Automatic leaf segmentation and overlapping leaf separation using stereo vision

Amean, Z. Mohammed; Löw, Tobias; Hancock, Nicola

doi:10.1016/j.array.2021.100099

Cited by 8 publications

(4 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the natural environment, the color of plants is mostly affected by changes in environmental factors. Genetic factors of plants are the internal cause of plant color formation, whereas plant photosynthesis, water metabolism, mineral metabolism and other processes are often affected by light, temperature, humidity, and other external factors, causing changes in the proportion of various pigments in plants, resulting in the manifestation of different colors [5][6][7].…”

Section: Introductionmentioning

confidence: 99%

Intelligent Color Reasoning of IOT Based on P-laws

Yu¹,

Qiu²,

Cao³

et al. 2023

Computer Systems Science and Engineering

View full text Add to dashboard Cite

Aiming at the dynamics and uncertainties of natural colors affected by the natural environment, a color P-law generation model based on the natural environment is proposed to develop algorithms and to provide a theoretical basis for plant dynamic color simulation and color sensor data transmission. Based on the HSL (Hue, Saturation, Lightness) color solid, the proposed method uses the function P-set to provide a color P-law generation model and an algorithm of the Dynamic Colors System (DCS), establishing the DCS modeling theory of the natural environment and the color P-reasoning simulation based on the HSL color solid. The experimental results show that based on the color P-law, for the DCS of the natural environment, when the external factors change, the color of the plant changes, accordingly, verifying the effectiveness of the color P-law generation model and the algorithm of the DCS. In the dynamic color intelligent simulation system, when external factors change, the dynamic change of plant color generally conforms to the basic laws of the natural environment. This enables the effective extraction of color data from the Internet of Things (IoT)based color sensors and provides an effective way to significantly reduce the data transmission bandwidth of the IoT network.

show abstract

Section: Introductionmentioning

confidence: 99%

Intelligent Color Reasoning of IOT Based on P-laws

Yu¹,

Qiu²,

Cao³

et al. 2023

Computer Systems Science and Engineering

View full text Add to dashboard Cite

show abstract

“…(2019) proposed a schema to augment the training dataset and remain the geometrical structure of the plant leaf by constructing a generation synthetic data. To segment multiple leaves at the same time and deal with the leaf over-segmentation, a deep extraction method for plant leaf ( Amean et al., 2021 ) was proposed by incorporating multiple features, such as color, shape, and depth information. Lin et al.…”

Section: Introductionmentioning

confidence: 99%

“…Kuznichov et al (2019) proposed a schema to augment the training dataset and remain the geometrical structure of the plant leaf by constructing a generation synthetic data. To segment multiple leaves at the same time and deal with the leaf over-segmentation, a deep extraction method for plant leaf (Amean et al, 2021) was proposed by incorporating multiple features, such as color, shape, and depth information. Lin et al (Lin et al, 2023) proposed a self-supervised blade segmentation framework consisting of a self-supervised semantic segmentation model, a color-based blade segmentation algorithm, and a self-supervised color correction model.…”

mentioning

confidence: 99%

BAF-Net: Bidirectional attention fusion network via CNN and transformers for the pepper leaf segmentation

et al. 2023

View full text Add to dashboard Cite

The segmentation of pepper leaves from pepper images is of great significance for the accurate control of pepper leaf diseases. To address the issue, we propose a bidirectional attention fusion network combing the convolution neural network (CNN) and Swin Transformer, called BAF-Net, to segment the pepper leaf image. Specially, BAF-Net first uses a multi-scale fusion feature (MSFF) branch to extract the long-range dependencies by constructing the cascaded Swin Transformer-based and CNN-based block, which is based on the U-shape architecture. Then, it uses a full-scale feature fusion (FSFF) branch to enhance the boundary information and attain the detailed information. Finally, an adaptive bidirectional attention module is designed to bridge the relation of the MSFF and FSFF features. The results on four pepper leaf datasets demonstrated that our model obtains F1 scores of 96.75%, 91.10%, 97.34% and 94.42%, and IoU of 95.68%, 86.76%, 96.12% and 91.44%, respectively. Compared to the state-of-the-art models, the proposed model achieves better segmentation performance. The code will be available at the website: https://github.com/fangchj2002/BAF-Net.

show abstract

“…The combination of occlusions and plant self-similarity makes it challenging to use standard tracking methods [7][8][9]. Some rare tools are proposed to extend the monitoring despite the overlap, as in [10] via watershed or extended feature space (color, texture, depth) as in [11,12] or via advanced machine learning object detection tools [13]. Here, we investigate a distinct approach to disentangle overlapped plants.…”

Section: Introductionmentioning

confidence: 99%

On the Use of Circadian Cycles to Monitor Individual Young Plants

et al. 2023

View full text Add to dashboard Cite

Occlusion is a very common problem in computer vision. The presence of objects seen as overlapped under a camera negatively impacts object recognition, object counting or shape estimation. This problem is especially important in plant imaging because plants are very self-similar objects which produce a lot of self-occlusions. A possible way to disentangle apparent occlusions is to acquire the same scene from different points of view when the object is motionless. Such a realization is not necessary if the objects move themselves under the camera and thus offer different points of view for free. This is the case in plant imagery, since plants have their own natural movements, including the so-called circadian rhythms. We propose to use these movements to solve some self-occlusion problems with a set of simple yet innovative sampling algorithms to monitor the growth of individualized young plants. The proposed sampling methods make it possible to monitor the growth of the individual plants until their overlap is definitive. The gain is significant with an average maximum duration of observation increase from 3 days to more than 10 days by comparison with a sampling method that would stop when the first overlap occurs.

show abstract

Automatic leaf segmentation and overlapping leaf separation using stereo vision

Cited by 8 publications

References 38 publications

Intelligent Color Reasoning of IOT Based on P-laws

Intelligent Color Reasoning of IOT Based on P-laws

BAF-Net: Bidirectional attention fusion network via CNN and transformers for the pepper leaf segmentation

On the Use of Circadian Cycles to Monitor Individual Young Plants

Contact Info

Product

Resources

About