3) vs. 
in the 
ble rate 
Table 3, 
olication 
as set to 
eal-time 
nd 71% 
provide 
f a map- 
'hemical 
Is in the 
rat 69.3 
% weed 
In other 
f saving 
periment 
Plot 1 
Plot 2 
4, CONCLUSIONS AND RECOMMENDATIONS 
The study showed that the spatial variations in weed density 
within a soybean field could be mapped using CIR digital aerial 
images in the earlier stages of crop growth. The correlation 
coefficient between image data and weed data varied with 
resolution. The maximum correlation coefficients (greater than 
0.85) between weed map data and remote sensing image data 
were found at 4.5-m/pixel resolution. Further studies are required 
to investigate the effect of other field specific factors such as the 
relative variability in weed density, weed size etc. and the sensor 
specific factors such as spatial and spectral resolution on the 
optimal spatial resolution for weed mapping. 
The best time for weed mapping should also be selected based on 
the critical time for weed control. A high spatial and spectral 
resolution will be help to identify weeds from soil background 
and crop, at early stages of crop growth. 
This work also showed that selective and variable-rate herbicide 
application methods had advantages over the uniform application 
method. The variable rate method had greater advantages when 
the weed density variation was high. 
5. ACKNOWLEDGMENTS 
This research has been supported by the Illinois Council of Food 
and Agricultural Research (C-FAR), Project Number 971-124-3. 
Special thanks to several of the author's former and current 
graduate students: B. Steward, L. Tang, S. Bajwa, and 
undergraduate student workers: M. Porter, A. Gemeny, etc. They 
participated in the system design, retrofitting works and field 
experiments. 
6. REFERENCES 
Andreasen, C., M. Rudemo, and S. Sevestre. 1997. Assessment of 
weed density at an early stage by use of image processing. Weed 
Research 37 (1): 5-18. 
Brivot, R, and J. A. Marchant. 1996. Segmentation of plants and 
weeds for a precision crop protection robot using infrared images. 
IEEE Proceedings Vision, Image and Signal Processing 143 (2): 
118-124. 
Cardina, J., G. A. Johnson and D. H. Sparrow. 1997. The nature 
and consequence of weed spatial distribution. Weed Science. 45: 
364-373. 
Gopalapillai, S. 2000. Remote sensing for precision agriculture: 
Within-field variability analysis and mapping with aerial digital 
multispectral images. Unpublished thesis, University of Illinois at 
Urbana-Champaign, USA. 
IAPRS & SIS, Vol.34, Part 7, “Resource and Environmental Monitoring", Hyderabad, India, 2002 
Hanks, J. E. 1996. Smart sprayer selects weeds for elimination. 
Agricultural Research. 44 (4): 15. 
. 
Heisel, T., C. Andreasen, and A. K. Ersboll. 1996. Annual weed 
distribution can be mapped with kriging. Weed Research 36 (4): 
325-337. 
Lee, W. and D. C. Slaughter. 1998. Plant recognition using 
hardware-based neural network. ASAE paper No. 983040. 
National Research Council. 1997. Precision Agriculture in the 
21st Century — Geospatial and Information Technologies in Crop 
Management. National Academy Press, Washington D.C. 
Oriade, C. A., R. P. King, F. Forcella, and J. L. Gunsolus. 1996. 
A bioeconomic analysis of site-specific management for weed 
control. Review of Agricultural Economics 18 (4):523-535. 
Rew, L. J., G. W. Cussans, M. A. Mugglestone, and P. C. H. 
Miller. 1996. A technique for mapping the spatial distribution of 
Elymus repens, with estimates of the potential reduction in 
herbicide usage from patch spraying. Weed Research 36 (4):283- 
292. 
Shearer, S. A. and P. T. Jones. 1991. Selective application of 
post-emergence herbicides using photoelectrics. Transactions of 
the ASAE 34 (4): 1661-1666. 
Stafford, J. V., J. M. Le Bars, and B. Ambler. 1996. A hand-held 
data logger with integral GPS for producing weed maps by field 
walking. Computers and Electronics in Agriculture 14 (3): 235- 
247. 
Steward, B. L. and L. F. Tian. 1999. Machine vision weed 
density estimation for real-time outdoor lighting conditions. 
Transactions of the ASAE 42 (6): 1897-1909. 
Tang, L., L. F. Tian, and B. L. Steward. 1999. Machine vision 
based high-resolution weed mapping and  patch-sprayer 
performance simulation, International Off-Highway & 
Powerplant Congress & Exposition 1999, Indianapolis, IN, SAE 
Paper no. 1999-01-2849, SAE, Warrendale, PA. 
Tian, L., D. C. Slaughter and R. F. Norris. 1997. Outdoor field 
machine vision identification of tomato seedlings for automated 
weed control. Transactions of the ASAE 40 (6): 1761-1768. 
Tian, L., J. F. Reid, and J. Hummel. 1999. Development of a 
precision sprayer for site-specific weed management. 
Transactions of the ASAE 42(4):893-900.