Difference between revisions of "Mandi Assignment Final Answer"

From Visual Analytics and Applications
Jump to navigation Jump to search
Line 24: Line 24:
 
[[File:Lake.JPG|600px]]
 
[[File:Lake.JPG|600px]]
 
[[File:Axis_Image.jpg|600px]] <br />
 
[[File:Axis_Image.jpg|600px]] <br />
Hence, the length of a pixel is 3000/(504 - 475+1) ft, equals to 1000 ft.
+
Hence, the length of a pixel is 3000/(504 - 475+1) ft, equals to 100 ft. Then the area of one pixel is 100 * 100 = 10000 square ft. <br />
 +
As the satellite image has 651*651 pixels, the actual scale of the region is 651*651*10000 square ft = 4,238,010,000 square ft.
 +
The orientation of the satellite image is oriented north-south.
 +
 
 
'''2. Features in the Preserve area as captured in the imagery.''' <br />
 
'''2. Features in the Preserve area as captured in the imagery.''' <br />
 
Most of the images have sensor artifacts at the bottom right corner.
 
Most of the images have sensor artifacts at the bottom right corner.

Revision as of 23:50, 7 July 2017

VAST Challenge 2017 MC 3

Introduction

Data Preparation

Analysis Procedure

Final Answer


Questions:

1. The scale and orientation of the supplied satellite images.
Identified the location and coordinates of the Boonsong Lake in the satellite image as below:
Lake.JPG Axis Image.jpg
Hence, the length of a pixel is 3000/(504 - 475+1) ft, equals to 100 ft. Then the area of one pixel is 100 * 100 = 10000 square ft.
As the satellite image has 651*651 pixels, the actual scale of the region is 651*651*10000 square ft = 4,238,010,000 square ft. The orientation of the satellite image is oriented north-south.

2. Features in the Preserve area as captured in the imagery.
Most of the images have sensor artifacts at the bottom right corner. To identify the features in the Preserve Area, I picked the image which is generated from the data [image11_2016_09_06.csv]. It has no sensor artifacts at all. Band combinations(B4, B3, B2) are mapped to the RGB image channels to create the false-color image as below.
2016 09 06 Changes PlantHealth.jpeg
Band combinations(B5, B4, B2) are mapped to the RGB image channels to create the false-color image as below:
2016 09 06 Floods newLands.jpeg
With the NDVI and RVI Value, we can identify the different vegetation.
NDVI NIR.jpg

  • Cluster 1: Common vegetation with lower chlorophyll content.
  • Cluster 2: Road/Newly Land/Soil.
  • Cluster 3: Healthy Plants with higher chlorophyll content which has absorbed the red light strongly.
  • Cluster 4: Waterbody.
  • Cluster 5: Clouds.

B2 B4 Cluster.jpg

3. Features that change over time in these images.
NDVI 3 compare.jpg
Jun.jpg
Sep WaterClear.JPG
Dec.jpg