package extraction&matching

README.md

@@ -49,30 +49,30 @@ This submission consists of various methods for video stitching from multi-camer
 - `PositioningSystem.py` - Define the function for point transformation and box transformation based on the `trans_params.json` files. It transforms the local coordinates of individual camera to the global coordinates.
 
 - `PositioningSystem_Test.py` - Test the positoning system of three farms by visualizing the panorama results of position transformation from each camera
-
+----
 ## Usage
 ### Feature Extraction
-- **Image Feature Extraction Test**: Extract different kinds of features from the input image and visualize the result
-```bash
-    $ python feature_extraction_test.py
-```
+- **Image Feature Extraction Test**: Extract various features (SIFT, BRISK, ORB) from input images and visualize results
+    ```bash
+    $ ./main.sh -t feature_extraction
+    ```
 <div align="center">
 <img src="result/feature_extraction.png" width="500" height="300"/>
 <br/>
-Figure 1  Feature Extraction Comparison
+Figure 1: Feature Extraction Comparison
 </div>
 
 ### Feature Matching
 - **Feature Matching Test**: Match the features with BF/KNN methods. Select suitable matching method based on the Inliers Result
-```bash
-    $ python feature_matching_test.py
-```
+    ```bash
+    $ ./main.sh -t feature_matching
+    ```
 </br>
 
 - **ROIs Matching Test**: Match the features within corresponding areas to avoid wrong matches across different regions. As a result of the Separate Region Processing, false matches and computation time will be effectively reduced, and the number of correct matching inliers will increase.
-```bash
+    ```bash
     $ python ROIs_matching_test.py
-```
+    ```
 <div align="center">
 <img src="result/feature_matching.png" width="375" height="250"/>
 <img src="result/ROIs.png" width="375" height="250"/>

main.sh

@@ -0,0 +1,39 @@
+#!/bin/bash
+usage() {
+     echo "Usage: ${0} [-t|--type] [-img1] [-img2]]" 1>&2
+     exit 1
+}
+
+ROT=0
+while [[ $# -gt 0 ]];do
+     key=${1}
+     case ${key} in
+          -t|--type)
+          TYPE=${2}
+          echo "TYPE : $TYPE"
+          shift 2
+          ;;
+          -img1)
+          IMG1=${2}
+          echo "IMAGE 1 : $IMG1"
+          shift 2
+          ;;
+          -img2)
+          IMG2=${2}
+          echo "IMAGE 2 : $IMG2"
+          shift 2
+          ;;
+          *)
+          usage
+          shift
+          ;;
+     esac
+done
+
+if [[ $TYPE == "feature_extraction" ]];
+then
+     python3 src/feature_extraction_test.py --img $IMG1 #--rotate
+elif [[ $TYPE == "feature_matching" ]];
+then
+     python3 src/feature_matching_test.py --img1 $IMG1 --img2 $IMG2 #--rotate
+fi

feature_extraction_test.py → src/feature_extraction_test.py

@@ -1,18 +1,32 @@
+import os
+import sys
+sys.path.append(os.path.join(os.path.dirname(__file__), "../"))
+
+import argparse
 import numpy as np
 import cv2 as cv
 import matplotlib.pyplot as plt
 
 from stitch import utils, Image
 
-
 if __name__ == '__main__':
-    '''This script is used for feature extraction from each image'''
+    """
+    This script is used for feature extraction testing.
+    """
+    # Define parser arguments
+    parser = argparse.ArgumentParser(description="Image Stitching")
+    parser.add_argument("--img", type=str)
+    parser.add_argument("--rotate", action="store_true" , help="Rotate the image to get better visualization")
+    args, _ = parser.parse_known_args()
+
     # Load exmaple image
-    img = cv.imread("dataset/example_image/APAP-railtracks/1.JPG")
+    img = cv.imread(args.img)
+    # img = cv.imread("dataset/example_image/APAP-railtracks/1.JPG")
     # img = cv.imread("dataset/Arie/lamp_01_Arie.PNG")
     # img = cv.imread("dataset/example_image/park/1.jpg")
 
