A hybrid machine learning approach to automatic plant phenotyping for smart agriculture

Yahata, So; Onishi, Tetsu; Yamaguchi, Katsunori; Ozawa, Seiichi; Kitazono, Jun; Ohkawa, Takenao; Yoshida, Takeshi; Murakami, Noriyuki; Tsuji, Hiroyuki

doi:10.1109/ijcnn.2017.7966067

Cited by 34 publications

(28 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nevertheless, methods used for flower detection can be selected based on the appearance and color of flowers and desired accuracy. [17,20,39] Current study and [40] SVM in [15,16,23] CNN in [18,24] Crops Apple, peach, pea, lesquerella, canola, camelina, chickpea…”

Section: Methods Of Flower Detectionmentioning

confidence: 99%

“…Flower detection has been tested on plant species such as cereals (rice, wheat, and corn), legumes (soybean), tree fruits (apple and citrus), oilseeds (lesquerella and canola), fibers (cotton), and ornamentals (rose) [15][16][17][18][19][20][21][22][23][24]. In literature, image-based detection of tangerine and lesquerella flowers showed good relationship between manual and image-based detection (R 2 = 0.91 and 0.87-0.91, respectively) [19,20].…”

Section: Introductionmentioning

confidence: 99%

“…In reported studies, different color spaces (RGB, hue-saturation-intensity (HSI), or vegetation index extracted from RGB color space) and morphological features (e.g., circular shape) have been used [19,[21][22][23]. In addition, texture features and machine learning algorithms, such as convolutional neural network (CNN) and support vector machine (SVM), have been applied to increase flower detection accuracy [15,16,18,23,24]. Sadeghi-Tehran et al [16] used scale invariant feature transformation, local linear constraint coding, and spatial pyramid matching to extract low-and mid-level features, and applied SVM to classify images to determine heading and flowering stages of six varieties of wheat.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Image-Based Phenotyping of Flowering Intensity in Cool-Season Crops

Zhang

Craine

McGee

et al. 2020

Sensors

View full text Add to dashboard Cite

The timing and duration of flowering are key agronomic traits that are often associated with the ability of a variety to escape abiotic stress such as heat and drought. Flowering information is valuable in both plant breeding and agricultural production management. Visual assessment, the standard protocol used for phenotyping flowering, is a low-throughput and subjective method. In this study, we evaluated multiple imaging sensors (RGB and multiple multispectral cameras), image resolution (proximal/remote sensing at 1.6 to 30 m above ground level/AGL), and image processing (standard and unsupervised learning) techniques in monitoring flowering intensity of four cool-season crops (canola, camelina, chickpea, and pea) to enhance the accuracy and efficiency in quantifying flowering traits. The features (flower area, percentage of flower area with respect to canopy area) extracted from proximal (1.6–2.2 m AGL) RGB and multispectral (with near infrared, green and blue band) image data were strongly correlated (r up to 0.89) with visual rating scores, especially in pea and canola. The features extracted from unmanned aerial vehicle integrated RGB image data (15–30 m AGL) could also accurately detect and quantify large flowers of winter canola (r up to 0.84), spring canola (r up to 0.72), and pea (r up to 0.72), but not camelina or chickpea flowers. When standard image processing using thresholds and unsupervised machine learning such as k-means clustering were utilized for flower detection and feature extraction, the results were comparable. In general, for applicability of imaging for flower detection, it is recommended that the image data resolution (i.e., ground sampling distance) is at least 2–3 times smaller than that of the flower size. Overall, this study demonstrates the feasibility of utilizing imaging for monitoring flowering intensity in multiple varieties of evaluated crops.

show abstract

Section: Methods Of Flower Detectionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Image-Based Phenotyping of Flowering Intensity in Cool-Season Crops

Zhang

Craine

McGee

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…Differing from the so-called single methods in Section 2.1, a combined method here means that several methods are used together in a parallel or serial structure. For example, Yahata et al [60] combined machine learning techniques to construct sensing methods in an agricultural cyber-physical system, in which big data of agricultural plants and environmental information (e.g., temperature, humidity, solar radiation, soil condition, etc.) were analyzed to mine useful rules for appropriate cultivation.…”

Section: Combined Methodsmentioning

confidence: 99%

Hybrid Deep Learning Predictor for Smart Agriculture Sensing Based on Empirical Mode Decomposition and Gated Recurrent Unit Group Model

Jin

Yang

Wang

et al. 2020

Sensors

View full text Add to dashboard Cite

Smart agricultural sensing has enabled great advantages in practical applications recently, making it one of the most important and valuable systems. For outdoor plantation farms, the prediction of climate data, such as temperature, wind speed, and humidity, enables the planning and control of agricultural production to improve the yield and quality of crops. However, it is not easy to accurately predict climate trends because the sensing data are complex, nonlinear, and contain multiple components. This study proposes a hybrid deep learning predictor, in which an empirical mode decomposition (EMD) method is used to decompose the climate data into fixed component groups with different frequency characteristics, then a gated recurrent unit (GRU) network is trained for each group as the sub-predictor, and finally the results from the GRU are added to obtain the prediction result. Experiments based on climate data from an agricultural Internet of Things (IoT) system verify the development of the proposed model. The prediction results show that the proposed predictor can obtain more accurate predictions of temperature, wind speed, and humidity data to meet the needs of precision agricultural production.

show abstract

“…Yahata, So, et al [18] has explained how a hybrid machine learning approach can be used for automatic plant phenotyping in smart agriculture. This research has considered 2 image sensing methods, one is for flower detection and the other one is for seedpod detection.…”

Section: Increasing the Productivity Of Agriculture Using Machine Leamentioning

confidence: 99%

Study on Machine Learning for Identification of Farmer’s Query in Kannada Language

Pai¹,

Of²,

Hegde³

2019

IJCA

View full text Add to dashboard Cite

Agriculture is considered as the economic backbone of almost all the countries in the world. As there is increase in population, the need for basic requirements such as food, clothing, shelters, and medicines also increases. To meet all these needs, advancement in agriculture is needed. Various technologies have been introduced in agriculture to increase the yield of several crops. One among them is the machine learning technology. Machine learning is an important area in computer science that allows the computers to write programs on its own without being explicitly programmed. Machine learning techniques in agriculture help to improve the traditional farming techniques in a very efficient way. The main purpose of this paper is to learn different use of machine learning techniques in agriculture and to develop machine learning model for agriculture.

show abstract

A hybrid machine learning approach to automatic plant phenotyping for smart agriculture

Cited by 34 publications

References 8 publications

Image-Based Phenotyping of Flowering Intensity in Cool-Season Crops

Image-Based Phenotyping of Flowering Intensity in Cool-Season Crops

Hybrid Deep Learning Predictor for Smart Agriculture Sensing Based on Empirical Mode Decomposition and Gated Recurrent Unit Group Model

Study on Machine Learning for Identification of Farmer’s Query in Kannada Language

Contact Info

Product

Resources

About