Shape Description of Completely Visible and Partially Occluded Leaves for Identifying Plants in Digital Images

Franz, Elke; Gebhardt, M. R.; Unklesbay, K.

doi:10.13031/2013.31716

Cited by 53 publications

(25 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Plant identification has been accomplished with the use of shape features of plants (Franz et al, 1991a;Guyer et al, 1993;Bezenek, 1994;Woebbecke et al, 1992Woebbecke et al, , 1995Zhang and Chaisattapagon, 1995), textural information from images of crop canopy and plant leaves (Shearer and Holmes, 1990;Dave and Runtz, 1995;Zhang and Chaisattapagon, 1995;Meyer et al, 1998), spectral information (Franz et al, 1991b;Zhang and Chaisattapagon, 1995), and fractal analysis of leaf shapes (Critten, 1996;Dave and Runtz, 1995).…”

mentioning

confidence: 99%

Machine-Vision Weed Density Estimation for Real-Time, Outdoor Lighting Conditions

Steward

Tian

1999

Transactions of the ASAE

View full text Add to dashboard Cite

show abstract

mentioning

confidence: 99%

Machine-Vision Weed Density Estimation for Real-Time, Outdoor Lighting Conditions

Steward

Tian

1999

Transactions of the ASAE

View full text Add to dashboard Cite

show abstract

“…Recent works by Lee and Chen ( 2006 ) and Du et al ( 2007 ) give examples of 2D object shape features useful in leaf shape characterization and demonstrate the performance of a shape feature classifi er on sets of 60 and 20 plant species, respectively, using 2D images of individual leaves. A number of studies have been published on the use of leaf boundary curvature from individual 2D leaf images for plant species recognition (e.g., Franz et al 1991 ;Chi et al 2002 ). As an example of a recent work in an agricultural context, Neto et al ( 2006 ) used elliptic Fourier descriptors of a closed contour of the leafl et edge calculated from the 2D chain code of the 2D image to classify soybean, sunfl ower, and two weed species.…”

Section: Individual Leaf Shape Sensorsmentioning

confidence: 99%

“…Two common factors leading to degraded machine vision performance in shape recognition are the visual occlusion of leaf shape due to overlapped leaves and the nonoptimal display of leaf shape for automated machine vision methods when the leaves are still attached to the plant and photographed in situ. Franz et al ( 1991 ) conducted one of the few studies that has characterized the impact of nonideal leaf pose (i.e., where the leaf is tilted away from the ideal image plane) and the loss of leaf shape information due to leaf occlusion (i.e., where part of the leaf is hidden behind another object, typically another part of the plant) when the species template database comes from the ideal pose (i.e., Fig. 5.2a ).…”

Section: Individual Leaf Shape Sensorsmentioning

confidence: 99%

The Biological Engineer: Sensing the Difference Between Crops and Weeds

Slaughter

2013

Automation: The Future of Weed Control in Cropping Systems

View full text Add to dashboard Cite

This chapter describes the current state of the art in technology and methodology being used to develop sensors for automated weed control in cropping systems. The development of a reliable universal weed vs. crop plant sensor that works well in a wide range of crops and cropping systems is a formidable task. The discussion in this chapter highlights the signifi cant progress that has been made in developing new, more robust, automatic sensing systems that can differentiate crop plants from weeds. Case studies documenting high levels of success in trials conducted outdoors in the natural, largely uncontrolled environment of an agricultural cropping system are presented. A discussion of the strengths and current challenges of the more successful weed and crop sensing techniques is provided. In many cases the methodology has utilized site-or condition-specifi c a priori knowledge to make the sensors smarter in a local context. This chapter highlights the advantages and compromises made in using these techniques. The chapter concludes with a discussion of the remaining engineering challenges to the development of a comprehensive, multifaceted fusion of several methods for sensing the differences between crops and weeds across the entire crop production cycle, and how the rapid development of advanced sensing and machine learning technologies will facilitate new plant recognition architectures and systems to achieve the level of machine recognition of weeds needed for automated weed control in cropping systems.

show abstract

“…), which are key to the interpretation process. Current computerbased digital interpretation processes depend largey on colour and tone (Gougeon 1995), although efforts are being made to involve texture and shape (Franz et al 1991). Spatial resolution requirements are not yet well defied for these digital interpretation processes (see Research and Development Directions below).…”

Section: Spatial Detail Resolvedmentioning

confidence: 99%

“…Auto-interpretation techniques based on crown shape are currently being developed for mature forest trees (Franz et al 1991;Gougeon 1992Gougeon ,1995Pollock 1994a,b). Although results to date are promising, complete success may not be achieved until additional feature processing algorithms, based on texture and branching structure, are included.…”

Section: Research and Development Directionsmentioning

confidence: 99%

Use of remote sensing for forest vegetation management: A problem analysis

Pitt¹,

Wagner²,

Hall³

et al. 1997

The Forestry Chronicle

View full text Add to dashboard Cite

k i e~ and Ulf ~u n e s s o n~ Forest managers require accurate and timely data that describe vegetation conditions on cutover areas to assess vegetation development and prescribe actions necessary to achieve forest regeneration objectives. Needs for such data are increasing with current emphasis on ecosystem management, escalating silvicultural treatment costs, evolving computer-based decision support tools, and demands for greater accountability. Deficiencies associated with field survey methods of data acquisition (e.g. high costs, subjectivity, and low spatial and temporal coverage) frequently limit decision-making effectiveness. The potential for remotely sensed data to supplement field-collected forest vegetation management data was evaluated in a problem analysis consisting of a comprehensive literature review and consultation with remote sensing and vegetation management experts at a national workshop. Among curently available sensors, aerial photographs appear to offer the most suitable combination of characteristics, including high spatial resolution, stereo coverage, a range of image scales, a variety of film, lens, and camera options, capability for geometric correction, versatility, and moderate cost. A flexible strategy that employs a sequence of 1: 10,000-, 1 5,000-, and 1:500-scale aerial photographs is proposed to: 1) accurately map cutover areas, 2) facilitate location-specific prescriptions for silvicultura1 treatments, sampling, buffer zones, wildlife areas, etc., and 3) monitor and document conditions and activities at specific points during the regeneration period. Surveys that require very detailed information on smaller plants (<0.5-m tall) andlor individual or rare plant species are not likely to be supported by current remote sensing technologies. Recommended areas for research include: 1) digital frame cameras, or other cost-effective digital imagers, as replacements for conventional cameras, 2) computer-based classification and interpretation algorithms for digital image data, 3) relationships between image measures and physical measures, such as leaf-area index and biomass, 4) imaging standards, 5) airborne video, laser altimeters, and radar as complementary sensors, and 6) remote sensing applications in partial cutting systems.

show abstract

Shape Description of Completely Visible and Partially Occluded Leaves for Identifying Plants in Digital Images

Cited by 53 publications

References 0 publications

Machine-Vision Weed Density Estimation for Real-Time, Outdoor Lighting Conditions

Machine-Vision Weed Density Estimation for Real-Time, Outdoor Lighting Conditions

The Biological Engineer: Sensing the Difference Between Crops and Weeds

Use of remote sensing for forest vegetation management: A problem analysis

Contact Info

Product

Resources

About