B.23. Image classification You are provided with the RED and the NIR bands of a Landsat TM image shown in Figure 2. DN v

Business, Finance, Economics, Accounting, Operations Management, Computer Science, Electrical Engineering, Mechanical Engineering, Civil Engineering, Chemical Engineering, Algebra, Precalculus, Statistics and Probabilty, Advanced Math, Physics, Chemistry, Biology, Nursing, Psychology, Certifications, Tests, Prep, and more.
Post Reply
answerhappygod
Site Admin
Posts: 899603
Joined: Mon Aug 02, 2021 8:13 am

B.23. Image classification You are provided with the RED and the NIR bands of a Landsat TM image shown in Figure 2. DN v

Post by answerhappygod »

B 23 Image Classification You Are Provided With The Red And The Nir Bands Of A Landsat Tm Image Shown In Figure 2 Dn V 1
B 23 Image Classification You Are Provided With The Red And The Nir Bands Of A Landsat Tm Image Shown In Figure 2 Dn V 1 (86.55 KiB) Viewed 24 times
B.23. Image classification You are provided with the RED and the NIR bands of a Landsat TM image shown in Figure 2. DN values for each band are shown in Table 1 and Table 2. The analysis aims to classify the image into two classes. For each class an analyst has selected 3 pixels as training samples for which DNs are provided in Table 4. The resulting classification is shown in Table 3. 51 42 34 40 39 42 45 46 34 28 43 31 32 34 41 41 39 42 45 42 41 35 38 35 41 37 45| 39| 44 44 49 52 49 43 48 47 39 42 52 46 50 58 48 47 67 50 43 48 45 33 50 46 55 48 43 36 30 28 28 29 Table 1. RED band 125 100 83 90 91 118 92 84 38 14 108 82 80 91 94 119 97 116 68 55 95 92 95 91 102 100 106 41 96 89 122 130 120 101 108 100 62 106 88 102 134 114 113 114 84 67 109 115 72 29 124 121 115 96 50 29 20 13 13 13 Table 2. NIR band 2 2 2 2 2 2 2 2 1 ? 2 2 2 2 2 2 2 2 1 ? 2 2 2 2 2 2 2 1 2 ? 2 2 2 2 2 2 1 2 2 ? 2 2 2 2 2 12 21 ? 2 2 2 2 1 11 11 ? Table 3. Classified image Figure 2. Coarse image of the Otago peninsula Table 4. Sample pixels for each class C1 C2 P1 P2 P3 01 02 03 RED 36 29 33 50 47 51 NIR 29 13 29 134 114 125 a) Compute the mean spectral signature of each class. (2 marks) b) Compute the mean NDVI value for each class. (1 mark) (2 marks) c) Deduce an appropriate label for each class. Explain your answer. d) Using the "minimum distance to mean" classifier, find how the pixels of the last column in Table 3 should be classified. Explain your answer. (3 marks) e) During the final assessment of the classification, you obtain the confusion matrix shown in Table 5. Provide the overall accuracy of the classification, as well as the producer's accuracy and user's accuracy for each class. (2 marks) Table 5. Classification confusion matrix. Reference Data C1 C2 C1 11 2 Classification Data C2 1 46 19
Join a community of subject matter experts. Register for FREE to view solutions, replies, and use search function. Request answer by replying!
Post Reply