Mercurial > hg > nsaunier > traffic-intelligence

comparison scripts/classify-objects.py @ 993:e8eabef7857c

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
update to OpenCV3 for python
author Nicolas Saunier <nicolas.saunier@polymtl.ca>
date Wed, 16 May 2018 21:06:52 -0400
parents 64259b9885bf
children 933670761a57
comparison
equal deleted inserted replaced
992:2cd1ce245024 993:e8eabef7857c
33 speedAggregationFunc = lambda speeds: np.percentile(speeds, args.speedAggregationQuantile) 33 speedAggregationFunc = lambda speeds: np.percentile(speeds, args.speedAggregationQuantile)
34 else: 34 else:
35 print('Unknown speed aggregation method: {}. Exiting'.format(classifierParams.speedAggregationMethod)) 35 print('Unknown speed aggregation method: {}. Exiting'.format(classifierParams.speedAggregationMethod))
36 sys.exit() 36 sys.exit()
37 37
38 pedBikeCarSVM = ml.SVM() 38 pedBikeCarSVM = ml.SVM_load(classifierParams.pedBikeCarSVMFilename)
39 pedBikeCarSVM.load(classifierParams.pedBikeCarSVMFilename) 39 bikeCarSVM = ml.SVM_load(classifierParams.bikeCarSVMFilename)
40 bikeCarSVM = ml.SVM()
41 bikeCarSVM.load(classifierParams.bikeCarSVMFilename)
42 40
43 # log logistic for ped and bik otherwise ((pedBeta/pedAlfa)*((sMean/pedAlfa)**(pedBeta-1)))/((1+(sMean/pedAlfa)**pedBeta)**2.) 41 # log logistic for ped and bik otherwise ((pedBeta/pedAlfa)*((sMean/pedAlfa)**(pedBeta-1)))/((1+(sMean/pedAlfa)**pedBeta)**2.)
44 carNorm = norm(classifierParams.meanVehicleSpeed, classifierParams.stdVehicleSpeed) 42 carNorm = norm(classifierParams.meanVehicleSpeed, classifierParams.stdVehicleSpeed)
45 pedNorm = norm(classifierParams.meanPedestrianSpeed, classifierParams.stdPedestrianSpeed) 43 pedNorm = norm(classifierParams.meanPedestrianSpeed, classifierParams.stdPedestrianSpeed)
46 # numpy lognorm shape, loc, scale: shape for numpy is scale (std of the normal) and scale for numpy is exp(location) (loc=mean of the normal) 44 # numpy lognorm shape, loc, scale: shape for numpy is scale (std of the normal) and scale for numpy is exp(location) (loc=mean of the normal)
70 timeInterval = moving.TimeInterval.unionIntervals([obj.getTimeInterval() for obj in objects]) 68 timeInterval = moving.TimeInterval.unionIntervals([obj.getTimeInterval() for obj in objects])
71 if args.startFrame0: 69 if args.startFrame0:
72 timeInterval.first = 0 70 timeInterval.first = 0
73 71
74 capture = cv2.VideoCapture(videoFilename) 72 capture = cv2.VideoCapture(videoFilename)
75 width = int(capture.get(cv2.cv.CV_CAP_PROP_FRAME_WIDTH)) 73 width = int(capture.get(cv2.CAP_PROP_FRAME_WIDTH))
76 height = int(capture.get(cv2.cv.CV_CAP_PROP_FRAME_HEIGHT)) 74 height = int(capture.get(cv2.CAP_PROP_FRAME_HEIGHT))
77 75
78 #if undistort: # setup undistortion 76 #if undistort: # setup undistortion
79 # [map1, map2] = cvutils.computeUndistortMaps(width, height, undistortedImageMultiplication, intrinsicCameraMatrix, distortionCoefficients) 77 # [map1, map2] = cvutils.computeUndistortMaps(width, height, undistortedImageMultiplication, intrinsicCameraMatrix, distortionCoefficients)
80 # height, width = map1.shape 78 # height, width = map1.shape
81 # newImgSize = (int(round(width*undistortedImageMultiplication)), int(round(height*undistortedImageMultiplication))) 79 # newImgSize = (int(round(width*undistortedImageMultiplication)), int(round(height*undistortedImageMultiplication)))
87 currentObjects = [] 85 currentObjects = []
88 if capture.isOpened(): 86 if capture.isOpened():
89 ret = True 87 ret = True
90 frameNum = timeInterval.first 88 frameNum = timeInterval.first
91 if not args.startFrame0: 89 if not args.startFrame0:
92 capture.set(cv2.cv.CV_CAP_PROP_POS_FRAMES, frameNum) 90 capture.set(cv2.CAP_PROP_POS_FRAMES, frameNum)
93 lastFrameNum = timeInterval.last 91 lastFrameNum = timeInterval.last
94 92
95 while ret and frameNum <= lastFrameNum: 93 while ret and frameNum <= lastFrameNum:
96 ret, img = capture.read() 94 ret, img = capture.read()
97 if ret: 95 if ret: