George E. Meyer

Shape Features for Identifying Young Weeds Using Image Analysis

Shape feature analyses were performed on binary images originally obtained from color images of 10 common weeds, along with corn and soybeans, found in the Midwest. Features studied were roundness, aspect, perimeter/thickness, elongatedness, and seven invariant central moments (ICM), for each plant type and age up to 45 days after emergence. Shape features were generally independent of plant size, image rotation, and plant location within most images. The ability to discriminate between monocots and dicots was most evident between 14 and 23 days using these features. Shape features that best distinguished these plants were aspect and first invariant central moment (ICM1), which classified 60 to 90% of the dicots from the monocots. Using Analysis of Variance and Tukey’s multiple comparison tests, shape features did not change significantly for most species over the study period. This information could be very useful in the future design of advanced spot spraying applications.

Textural imaging and discriminant analysis for distinguishing weeds for spot spraying

Advanced computer vision and statistical methods were employed for identifying living plants from soil/ residue background for two species of grasses (Shattercane, Green Foxtail) and two broadleaf species (Velvetleaf, Red Root Pigweed) weeds. The excess green index method was used as a contrast enhancement for specifically identifying plant from soil regions. Excess green classified plant and soil regions correctly over the entire three-week observation period with high accuracies (99% plus). Plant and soil binary images were derived from excess green images and provided edge boundaries. These boundaries were used with corresponding gray scale images to extract four classical textural features for plants and soil: angular second moment, inertia, entropy, and local homogeneity. These features were derived from the co-occurrence matrix. Stepwise and canonical discriminant analyses were used to test the classification performance of the texture and excess green features. Discrimination models of local homogeneity, inertia, and angular second moment were found to classify grass and broadleaf categories of plants, with classification accuracies of 93 and 85%, respectively. Classification accuracies of individual species only ranged from 30 to 77%. Soil classification accuracies were also high for textural feature algorithms (97%). The time required to produce tokensets ranged from 15 to 20 s on a UNIX computer system. Additional time required for the system to reach a plant/soil classification ranged from 5 to 10 s. This translated into an overall system response time of 20 to 30 s, with the preprocessing step constituting the major part of the system response time.

Machine vision detection parameters for plant species identification

Machine vision based on classical image processing techniques has the potential to be a useful tool for plant detection and identification. Plant identification is needed for weed detection, herbicide application or other efficient chemical spot spraying operations. The key to successful detection and identification of plants as species types is the segmentation of plants form background pixel regions. In particular, it would be beneficial to segment individual leaves form tops of canopies as well. The segmentation process yields an edge or binary image which contains shape feature information. Results indicate that red-green-blue formats might provide the best segmentation criteria, based on models of human color perception. The binary image can be also used as a template to investigate textural features of the plant pixel region, using gray image co-occurrence matrices. Texture features considers leaf venation, colors, or additional canopy structure that might be used to identify various type of grasses or broadleaf plants.

Plant species identification, size, and enumeration using machine vision techniques on near-binary images

Shape parameters such as aspect, roundness, and the ratio of thickness to perimeter were used to describe plant shape and are different according to the species that they represent. Color slide images of several species of plants were digitized for computer analysis. Three optical methods were tested to separate target plants from the soil and residue background. The separation method that provided the best contrast was the normalized difference index. Subtracting the blue or the red raster from the green raster also provided good separation on soils with little residue. Once the plant image had been isolated from the background, leaf edges were automatically traced using a commercial software package. Analysis of the shape of the plant outline was then performed, resulting in the plant shape parameters. Grasses and broadleaf plants had similar values for each shape parameter during the first ten days after emergence. After this period, differences occurred between grasses and broadleaf plants. The parameter that best discriminated grasses from broadleaf plants was the aspect (major axis length/minor axis length). However, when a grass sends out more than one shoot radially from the stem, the aspect will be similar to broadleaf plants. This study contributes to the design of a system that can determine weed populations and identify plant species without the use of human intervention.

A crop water stress index for tall fescue (Festuca arundinacea Schreb.) irrigation decision-making — a traditional method

Abstract A high irradiance plant growth chamber was used to study crop water stress indices (CWSI) and baselines with increasing soil water deficit for Tall Fescue (Festuca arundinacea Schreb.). Canopy temperatures for turf plugs were continuously measured with infrared thermometers, along with plant water use, measured with electronic mini-lysimeters. Net radiation, canopy and air temperatures, and vapor pressure deficit (VPD) levels were recorded and analyzed statistically. The canopy–air temperature differential (Tc−Ta) increased with a decrease in soil moisture content. Tc−Ta increased as net radiation became greater, independent of soil water deficit. Canopy temperature of well-watered plants decreased at rate of 2.4°C for each 1 kPa reduction in air vapor pressure deficit for all net radiation levels. For each 100 Wm−2 increase in net radiation, canopy temperature of well-watered plants increased at a rate of 0.6°C and was well correlated (well-watered baseline) with VPD. Increases in canopy temperature coupled with a decrease in transpiration rate were hallmark signs of water stress progression. However, (Tc−Ta) and VPD baseline relationships correlated poorly for moderate-stress and severe stress conditions regardless of net radiation levels. Thus, even with the increased precision and replications of a controlled environment study, lower limit crop water stress baselines were quite variable.

