<html><head><meta http-equiv="Content-Type" content="text/html; charset=UTF-8"></head><body dir="auto"><div dir="auto">Hi Loke.</div><div dir="auto"><br></div><div dir="auto">You came up with an interesting approach. You are using the green band to complete an unsupervised classification using the Birch module in Scikit. An unsupervised classification is just that, the implementation of an algorithm without training data. </div><div dir="auto"><br></div><div dir="auto">I would suggest using your local point data from your local maxima routine as training data. You will have to come up with some logic to filter out the points that are actually palm centers, perhaps based on distance between trees. I would then use one of the supervised classification modules to run a supervised classification on the training data ( local maxima). I would also experiment with all or 2 colour bands as more data may help the classification.</div><div dir="auto"><br></div><div dir="auto">I must restate by previous comment that there is no bulletproof methodology to get 100 percent success. </div><div dir="auto"><br></div><div dir="auto">Kirk Schmidt</div><div dir="auto"><br></div><div dir="auto"><br></div><div dir="auto"><br></div><div id="composer_signature" dir="auto"><div style="font-size:12px;color:#575757" dir="auto">Sent from my Galaxy</div></div><div dir="auto"><br></div><div><br></div><div align="left" dir="auto" style="font-size:100%;color:#000000"><div>-------- Original message --------</div><div>From: Loke Jian Munn <jm.loke@klk.com.my> </div><div>Date: 2023-06-21 5:09 a.m. (GMT-04:00) </div><div>To: kirk <kirk@nortekresources.com>, qgis-user@lists.osgeo.org, Richard McDonnell <richard.mcdonnell@opw.ie> </div><div>Subject: RE: </div><div><br></div></div>
<div class="WordSection1">
<p class="MsoNormal">Hi, </p>
<p class="MsoNormal"> </p>
<p class="MsoNormal">As mention previously, I need NIR band to perform the NDVI, however my drone sensor does not record NIR band.</p>
<p class="MsoNormal"> </p>
<p class="MsoNormal">So, I trying another way which is crop counting from orthophoto with Python and Scikit Image. The whole process is geospatial as it works with raster and shapefiles and results are finally displayed on QGIS.</p>
<p class="MsoNormal"> </p>
<p class="MsoNormal">But the results I get are like below:</p>
<p class="MsoNormal"> </p>
<p class="MsoNormal"><img src="cid:com_samsung_android_email_attachmentprovider_1_1319_RAW_1687337679187" id="Picture_x0020_4" style="width:11.7395in;height:4.8229in" height="463" width="1127" onmouseover="imageMousePointerUpdate(true)" onmouseout="imageMousePointerUpdate(false)" name="com_samsung_android_email_attachmentprovider_1_1319_RAW_1687337679187"></p>
<p class="MsoNormal"> </p>
<p class="MsoNormal">After Zoom in: </p>
<p class="MsoNormal"><img src="cid:com_samsung_android_email_attachmentprovider_1_1320_RAW_1687337679187" id="Picture_x0020_5" style="width:11.75in;height:4.8333in" height="464" width="1128" onmouseover="imageMousePointerUpdate(true)" onmouseout="imageMousePointerUpdate(false)" name="com_samsung_android_email_attachmentprovider_1_1320_RAW_1687337679187"></p>
<p class="MsoNormal"> </p>
<p class="MsoNormal">May I know what’s goes wrong ? I have attached the Python code above for references. For this project, I using an Orthomosaic layer with resolution of 5cm.</p>
<p class="MsoNormal"> </p>
<p class="MsoNormal">Appreciate if you can provide me some guidelines or insights in this as this is my first time touching python and scikit.</p>
<p class="MsoNormal"> </p>
