| 1. |
- Hedin, Jonas, et al.
(författare)
-
Using radio telemetry to study dispersal of the beetle Osmoderma eremita, an inhabitant of tree hollows
- 2002
-
Ingår i: Computers and Electronics in Agriculture. - 0168-1699. ; 35:2-3, s. 171-180
-
Konferensbidrag (refereegranskat)abstract
- This paper describes a radio-tracking study of Osmoderma eremita, a large Scarabaeid beetle, living in hollow trees. The study seems to be the first in which radio telemetry has been used with a flying insect in the field. Some 74 adult beetles were tagged with radio transmitters weighing 0.48-0.52 1, and having a nominal battery life of 12-20 days. Transmissions were detected at ranges of up to 330 m, with 50-100 in obtained routinely. Contact was lost with 71% of the females and 20% of the males before the end of the nominal lifetime of the transmitter's battery, probably because the transmitter ceased to function. Radio telemetry proved effective in this study and gave dispersal ranges and rates that were consistent with those from a concurrent mark-recapture study in the same area. However, further development of the technique is desirable. The antennas need to be more flexible and the transmitters smaller and lighter. Nevertheless, even the current form of the technique may be suitable for studying short-range dispersal in other large-bodied flight-capable insects.
|
|
| 2. |
- Johansson, J., et al.
(författare)
-
Predicting moisture content and density of Scots pine by microwave scanning of sawn timber
- 2003
-
Ingår i: Computers and Electronics in Agriculture. - 0168-1699 .- 1872-7107. ; 41:1-3, s. 85-90
-
Tidskriftsartikel (refereegranskat)abstract
- Non-destructive testing of wood for prediction of strength is significantly influenced by wood density and moisture content. A sensor capable of measuring both density and moisture content would be a good tool to aid in predicting the strength of sawn timber. This study was carried out to investigate the possibility of calibrating a prediction model for the moisture content and density of Scots pine (Pinus sylvestris) using microwave sensors. The material was initially at green moisture content, and thereafter dried in several steps to zero moisture content. At each step all the samples were weighted, scanned with a microwave camera (Satimo 9.4 GHz) and CT scanned with a medical CT scanner (Siemens Somatom AR.T.). The output variables from the microwave camera were used as predictors, and CT images correlated with known moisture content were used as response variables. Multivariate models to predict moisture content and density were calibrated using partial least squares (PLS) regression. The result shows that it is possible to predict both moisture content and density with very high accuracy using microwave sensors
|
|
| 3. |
- Nyström, Jan
(författare)
-
Automatic measurement of fiber orientation in softwoods by using the tracheid effect
- 2003
-
Ingår i: Computers and Electronics in Agriculture. - 0168-1699 .- 1872-7107. ; 41:1-3, s. 91-99
-
Tidskriftsartikel (refereegranskat)abstract
- Spiraled grain commonly occurs in softwood trees. Instead of running parallel to the pith, the grain runs spirally around the trunk like a helix. Since wood is an orthotropic material with higher shrinkage perpendicular to than parallel to the fibers, the log will twist when dried, and so will a plank or board cut from it. Several investigations have shown that the magnitude of twist in sawn wood is highly correlated to the fiber orientation, so by measuring the fiber orientation on green lumber, the risk of warp after drying can be indicated. Fiber orientation is also interesting for other purposes, for example stress grading and research applications. We concern the tracheid effect, which utilizes the light conducting properties of the softwood tracheids to measure fiber orientation. A small circular laser beam was projected onto the wood surface. The light was transmitted in the wood and scattered back to form an elliptical shape extended in the direction of the fibers. The ellipse of light was registered with a CMOS camera, and the orientation of the ellipse's major axis was calculated. This method has a correlation coefficient of 0.99996 to manually aligned fiber orientation, and repeated measurements show a standard deviation of 0.2°. Calculation time for one 64×64 pixel image was 67 μs, which must be regarded as useful for industrial applications.
|
|
| 4. |
- Oja, Johan, et al.
