Background rm (#51)

* initial slot machine algo and watershed bg removal

* add haze and background removal initia files

* initial slot machine algo and watershed bg removal

* add haze and background removal initia files

* Added depth_map as a TaskPerceiver

* adapt Background Removal for the visualizer

* Added DepthMap With Histogram For Vis

* PCA experimentation with Depth

* add temporal blur function to remove background artifacts

* Cleaned Up Various Algorithms

* Deleted algo_stats

* Cleaned Up Imports

This commit cleans up different imports and also deletes any out of place relics.

* switch to knn based background algo

* Added MBD

* Added MBD to Code

* Cythonized the saliency_mbd

* Removed Internal Resizing

* add bitwise and for saliency and knn

* Fixed prev returned frame

* Updated combined file

* Removed experiment

* added build firle

* use numpy oriented C functions for better cython performance

Next steps include adding support for skimage, cython views (maybe)

* Added iou function

* Cleaned Up Combined Algorithm

This commit cleans up all unused code and imports.

* add gitignore and readme for cython

* Added Contours

* Added Contours and Centroid Plotting

* Implemented basics of switching

* Fixed to being in opencv version 4

* Added slider to change if both algorithms should run

* Added 0 area protections

* Added sliders for area_percentage_weight and centroid_distance_weight

* Added multi-contour output

* Updated to reflect debug mode

* Integrated saliency detection with roulette algo

* saliency with the predefined array and loops

* Added dice detector

* finalize cleaner version of saliency with "chunks"

* Adding DiceLabels.csv (#50)

This file contains dice labels for the dice.mp4 video for use as training data.

Co-authored-by: Matthew-Haddad <[email protected]>

Co-authored-by: Shrey A <[email protected]>
Co-authored-by: ayush0624 <[email protected]>
Co-authored-by: Matthew-Haddad <[email protected]>

Author: 4 people

.gitignore

@@ -4,6 +4,7 @@
 
 # Byte-compiled / optimized / DLL files
 __pycache__/
+build/
 .ipynb_checkpoints/
 *.py[cod]
 *$py.class
@@ -14,9 +15,11 @@ __pycache__/
 
 # C extensions
 *.so
+*.o
 
 # IDE files
 .idea
 .vs_code/
+.vscode/
 
 data/

README.md

@@ -27,6 +27,12 @@ and install it
 
 Also, our training data is stored here https://www.dropbox.com/sh/rrbfqfutrmifrxs/AAAfXxlcCtWZmUELp4wXyTIxa?dl=0 so download it and unzip it in the same folder as `perception`.
 
+### Cython
+To compile cythonized code, run the following commands after `cd`ing into the folder with Cython `setup.py`
+
+    python setup.py build_ext --inplace
+    cythonize file_to_cythonize.pyx
+
 
