.1016/j.suscom.2018.05.010

Cited by 49 publications

(42 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If more data are available, the prediction module of the spatial pattern of land-use, social, economic, policy, demographic, and other factors should be taken into account in future research. We will also consider combining the auto image-identification method [37] into our current work to reduce manual preprocessing work. When Cloud-CELUC acquired the output result of the Map stage in the Reduce stage, input/output (IO) became a bottleneck in system performance.…”

Section: Discussionmentioning

confidence: 99%

Parallel Cellular Automata Markov Model for Land Use Change Prediction over MapReduce Framework

Kang

Fang

et al. 2019

IJGI

View full text Add to dashboard Cite

The Cellular Automata Markov model combines the cellular automata (CA) model’s ability to simulate the spatial variation of complex systems and the long-term prediction of the Markov model. In this research, we designed a parallel CA-Markov model based on the MapReduce framework. The model was divided into two main parts: A parallel Markov model based on MapReduce (Cloud-Markov), and comprehensive evaluation method of land-use changes based on cellular automata and MapReduce (Cloud-CELUC). Choosing Hangzhou as the study area and using Landsat remote-sensing images from 2006 and 2013 as the experiment data, we conducted three experiments to evaluate the parallel CA-Markov model on the Hadoop environment. Efficiency evaluations were conducted to compare Cloud-Markov and Cloud-CELUC with different numbers of data. The results showed that the accelerated ratios of Cloud-Markov and Cloud-CELUC were 3.43 and 1.86, respectively, compared with their serial algorithms. The validity test of the prediction algorithm was performed using the parallel CA-Markov model to simulate land-use changes in Hangzhou in 2013 and to analyze the relationship between the simulation results and the interpretation results of the remote-sensing images. The Kappa coefficients of construction land, natural-reserve land, and agricultural land were 0.86, 0.68, and 0.66, respectively, which demonstrates the validity of the parallel model. Hangzhou land-use changes in 2020 were predicted and analyzed. The results show that the central area of construction land is rapidly increasing due to a developed transportation system and is mainly transferred from agricultural land.

show abstract

Section: Discussionmentioning

confidence: 99%

Parallel Cellular Automata Markov Model for Land Use Change Prediction over MapReduce Framework

Kang

Fang

et al. 2019

IJGI

View full text Add to dashboard Cite

show abstract

“…The second choice depends on the average value of the activation map according to Equation (6). The third applies the ReLU function to the activation map according to Equation (7). The masks generated by the first two thresholds are binary.…”

Section: The Performance Of Mfmentioning

confidence: 99%

“…In recent years, with the improvement of hardware performance, deep neural networks have experienced tremendous development and have been widely applied in various fields, such as classification [7,8], detection [9,10], and segmentation [11,12]. Specifically, deep neural network have made breakthroughs in aircraft recognition in remote sensing images.…”

Section: Introductionmentioning

confidence: 99%

MultiCAM: Multiple Class Activation Mapping for Aircraft Recognition in Remote Sensing Images

Dai

Zhang

et al. 2019

Remote Sensing

View full text Add to dashboard Cite

Aircraft recognition in remote sensing images has long been a meaningful topic. Most related methods treat entire images as a whole and do not concentrate on the features of parts. In fact, a variety of aircraft types have small interclass variance, and the main evidence for classifying subcategories is related to some discriminative object parts. In this paper, we introduce the idea of fine-grained visual classification (FGVC) and attempt to make full use of the features from discriminative object parts. First, multiple class activation mapping (MultiCAM) is proposed to extract the discriminative parts of aircrafts of different categories. Second, we present a mask filter (MF) strategy to enhance the discriminative object parts and filter the interference of the background from original images. Third, a selective connected feature fusion method is proposed to fuse the features extracted from both networks, focusing on the original images and the results of MF, respectively. Compared with the single prediction category in class activation mapping (CAM), MultiCAM makes full use of the predictions of all categories to overcome the wrong discriminative parts produced by a wrong single prediction category. Additionally, the designed MF preserves the object scale information and helps the network to concentrate on the object itself rather than the interfering background. Experiments on a challenging dataset prove that our method can achieve state-of-the-art performance.

show abstract

“…Accordingly, extracting objects of interest in RS images with high quality has become an urgent need. Technically, efforts in semantic segmentation for RS images have surged in recent decades because it is a fundamental approach to analyze RS images, which has many important real-world applications [1][2][3][4], typically including plant-disease detection [5][6][7][8][9][10], land-cover planning [11], vegetation extraction [12], cloud detection [13,14], urban-change detection [15][16][17], vehicle detection [18], building extraction [19,20] and road extraction [21,22]. However, none of these applications reaches satisfactory segmentation quality.…”

Section: Introductionmentioning

confidence: 99%

Learnable Gated Convolutional Neural Network for Semantic Segmentation in Remote-Sensing Images

et al. 2019

View full text Add to dashboard Cite

Semantic segmentation in high-resolution remote-sensing (RS) images is a fundamental task for RS-based urban understanding and planning. However, various types of artificial objects in urban areas make this task quite challenging. Recently, the use of Deep Convolutional Neural Networks (DCNNs) with multiscale information fusion has demonstrated great potential in enhancing performance. Technically, however, existing fusions are usually implemented by summing or concatenating feature maps in a straightforward way. Seldom do works consider the spatial importance for global-to-local context-information aggregation. This paper proposes a Learnable-Gated CNN (L-GCNN) to address this issue. Methodologically, the Taylor expression of the information-entropy function is first parameterized to design the gate function, which is employed to generate pixelwise weights for coarse-to-fine refinement in the L-GCNN. Accordingly, a Parameterized Gate Module (PGM) was designed to achieve this goal. Then, the single PGM and its densely connected extension were embedded into different levels of the encoder in the L-GCNN to help identify the discriminative feature maps at different scales. With the above designs, the L-GCNN is finally organized as a self-cascaded end-to-end architecture that is able to sequentially aggregate context information for fine segmentation. The proposed model was evaluated on two public challenging benchmarks, the ISPRS 2Dsemantic segmentation challenge Potsdam dataset and the Massachusetts building dataset. The experiment results demonstrate that the proposed method exhibited significant improvement compared with several related segmentation networks, including the FCN, SegNet, RefineNet, PSPNet, DeepLab and GSN.For example, on the Potsdam dataset, our method achieved a 93.65% F 1 score and 88.06% I o U score for the segmentation of tiny cars in high-resolution RS images. As a conclusion, the proposed model showed potential for object segmentation from the RS images of buildings, impervious surfaces, low vegetation, trees and cars in urban settings, which largely varies in size and have confusing appearances.

show abstract

UAV based wilt detection system via convolutional neural networks

Cited by 49 publications

References 26 publications

Parallel Cellular Automata Markov Model for Land Use Change Prediction over MapReduce Framework

Parallel Cellular Automata Markov Model for Land Use Change Prediction over MapReduce Framework

MultiCAM: Multiple Class Activation Mapping for Aircraft Recognition in Remote Sensing Images

Learnable Gated Convolutional Neural Network for Semantic Segmentation in Remote-Sensing Images

Contact Info

Product

Resources

About