<p class="MsoNormal">Thank you.</p>
<p class="MsoNormal"> </p>
<p class="MsoNormal">Regards,</p>
<div>
<p class="MsoNormal"><b><span style="color:#005826;letter-spacing:-.3pt;mso-ligatures:standardcontextual;mso-fareast-language:ZH-TW">Loke Jian Munn</span></b><span style="font-size:12.0pt;font-family:"MS PGothic",sans-serif;mso-ligatures:standardcontextual;mso-fareast-language:ZH-TW" lang="EN-US"></span></p>
<p style="margin-bottom:3.0pt" class="MsoNormal"><span style="color:#585858;mso-ligatures:standardcontextual;mso-fareast-language:ZH-TW">Information Technology (IT) Department</span><span style="font-size:12.0pt;font-family:"MS PGothic",sans-serif;mso-ligatures:standardcontextual;mso-fareast-language:ZH-TW" lang="EN-US"></span></p>
<p class="MsoNormal"><span style="color:#585858;mso-fareast-language:ZH-TW"><img src="cid:com_samsung_android_email_attachmentprovider_1_1316_RAW_1687337679188" id="Picture_x0020_3" style="width:1.802in;height:.7604in" height="73" width="173" onmouseover="imageMousePointerUpdate(true)" onmouseout="imageMousePointerUpdate(false)" name="com_samsung_android_email_attachmentprovider_1_1316_RAW_1687337679188"></span><span style="font-size:12.0pt;font-family:"MS PGothic",sans-serif;mso-ligatures:standardcontextual;mso-fareast-language:ZH-TW" lang="EN-US"></span></p>
<p style="margin-top:6.0pt" class="MsoNormal"><b><span style="font-size:9.5pt;color:#005826;letter-spacing:-.2pt;mso-ligatures:standardcontextual;mso-fareast-language:ZH-TW">KUALA LUMPUR KEPONG BERHAD</span></b><span style="font-size:12.0pt;font-family:"MS PGothic",sans-serif;mso-ligatures:standardcontextual;mso-fareast-language:ZH-TW" lang="EN-US"></span></p>
<p style="line-height:95%" class="MsoNormal"><span style="font-size:9.5pt;line-height:95%;color:#585858;letter-spacing:-.1pt;mso-ligatures:standardcontextual;mso-fareast-language:ZH-TW">Wisma Taiko,</span><span style="font-size:12.0pt;line-height:95%;font-family:"MS PGothic",sans-serif;mso-ligatures:standardcontextual;mso-fareast-language:ZH-TW" lang="EN-US"></span></p>
<p style="line-height:95%" class="MsoNormal"><span style="font-size:9.5pt;line-height:95%;color:#585858;letter-spacing:-.1pt;mso-ligatures:standardcontextual;mso-fareast-language:ZH-TW">No. 1, Jalan S.P. Seenivasagam,</span><span style="font-size:12.0pt;line-height:95%;font-family:"MS PGothic",sans-serif;mso-ligatures:standardcontextual;mso-fareast-language:ZH-TW" lang="EN-US"></span></p>
<p style="line-height:95%" class="MsoNormal"><span style="font-size:9.5pt;line-height:95%;color:#585858;letter-spacing:-.1pt;mso-ligatures:standardcontextual;mso-fareast-language:ZH-TW">30000 Ipoh,Perak Darul Ridzuan,Malaysia</span><span style="font-size:12.0pt;line-height:95%;font-family:"MS PGothic",sans-serif;mso-ligatures:standardcontextual;mso-fareast-language:ZH-TW" lang="EN-US"></span></p>
<p style="line-height:95%" class="MsoNormal"><b><span style="font-size:9.5pt;line-height:95%;color:#005826;mso-ligatures:standardcontextual;mso-fareast-language:ZH-TW">T :
</span></b><span style="font-size:9.5pt;line-height:95%;color:#585858;letter-spacing:-.1pt;mso-ligatures:standardcontextual;mso-fareast-language:ZH-TW">+605 240 8000 (ext. 2443)</span><span style="font-size:12.0pt;line-height:95%;font-family:"MS PGothic",sans-serif;mso-ligatures:standardcontextual;mso-fareast-language:ZH-TW" lang="EN-US"></span></p>
<p style="margin-top:4.0pt;line-height:85%" class="MsoNormal"><a href="https://clicktime.symantec.com/15tpDKjABDCCmu4drBEZD?h=4-LzQeEUOcKmp7sCwswGafke694l_dZCDQJ4Rb8N8bc=&u=http://www.klk.com.my/"><span style="font-size:9.5pt;line-height:85%;color:#585858;mso-fareast-language:ZH-TW;text-decoration:none"><img alt="A close up of a sign