-    # img = np.rot90(img,1) # Rotate the image to get better visualization
+    if bool(args.rotate):
+        img = np.rot90(img,1) # Rotate the image to get better visualization
 
     Img = Image(img)
 

feature_matching_test.py → src/feature_matching_test.py

@@ -1,28 +1,42 @@
-import matplotlib.pyplot as plt
+import os
+import sys
+sys.path.append(os.path.join(os.path.dirname(__file__), "../"))
+
+import argparse
+import itertools
 import numpy as np
 import cv2 as cv
-import itertools
+import matplotlib.pyplot as plt
 
 from stitch import Image, utils
 
 
 if __name__ == '__main__':
     '''This script will be tested for feature matching'''
+    # Define parser arguments
+    parser = argparse.ArgumentParser(description="Image Stitching")
+    parser.add_argument("--img1", type=str)
+    parser.add_argument("--img2", type=str)
+    parser.add_argument("--rotate", action="store_true", help="Rotate the image to get better visualization")
+    args, _ = parser.parse_known_args()
 
     draw_params = dict(matchColor = (0,255,0),
                    singlePointColor = (255,0,0),
                    flags = cv.DrawMatchesFlags_DEFAULT)
 
     # load the matching images
-    #img1 = cv.imread("dataset/Arie/lamp_02_Arie.PNG")
-    #img2 = cv.imread("dataset/Arie/lamp_01_Arie.PNG")
-    img1 = cv.imread("dataset/example_image/APAP-railtracks/1.JPG")
-    img2 = cv.imread("dataset/example_image/APAP-railtracks/2.JPG")
+    img1 = cv.imread(args.img1)
+    img2 = cv.imread(args.img2)
+    # img1 = cv.imread("dataset/Arie/lamp_02_Arie.PNG")
+    # img2 = cv.imread("dataset/Arie/lamp_01_Arie.PNG")
+    #img1 = cv.imread("dataset/example_image/APAP-railtracks/1.JPG")
+    #img2 = cv.imread("dataset/example_image/APAP-railtracks/2.JPG")
     #img1 = cv.imread("dataset/example_image/NISwGSP-denny/denny02.jpg")
     #img2 = cv.imread("dataset/example_image/NISwGSP-denny/denny03.jpg")
 
-    #img1 = np.rot90(img1,1) 
-    #img2 = np.rot90(img2,1)
+    if args.rotate:
+        img1 = np.rot90(img1,1)
+        img2 = np.rot90(img2,1)
 
     # Initialize the Stitch Class
     Img1 = Image(img1)
@@ -39,9 +53,8 @@
     matches_sift_knn = utils.featureMatch(des1_filter, des2_filter, 'sift', knn=True)
 
 
-    img_sift = cv.drawMatches(Img1.img,kps1_filter,Img2.img,kps2_filter,matches_sift[:300],None,**draw_params)
-    img_sift_knn = cv.drawMatches(Img1.img,kps1_filter,Img2.img,kps2_filter,matches_sift_knn[:300],None,**draw_params)
-
+    img_sift = cv.drawMatches(Img1.img, kps1_filter, Img2.img, kps2_filter, matches_sift[:300],None,**draw_params)
+    img_sift_knn = cv.drawMatches(Img1.img, kps1_filter, Img2.img, kps2_filter, matches_sift_knn[:300],None,**draw_params)
 
     '''BRISK Features Matching Comparison'''
     # Extract the BRISK features

stitch/ImageStitch.py

@@ -31,7 +31,7 @@ def __init__(self, img, nfeatures=0, method = 'sift'):
 
         # Extract the features from image and update the feature property
         kps, des = self.findFeatures(method)
-        print("\nInitial Successfullys")
+        print("\nInitial Successfully!")
 
     def equalizeHist(self):
         self.img = utils.equalizeHist(self.img)