Decreased nasal mucosal sensitivity in older subjects

Background The sensitivity of the human nasal cavity mucosa to touch is not well understood. The site of receptors and mode of action responsible for the sensation of the nasal airflow is a topic of controversy. Previous studies have suggested that the skin-lined nasal vestibule is more sensitive to airflow than the mucosa of the nasal cavity. A possible decline in nasal sensitivity to airflow in older subjects has not been studied. Methods The threshold of the mucosal sensitivity to jets of air was assessed in 76 subjects with healthy nasal cavities. A total of 141 nostrils were tested, 67 in younger patients and 74 in older patients. Results Statistically significant (p < 0.001) increases in thresholds were found for all points tested for older patients compared with the younger patients. In general, the more sensitive locations were in the nasal vestibule. The nasal cavity mucosa in the inferior meatus was slightly more sensitive than the middle meatus. Conclusion We have measured the threshold to touch (air jet sensitivity) in nine places in each of 141 nasal cavities and determined that the variability and sensitivity of these measurements among people varies by age and the distance from the nostril. Older subjects were found to have a higher threshold for the sensation of air flow, and the nasal vestibule was found to be more sensitive than the rest of the nasal cavity mucosa with the inferior meatus slightly more sensitive then the middle meatus.

DIGITAL CAMERA OPERATION AND FUZZY LOGIC CLASSIFICATION OF UNIFORM PLANT, SOIL, AND RESIDUE COLOR IMAGES

Low-cost, consumer grade cameras have been used in recent machine vision studies. Users are faced with a choice of manual or automatic operations for obtaining quality images for classifying plant, soil, and residue for field maps and precision agriculture. A digital camera operations study was conducted for classifying uniform images of grass, bare soil, corn stalks residue, wheat straw residue, and a barium sulfate reference panel, based on color. Both natural and artificial background lighting was studied. Classifications were conducted with fuzzy inference systems, built with subtractive clustering, an Adaptive-Network Fuzzy Inference System (ANFIS) and ten-fold cross-validation. Each image was labeled with an integer for classification and reference. Classification systems contained from 5 to 36 rules. Rules for automatic digital camera operation were well trained (r2 > 0.94), with low root-mean-square errors (RMSE < 0.2). Manual digital camera operation gave lower training correlations (r2 3). Since predicted classification values were not integral, Zadeh’s principle of maximum membership was used for final classification using trained output membership functions. Correct classification rates (CCR) for manual camera operation were low (<64%), and only slightly improved by eliminating over- and underexposed and monochromatic-lit images. The automatic digital camera provided better classification rates (>>81%). Independent background lighting luminosity and color temperature measurements did not significantly improve classification. The results suggest that low-cost, digital cameras used in automatic mode would be best for remote sensing and site-specific crop management use.

Some Perspectives on Recent In Situ Air Temperature Observations: Modeling the Microclimate inside the Radiation Shields*

Abstract Air temperature measurement has inherent biases associated with the particular radiation shield and sensor deployed. The replacement of the Cotton Region Shelter (CRS) with the Maximum–Minimum Temperature System (MMTS) and the introduction of Automated Surface Observing System (ASOS) air temperature observing systems during the NWS modernization introduced bias shifts in federal networks that required quantification. In rapidly developing nonfederal networks, the Gill shield temperature systems are widely used. All of these systems house an air temperature sensor in a radiation shield to prevent radiation loading on the sensors; a side effect is that the air temperature entering a shield is modified by interior solar radiation, infrared radiation, airspeed, and heat conduction to or from the sensor so that the shield forms its own interior microclimate. The objectives of this study are to develop an energy balance model to evaluate the microclimate inside the ASOS, MMTS, Gill, and CRS shields, in...

Electronic Image Analysis of Crop Residue Cover on Soil

ABSTRACT CLASSIFICATION procedures for using both black-and-white and color imaging systems were developed and tested for determination of percent residue cover on the soil surface from video and slide images. A spectral analysis of the image components was used for determining applicable wavelengths and filters. Color imagery provided an acceptable replacement for manual visual procedures. Black-and-white imagery also worked when appropriate blocking filters were used.

Crop species identification using machine vision of computer extracted individual leaves

An unsupervised method for plant species identification was developed which uses computer extracted individual whole leaves from color images of crop canopies. Green canopies were isolated from soil/residue backgrounds using a modified Excess Green and Excess Red separation method. Connected components of isolated green regions of interest were changed into pixel fragments using the Gustafson-Kessel fuzzy clustering method. The fragments were reassembled as individual leaves using a genetic optimization algorithm and a fitness method. Pixels of whole leaves were then analyzed using the elliptic Fourier shape and Haralicks classical textural feature analyses. A binary template was constructed to represent each selected leaf region of interest. Elliptic Fourier descriptors were generated from a chain encoding of the leaf boundary. Leaf template orientation was corrected by rotating each extracted leaf to a standard horizontal position. This was done using information provided from the first harmonic set of coefficients. Textural features were computed from the grayscale co-occurrence matrix of the leaf pixel set. Standardized leaf orientation significantly improved the leaf textural venation results. Principle component analysis from SAS (R) was used to select the best Fourier descriptors and textural indices. Indices of local homogeneity, and entropy were found to contribute to improved classification rates. A SAS classification model was developed and correctly classified 83% of redroot pigweed, 100% of sunflower 83% of soybean, and 73% of velvetleaf species. An overall plant species correct classification rate of 86% was attained.