(författare)
-
Automatic grading of Scots pine (Pinus sylvestris L.) sawlogs using an industrial X-ray log scanner
- 2003
-
Ingår i: Computers and Electronics in Agriculture. - 0168-1699 .- 1872-7107. ; 41:1-3, s. 63-75
-
Tidskriftsartikel (refereegranskat)abstract
- The successful running of a sawmill is dependent on its ability to achieve the highest possible value recovery from the sawlogs, i.e. to optimize the use of the raw material. Such optimization requires information about the properties of every log. One method of measuring these properties is to use an X-ray log scanner. The objective was to determine the accuracy when grading Scots pine (Pinus sylvestris L.) sawlogs using an industrial scanner known as the X-ray LogScanner. The study was based on 150 Scots pine sawlogs from a sawmill in northern Sweden. All logs were scanned in the LogScanner at a speed of 125 m/min. The X-ray images were analyzed on-line with measures of different properties as a result (e.g. density and density variations). The logs were then sawn with a normal sawing pattern (50 × 125 mm) and the logs were graded depending on the result from the manual grading of the center boards. Finally, partial least squares (PLS) regression was used to calibrate statistical models that predict the log grade based on the properties measured by the X-ray LogScanner. The study showed that 77-83% of the logs were correctly sorted when using the scanner to sort logs into three groups according to the predicted grade of the center boards. After sawing the sorted logs, 67% of the boards had the correct grade. When scanning the same logs repeatedly, the relative standard deviation of the predicted grade was 12-20%. The study also showed that it is possible to sort out 10 and 16%, respectively, of the material into two groups with high quality logs, without changing the grade distribution of the rest of the material to any great extent
|
|
| 5. |
- Seger, M.M., et al.
(författare)
-
Scanning of logs with linear cone-beam tomography
- 2003
-
Ingår i: Computers and Electronics in Agriculture. - 0168-1699 .- 1872-7107. ; 41:1-3, s. 45-62
-
Konferensbidrag (övrigt vetenskapligt/konstnärligt)abstract
- This paper reports an ongoing feasibility study in industrial X-ray tomography. Full volume scanning of logs may have a large potential in terms of increased sales value. On the other hand, there is no technology commercially available today which can meet the requirements for speed. In conventional medical 3D-tomography, the source-detector system rotates around a slowly translating patient. We do not believe such an arrangement is able to reach our speed requirements. Instead, we have been simulating an arrangement with two fixed source-detector systems rotated 90° relative to each other. Each system consists of an X-ray source and a 2D detector. The logs are to be translated through this arrangement at relatively high speed (2-3 m/s) lengthwise on a conveyor belt, while cone-beam projections are acquired by each of the source-detector systems. The 2D-detectors are composed of a number of 1D-detectors side by side. For cost reasons we will try to limit the number of rows to nine, forming a 2D-array of 256 x 9 detector elements. Due to the unconventional scanning geometry, we have developed a new reconstruction algorithm, which also takes special care to avoid many artifacts due to sparse and/or missing data. Experiments (still simulated), performed on voxelized CT data, indicate that the knots are reconstructed with sufficient accuracy to allow for quantitative optimization. Due to the missing data, however, heartwood can barely be distinguished from sapwood, but his fact does not seem to compromise the subsequent knot detection. Note that this paper only describes the reconstruction part of the simulated experiments. To be complete, the feasibility study should also include segmentation, which is outside the scope of this paper. © 2003 Elsevier Science B.V. All rights reserved.
|
|
| 6. |
- A. Bateki, Christian, et al.