Description automatically generated" src="cid:com_samsung_android_email_attachmentprovider_1_1317_RAW_1687337679189" id="Picture_x0020_19" style="width:1.052in;height:.1354in" height="13" width="101" border="0" onmouseover="imageMousePointerUpdate(true)" onmouseout="imageMousePointerUpdate(false)" name="com_samsung_android_email_attachmentprovider_1_1317_RAW_1687337679189"></span></a><a href="https://clicktime.symantec.com/15tpJ9vSdpsoBqtZPjdhq?h=bX-LFOj0HrSJV_t-3L_WhMP3i5PRx5AtNBaHlI02C7k=&u=http://www.linkedin.com/company/klkberhad"><b><span style="font-size:9.5pt;line-height:85%;color:#005826;letter-spacing:-.2pt;mso-fareast-language:ZH-TW;text-decoration:none"><img alt="A close up of a sign
Description automatically generated" src="cid:com_samsung_android_email_attachmentprovider_1_1318_RAW_1687337679190" id="Picture_x0020_27" style="width:.6041in;height:.1354in" height="13" width="58" border="0" onmouseover="imageMousePointerUpdate(true)" onmouseout="imageMousePointerUpdate(false)" name="com_samsung_android_email_attachmentprovider_1_1318_RAW_1687337679190"></span></b></a><span style="font-size:12.0pt;line-height:85%;font-family:"MS PGothic",sans-serif;mso-ligatures:standardcontextual;mso-fareast-language:ZH-TW" lang="EN-US"></span></p>
</div>
<p class="MsoNormal"> </p>
<div>
<div style="border:none;border-top:solid #E1E1E1 1.0pt;padding:3.0pt 0cm 0cm 0cm">
<p class="MsoNormal"><b><span lang="EN-US">From:</span></b><span lang="EN-US"> kirk <kirk@nortekresources.com>
<br>
<b>Sent:</b> Tuesday, 6 June, 2023 6:09 PM<br>
<b>To:</b> Loke Jian Munn <jm.loke@klk.com.my>; qgis-user@lists.osgeo.org<br>
<b>Subject:</b> </span></p>
</div>
</div>
<p class="MsoNormal"> </p>
<div>
<div>
<p class="MsoNormal">Hi Loke</p>
</div>
<div>
<p class="MsoNormal"> </p>
</div>
<div>
<p class="MsoNormal">Richard suggested using a NDVI approach which would require data in the Near Infrared (NIR) band. An orthomisaic would contain 3 colour bands, but not the NIR. NDVI provides an understanding of plant greenness and health and may not be
suitable for detecting oil palm's. </p>
</div>
<div>
<p class="MsoNormal"> </p>
</div>
<div>
<p class="MsoNormal">If you are getting 90 percent plus with your current approach , you may find that you will spend 4 times longer capturing the additional 10 percent. </p>
</div>
<div>
<p class="MsoNormal"> </p>
</div>
<div>
<p class="MsoNormal">NIR data,are available from various satellite sensors however, their resolution would not work at the individual plant level.</p>
</div>
<div>
<p class="MsoNormal"> </p>
</div>
<div>
<p class="MsoNormal">Some drone sensors record the NIR band.</p>
</div>
<div>
<p class="MsoNormal"> </p>
</div>
<div>
<p class="MsoNormal">Kirk Schmidt</p>
</div>
</div>
<div>
<p class="MsoNormal"> </p>
</div>
<div>
<p class="MsoNormal"> </p>
</div>
<div>
<p class="MsoNormal"> </p>
</div>
<div id="composer_signature">
<div>
<p class="MsoNormal"><span style="font-size:9.0pt;color:#575757">Sent from my Galaxy</span></p>
</div>
</div>
<div>
<p class="MsoNormal"> </p>
</div>
</div>
<br>
DISCLAIMER : This email and any attachments are confidential and intended solely for the addressee. If you are not the intended recipient, any disclosure, copying, distribution either whole or partial, is prohibited and may be unlawful. In such case, please
delete this message and kindly notify the sender. <br>
<b>Kuala Lumpur Kepong Berhad </b>
</body></html>