Spectral Weed Detection and Precise Spraying

1
Spectral Weed Detectionand Precise Spraying

• Laboratory of AgroMachinery and Processing
• Els Vrindts, Dimitrios Moshou, Jan ReumersHerman
  Ramon, Josse De Baerdemaeker

Research sponsored by IWT and the Belgian
Ministry of Small Trade and Agriculture
2
Overview

• Spectral measurements of crops and weeds
• in laboratory
• in field
• Processing of spectral data with neural networks
• Precise spraying

3
Optical detection of weeds

• Techniques
• red/NIR detectors (vegetation index)
• image processing (color, texture, shape)
• remote sensing of weed patches
• reflection in visible NIR light
• different detection possibilities, different
  scales
• Requirements for on-line weed detection
• fast accurate weed detection
• synchronized with treatment

4
Spectral weed detection

• Factors affecting spectral plant signals
• leaf reflection, dependent on species and
  environment, stress, disease
• canopy measurement geometry
• light conditions
• detector sensitivity

5
Spectral analysis of plant leavesin laboratory
Laboratory measurements
Diffuse Reflectance Spectroscopy of Crop and Weed
Leaves
6
Diffuse Reflectance of a Leaf
Laboratory measurements
7
Spectral Dataset
Laboratory measurements
8
Reflectance of crop and weed leaves
Laboratory measurements
9
Spectral analysis
Laboratory measurements

• stepwise selection of discriminant wavelengths
• multivariate discriminant analysis, based on
  reflectance response at selected wavelengths
  (dataset a)
• assuming multivariate normal distribution
• quadratic discriminant rule
• classes with different covariance structure
• testing the discriminant function classification
  of spectra from dataset b

10
Spectral response of beet weeds
Laboratory measurements
11
Spectral response of maize weeds
Laboratory measurements
12
Spectral response of potato weeds
Laboratory measurements
13
Classification results
Laboratory measurements
14
Field measurement of crop and weeds
Field measurements
Signal path
Processingmethod
Variation inlight condition
Detector sensitivity
Measurement geometry
15
Equipment for field measurement
Field measurements
spectrograph 10-bit CCD, digital
camera, computer, 12 V battery and transformer on
mobile platform
16
Equipment - Spectrograph
Field measurements
both spatial and spectral information in images
17
Image data
Field measurements

• maize, sugarbeet, 11 weeds
• 2 different days, different light conditions
• 755 x 484 pixels

18
Spectral response of sensor
Field measurements
19
Data processing
Field measurements

• spectral resolution 0.71 nm /pixel
• plant/soil discrimination with ratio NIR (745
  nm) / red (682 nm)
• data reduction by calculating average per 2.1 nm,
  removing noisy ends
• resulting spectra 484.8 - 814.6 nm range, 2.1 nm
  step
• independent datasets of maize, sugarbeet and weeds

20
Spectral datasets
Field measurements
21
Mean canopy reflections
Field measurements
22
Canonical analysis of Sugarbeet - weeds
Field measurements
23
Canonical analysis of Maize - weeds
Field measurements
24
Discriminant analysis Sugarbeet
Field measurements
25
Discriminant analysis Maize
Field measurements
26
Graphic comparison datasets
Field measurements
27
Graphic comparison datasets
Field measurements
28
Graphic comparison datasets
Field measurements
29
Discriminant analysis ratiosSugarbeet
Field measurements
30
Discriminant analysis ratiosMaize
Field measurements
31
Results
Field measurements

• only spectral info (485-815 nm)
• classification based on narrow bands in
  discriminant functions
• good results in similar light and crop conditions
• large decrease in performance for other light
  conditions
• using ratios of narrow bands
• improvement, but not sufficient

32
Improving results
Field measurements

• influence of light conditions
• adaption of classification rule
• determining light condition and applying
  appropriate calibration/LUT
• spectral inputs that are less affected by
  environment
• measuring irradiance, calculating reflectance
• other classification methods

33
Neural network for classification
Crop-weed classification

• Comparison of different NN techniques for
  classification
• Self-Organizing Map (SOM) neural network for
  classification
• used in a supervised way for classification
• neurons of the SOM are associated with local
  models
• achieves fast convergence and good
  generalisation.

34
Neural network for classification
Crop-weed classification
SOM
MLP
PNN

• ADVANTAGES
• Learns with reduced
• amounts of data
• Fast Learning
• Visualisation
• Retrainable
• DISADVANTAGES
• Discrete output

• ADVANTAGES
• Good extrapolation
• DISADVANTAGES
• Slow Learning
• Local minima
• Needs a lot of data

• ADVANTAGES
• Fast Learning
• Retrainable
• DISADVANTAGES
• Needs all training data
• during operation
• Needs a lot of data

35
Comparison between methods
Crop-weed classification
MLP Multi-Layer Perceptron, PNN Probabilistic N
Network, SOM Self-Organizing Map, LVQ Learning
Vector Qantization, LLM Local Linear Mapping
Moshou et al., 1998, AgEng98, Oslo Moshou et al.,
2001, Computers and Electronics in Agriculture 31
(1) 5-16
36
Crop-weed classification
Comparison between methods
MLP Multi-Layer Perceptron, PNN Probabilistic N
Network, SOM Self-Organizing Map, LVQ Learning
Vector Qantization, LLM Local Linear Mapping
37
Crop-weed classification
Comparison between methods
MLP Multi-Layer Perceptron, PNN Probabilistic N
Network, SOM Self-Organizing Map, LVQ Learning
Vector Qantization, LLM Local Linear Mapping
38
Conclusions on LLM SOM technique
Crop-weed classification

• The strongest point is the local representation
  of the data accompanied by a local updating
  algorithm
• Local updating algorithms assure much faster
  convergence than global updating algorithms (e.g.
  backpropagation for MLPs)
• Because of the topologically preserving
  character of the SOM, the proposed classification
  method can deal with missing or noisy data,
  outperforming optimal classifiers (PNN)
• The proposed method has been tested and gave
  superior results compared to a variety
  statistical and neural classifiers

39
Precision spraying through controlled dose
application
Precision treatment
Unwanted variations in dose caused by horizontal
and vertical boom movements
40
Active horizontal stabilisation of spray boom
Precision treatment

• Validation with ISO 5008 track
• movement of spray boom tip with and without
  controller

41
Vertical stabilisation of spray boom
Precision treatment
Slow-active system for slopes
Resulting boom movement
42
On-line selective weed treatment
Precision treatment
Indoor test of on-line weed detection and
treatment
43
Indoor test of on-line weed detection and
treatment
Precision treatment

• Sensor Spectral line camera
• Classification Probabilistic neural network
• Program in Labview with c-code
• Image acquisition frequence 10 images/sec,
  travel speed 30cm/sec, segmentation with NDVI (
  gt 0.3)
• Off-line training of NN, On-line classification
• Decision to spray
• gt 20 weed pixels and gt 35 of vegetation is weed
• Spray boom with PWM nozzles and controller,
  provided by Teejet Technologies

44
Indoor test of on-line weed detection and
treatment
Precision treatment

• Color image and spectral image

45
Indoor test - Results
Precision treatment

• Comparison of nozzle activation with weed
  positions

46
Indoor test - Results
Precision treatment

• separate weed classes (4) did not improve
  crop-weed classification
• Correct detection of nearly all weeds
• Only 6 redundant spraying of crop
• Up to 70 reduction of herbicide use

Experimental set up
camera
nozzle
weed