(författare)
-
Of milk and mobiles: Assessing the potential of cellphone applications to reduce cattle milk yield gaps in Africa using a case study
- 2021
-
Ingår i: Computers and Electronics in Agriculture. - : Elsevier BV. - 0168-1699. ; 191
-
Tidskriftsartikel (refereegranskat)abstract
- There are growing expectations that Information and Communication Technology (ICT) applications could help improve on-farm yields amongst smallholder farmers in developing countries, and consequently, food and nutrition security. However, few studies have quantified the actual contribution of ICT applications on farmers’ yields, and these studies predominantly focused on crop production. We assessed the potential of ICT applications to close milk yield gaps among small- and medium scale dairy cattle farmers in Africa. First, we developed a theoretical framework summarizing biophysical and socio-economic constraints that foster milk yield gaps and discussed which constraints can be addressed using ICT applications. Second, using a case study of a feeding advice application for dairy cattle pre-tested with farmers in rural Kenya, we analyzed how much stand-alone the application could contribute to close dairy cattle milk yield gaps. Our findings suggest that ICT applications could help address some existing biophysical and socio-economic constraints fostering milk yield gaps, including data collection for breeding programs, feeding management advice, and facilitating access to markets and capital. Our stand-alone ICT application closed yield gaps by 2 % to 6 % on representative farms. Several factors may explain the limited actual contribution of selected ICT applications to reduce existing milk yield gaps, including the quality of the input data and models used in ICT applications, and more structural constraints that cannot be addressed by digital tools. Therefore, although ICT applications could help address constraints to achieving higher milk yields on dairy farms, a significant contribution to improve yields may only be achieved when conditions surrounding their use are adequate.
|
|
| 7. |
- Ahlman, Linnéa, 1987, et al.
(författare)
-
Using chlorophyll a fluorescence gains to optimize LED light spectrum for short term photosynthesis
- 2017
-
Ingår i: Computers and Electronics in Agriculture. - : Elsevier BV. - 0168-1699. ; 142, s. 224-234
-
Tidskriftsartikel (refereegranskat)abstract
- When changing from the traditional high pressure sodium (HPS) lamps to light emitting diode (LED) lamps there is a quite unexplored energy saving potential in the fact that they are far better suited for control, since both spectrum and light intensity can be adjusted. This work aims at finding a way to automatically adjust the spectrum of a LED lamp, equipped with several different types of LEDs, to maximize plant growth by feedback of a remote online measure correlated with growth.A series of experiments were conducted on basil plants in order to examine whether remotely sensed steady-state chlorophyll fluorescence (F740) can be used for this purpose, and if its derivatives (fluorescence gains) w.r.t. applied powers change relative to each other for different light intensities and spectraA strong correlation between F740 and photosynthetic rate was indeed found. However, the order (w.r.t. LED type) of the fluorescence gains was only moderately affected by the light intensities and spectra investigated. The gain was highest w.r.t. red light (630 nm), though, when taking the electrical efficiencies of individual LED types into consideration, blue LEDs (450 nm) were equally, or even more efficient than the red onesAn online controller to regulate optimal spectrum for basil appears to be unnecessary. However, the fluorescence gains could be used to adapt to changes in the efficiencies when crops and operating conditions change, or when the diodes degrade. The method also shows promise as a tool to find optimal light intensity levels as well as identifying plant stress.
|
|
| 8. |
- Araujo Sandroni, Murilo, et al.
(författare)
-
In-field classification of the asymptomatic biotrophic phase of potato late blight based on deep learning and proximal hyperspectral imaging
- 2023
-
Ingår i: Computers and Electronics in Agriculture. - : Elsevier BV. - 0168-1699 .- 1872-7107. ; 205
-
Tidskriftsartikel (refereegranskat)abstract
- Effective detection of potato late blight (PLB) is an essential aspect of potato cultivation. However, it is a challenge to detect late blight in asymptomatic biotrophic phase in fields with conventional imaging approaches because of the lack of visual symptoms in the canopy. Hyperspectral imaging can capture spectral signals from a wide range of wavelengths also outside the visual wavelengths. Here, we propose a deep learning classification architecture for hyperspectral images by combining 2D convolutional neural network (2D-CNN) and 3D-CNN with deep cooperative attention networks (PLB-2D-3D-A). First, 2D-CNN and 3D-CNN are used to extract rich spectral space features, and then the attention mechanism AttentionBlock and SE-ResNet are used to emphasize the salient features in the feature maps and increase the generalization ability of the model. The dataset is built with 15,360 images (64x64x204), cropped from 240 raw images captured in an experimental field with over 20 potato genotypes. The accuracy in the test dataset of 2000 images reached 0.739 in the full band and 0.790 in the specific bands (492 nm, 519 nm, 560 nm, 592 nm, 717 nm and 765 nm). This study shows an encouraging result for classification of the asymptomatic biotrophic phase of PLB disease with deep learning and proximal hyperspectral imaging.
