Lab 11: LIDAR Remote Sensing

Introduction:

The main purpose of this lab was to give the class an introduction on LIDAR data and how to process it.  Though this is just an introduction to LIDAR, learning how to simply process this advanced technology will put the class at a great advantage in the marketplace due to there being little to no one who knows how to process the imagery correctly and it's a ever-growing necessary skill.  Some objectives of the lab include:  retrieval and processing of surface terrain models, and processing a point cloud to create various products from it.

Methods:

The first portion of the lab had the class visualize a LIDAR point cloud in ERDAS Imagine.  The LAS files were brought in and viewed, yet ERDAS has limited LIDAR functionality when compared to ArcGIS.  

Knowing this ArcMap was opened to analyze the LIDAR data.  The first step to using LIDAR point clouds with ArcGIS is creating an LAS dataset.  The LAS dataset was created using the ArcCatalog plugin in ArcMap.  The various LAS files were then imported into the dataset and their properties were analysed to check for errors (Figure 1).  One way to perform quality assurance/quality control that was learned was to look at the Min Z and the Max Z to see if they match the expected elevation range well.  When importing the LAS files, the xy coordinate system and the z coordinate system needed to be selected.  This data was able to be found within the metadata file that came with the LAS data.

This is inside the LAS Dataset properties looking at the various LAS files that were imported into it.  (Figure 1)

From here the LAS dataset was able to be viewed in ArcMap.  At first it just appeared like several squares.  This was the different LAS files split up to reduce space.  The points automatically don't appear until zoomed in enough to help speed up processing.

At this point the LAS Dataset toolbar was explored to learn the various options for viewing and analyzing a LIDAR point cloud.  Some of these options included viewing the point cloud as a TIN or simply as elevation points.  Different side profiles of the data could also be viewed using the toolbar.

Several products were then generated using the LIDAR point cloud.  These included a digital surface model (DSM) that was generated using the first-return points, a digital terrain model (DTM) using the last return, and hillshades using both the DSM and DTM.  A LIDAR intensity image was also generated as a final product (Figure 2).

This LIDAR intensity image has a spectral signature near the NIR and is very fine in resolution.  (Figure 2)

Conclusion:

Learning how to utilize and process LIDAR data may seem like a daunting task at first but it actually isn't as complicated as some would make it seem.  ArcGIS and the the LAS Datasets within ArcGIS are rather user-friendly and useful as many different products can be generated from the LIDAR point clouds.  LIDAR is a technology that will only continue to grow in the future as demand for it will increase due to it's unparalleled precision at this time.  Possessing he skills to utilize and process LIDAR data will be invaluable to the class in the future. 

Lab 10: Object-Based Classification

Introduction:

This lab exercise was set up to teach the class how to properly perform object-based classification using eCognition, an object-based image processing tool.  Object-based classification integrates both spectral and spatial information to aid in extracting land use/land cover features from remotely sensed imagery.  Some of the objectives in this lab included:  segmenting an image into spatial and spectral clusters, selecting which of these clusters (objects) to use as training samples using a nearest neighbor classifier, and executing and refining the object-based classification output.


Methods:

As this was the first time the class had used eCognition, the first portion of the lab involved getting to know the software and then importing an image of the same study area of Eau Claire and Chippewa Counties that was classified in previous lab exercises.  A project was then created with the imagery being set using layer mixing to the 4, 3, 2 band combination that the class has become so used to.

At this point, it was time to create the different image objects (Figure 1).  This is a simple process that involved opening up the process tree and creating a new process.  Multiresolution segmentation was used along with a scale parameter of 10.  From there, the process was executed and the various objects were created.  It was possible to view the objects in several different ways including pixel view, object mean view, with or without the outline, and transparent or not.

The different objects that were created can be seen here as outlined in blue.  (Figure 1)

From here classes were created, these included:  agriculture, forest, green vegetation, urban, and water.  A nearest neighbor classifier using mean was then assigned to the classes.  Sample objects were selected  based on the classes knowledge of the spectral reflectance of the classes and the appearance of the land cover in a 4, 3, 2 band image (Figure 2).  After the samples were selected the classification was run and it was possible to review the results.

Here several green vegetation training samples and one urban training sample can be seen.  (Figure 2)

One interesting aspect of object-based classification is that it's possible to easily, manually edit objects that are known to be incorrectly classified.  After all manual editing was performed it was possible to export the result to a raster and create a map from the classified image (Figure 3).

This is the final map of the image that was classified using object-based classification.  (Figure 3)

Conclusion:

Image based classification is an interesting, newer way to perform image classification.  It is more useful in some application than other and seems to be especially customizable if the original result isn't up to a high enough quality.  eCognition is also an extremely useful and rather user-friendly software that could help make object-based classification more relevant in many future applications.