 ## misc:
 Misc code, camera calibration etc.

algo_stats

@@ -0,0 +1,84 @@
+import cv2 as cv
+import numpy as np
+import os
+import argparse
+parser = argparse.ArgumentParser()
+parser.add_argument("file", help="file")
+args = parser.parse_args()
+from dark_channel.handler import process_frame as dark_channel
+
+
+
+def DarkChannel(im):
+    b,g,r = cv.split(im)
+    dc = cv.min(cv.min(r,g),b);
+    kernel = cv.getStructuringElement(cv.MORPH_RECT,(im.shape[0],im.shape[1]))
+    dark = cv.erode(dc,kernel)
+    return dark
+
+def resize_frame(frame,ratio = 0.4):
+    return cv.resize(frame,(int(frame.shape[1]*ratio),int(frame.shape[0]*ratio)))
+
+def save_frames(frames,folder):
+    os.mkdir(folder)
+    [cv.imwrite(f'{folder}/{frame}.png', frames[frame]) for frame in frames]
+
+def show_frames(frames):
+    [cv.imshow(frame,frames[frame]) for frame in frames]
+
+def analyze(src):
+
+    # src = cv.imread(fn);
+    # src = resize_frame(src)
+    img = src
+    gray = cv.cvtColor(img,cv.COLOR_BGR2GRAY)
+    ret, thresh = cv.threshold(gray,0,255,cv.THRESH_BINARY_INV+cv.THRESH_OTSU)
+
+        # noise removal
+    kernel = np.ones((3,3),np.uint8)
+    opening = cv.morphologyEx(thresh,cv.MORPH_OPEN,kernel, iterations = 2)
+    # # sure background area
+    # sure_bg = cv.dilate(opening,kernel,iterations=3)
+    # # Finding sure foreground area
+    # dist_transform = cv.distanceTransform(opening,cv.DIST_L2,5)
+    # ret, sure_fg = cv.threshold(dist_transform,0.7*dist_transform.max(),255,0)
+    # # Finding unknown region
+    # sure_fg = np.uint8(sure_fg)
+    # unknown = cv.subtract(sure_bg,sure_fg)
+
+    # # Marker labelling
+    # ret, markers = cv.connectedComponents(sure_fg)
+    # # Add one to all labels so that sure background is not 0, but 1
+    # markers = markers+1
+    # # Now, mark the region of unknown with zero
+    # markers[unknown==255] = 0
+    # markers = cv.watershed(img,markers)
+    # orig = resize_frame(cv.imread(fn))
+    # orig[markers == -1] = [255,0,0]
+    return thresh
+    # frames = {'test':thresh,'dist':dist_transform,'sure_fg':sure_fg,'sure_bg':sure_bg,'unknown':unknown,'marked':orig}
+    # show_frames(frames)
+    # save_frames(frames,'binary_inv_dc/orig')
+    # cv.waitKey()
+    
+
+if __name__ == '__main__':
+    print(args.file)
+    cap = cv.VideoCapture(args.file)
+    while not cap.isOpened():   
+        cap = cv.VideoCapture(args.file)
+        cv.waitKey(1000)
+        print ("Wait for the header")
+    while(True):
+        ret, frame = cap.read()
+        if ret:
+            frame = resize_frame(frame, 0.25)
+            dark = dark_channel(frame)[0]
+            # cv.imshow('OTSU+Dark',analyze(dark))
+            show_frames({'OTSU':analyze(frame),'dark':dark,'OTSU+DARK':analyze(dark),'orig':frame})
+            if cv.waitKey(1) & 0xFF == ord('q'):
+                break
+            if cv.waitKey(32) == ord(' '):
+                while(not cv.waitKey(32) == ord(' ')):
+                    continue
+    cv.waitKey(-1)

misc/general_bg_rm.py

@@ -3,12 +3,21 @@
 import perception.tasks.gate.GateSegmentationAlgoA as GateSegA
 import perception.tasks.gate.GateSegmentationAlgoB as GateSegB
 import perception.tasks.gate.GateSegmentationAlgoC as GateSegC
-# import perception.tasks as tasks
+import perception.tasks.segmentation.saliency_detection.MBD as MBD
+from perception.tasks.segmentation.COMB_SAL_BG import COMB_SAL_BG
+import perception.vis.TestTasks.BackgroundRemoval as BackgroundRemoval
+import perception.tasks.roulette.color_detection as RouletteColorDetector
+from perception.tasks.dice.DiceDetector import DiceDetector
 
 ALGOS = {
     'test': TestAlgo.TestAlgo,
     'gateseg': GateSeg.GateCenterAlgo,
     'gatesegA': GateSegA.GateSegmentationAlgoA,
     'gatesegB': GateSegB.GateSegmentationAlgoB,
-    'gatesegC': GateSegC.GateSegmentationAlgoC
+    'gatesegC': GateSegC.GateSegmentationAlgoC,
+    'MBD': MBD.MBD,
+    'bg-rm': BackgroundRemoval.BackgroundRemoval,
+    'combined': COMB_SAL_BG,
+    'roulette': RouletteColorDetector.RouletteColorDetector,
+    'dice': DiceDetector
 }