|
|
| 9. |
- Awad, Ali Ismail
(författare)
-
From classical methods to animal biometrics: A review on cattle identification and tracking
- 2016
-
Ingår i: Computers and Electronics in Agriculture. - : Elsevier BV. - 0168-1699 .- 1872-7107. ; 123, s. 423-435
-
Tidskriftsartikel (refereegranskat)abstract
- Cattle, buffalo and cow, identification has recently played an influential role towards understanding disease trajectory, vaccination and production management, animal traceability, and animal ownership assignment. Cattle identification and tracking refers to the process of accurately recognizing individual cattle and their products via a unique identifier or marker. Classical cattle identification and tracking methods such as ear tags, branding, tattooing, and electrical methods have long been in use; however, their performance is limited due to their vulnerability to losses, duplications, fraud, and security challenges. Owing to their uniqueness, immutability, and low costs, biometric traits mapped into animal identification systems have emerged as a promising trend. Biometric identifiers for beef animals include muzzle print images, iris patterns, and retinal vascular patterns. Although using biometric identifiers has replaced human experts with computerized systems, it raises additional challenges in terms of identifier capturing, identification accuracy, processing time, and overall system operability. This article reviews the evolution in cattle identification and tracking from classical methods to animal biometrics. It reports on traditional animal identification methods and their advantages and problems. Moreover, this article describes the deployment of biometric identifiers for effectively identifying beef animals. The article presents recent research findings in animal biometrics, with a strong focus on cattle biometric identifiers such as muzzle prints, iris patterns, and retinal vascular patterns. A discussion of current challenges involved in the biometric-based identification systems appears in the conclusions, which may drive future research directions.
|
|
| 10. |
- Barros, T., et al.
(författare)
-
Multispectral vineyard segmentation : A deep learning comparison study
- 2022
-
Ingår i: Computers and Electronics in Agriculture. - : Elsevier BV. - 0168-1699 .- 1872-7107. ; 195
-
Tidskriftsartikel (refereegranskat)abstract
- Digital agriculture has evolved significantly over the last few years due to the technological developments in automation and computational intelligence applied to the agricultural sector, including vineyards which are a relevant crop in the Mediterranean region. In this work, a study is presented of semantic segmentation for vine detection in real-world vineyards by exploring state-of-the-art deep segmentation networks and conventional unsupervised methods. Camera data have been collected on vineyards using an Unmanned Aerial System (UAS) equipped with a dual imaging sensor payload, namely a high-definition RGB camera and a five-band multispectral and thermal camera. Extensive experiments using deep-segmentation networks and unsupervised methods have been performed on multimodal datasets representing four distinct vineyards located in the central region of Portugal. The reported results indicate that SegNet, U-Net, and ModSegNet have equivalent overall performance in vine segmentation. The results also show that multimodality slightly improves the performance of vine segmentation, but the NIR spectrum alone generally is sufficient on most of the datasets. Furthermore, results suggest that high-definition RGB images produce equivalent or higher performance than any lower resolution multispectral band combination. Lastly, Deep Learning (DL) networks have higher overall performance than classical methods. The code and dataset are publicly available on https://github.com/Cybonic/DL_vineyard_segmentation_study.git.
|
|
