Mercurial > hg > nsaunier > traffic-intelligence

comparison scripts/learn-motion-patterns.py @ 818:181bcb6dad3a

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
added option to learn motion patterns and show to display results
author Nicolas Saunier <nicolas.saunier@polymtl.ca>
date Tue, 21 Jun 2016 17:08:07 -0400
parents 0e875a7f5759
children f3ae72d86762
comparison
equal deleted inserted replaced
817:b9ec0cc2677d 818:181bcb6dad3a
9 9
10 parser = argparse.ArgumentParser(description='The program learns prototypes for the motion patterns') #, epilog = '' 10 parser = argparse.ArgumentParser(description='The program learns prototypes for the motion patterns') #, epilog = ''
11 #parser.add_argument('--cfg', dest = 'configFilename', help = 'name of the configuration file') 11 #parser.add_argument('--cfg', dest = 'configFilename', help = 'name of the configuration file')
12 parser.add_argument('-d', dest = 'databaseFilename', help = 'name of the Sqlite database file', required = True) 12 parser.add_argument('-d', dest = 'databaseFilename', help = 'name of the Sqlite database file', required = True)
13 parser.add_argument('-t', dest = 'trajectoryType', help = 'type of trajectories to display', choices = ['objectfeatures', 'feature', 'object'], default = 'objectfeatures') 13 parser.add_argument('-t', dest = 'trajectoryType', help = 'type of trajectories to display', choices = ['objectfeatures', 'feature', 'object'], default = 'objectfeatures')
14 parser.add_argument('--max-nobjectfeatures', dest = 'maxNObjectFeatures', help = 'maximum number of features per object to load', type = int, default = 3)
14 parser.add_argument('-n', dest = 'nTrajectories', help = 'number of the object or feature trajectories to load', type = int, default = None) 15 parser.add_argument('-n', dest = 'nTrajectories', help = 'number of the object or feature trajectories to load', type = int, default = None)
15 parser.add_argument('-e', dest = 'epsilon', help = 'distance for the similarity of trajectory points', type = float, required = True) 16 parser.add_argument('-e', dest = 'epsilon', help = 'distance for the similarity of trajectory points', type = float, required = True)
16 parser.add_argument('--metric', dest = 'metric', help = 'metric for the similarity of trajectory points', default = 'cityblock') # default is manhattan distance 17 parser.add_argument('--metric', dest = 'metric', help = 'metric for the similarity of trajectory points', default = 'cityblock') # default is manhattan distance
17 parser.add_argument('-s', dest = 'minSimilarity', help = 'minimum similarity to put a trajectory in a cluster', type = float, required = True) 18 parser.add_argument('-s', dest = 'minSimilarity', help = 'minimum similarity to put a trajectory in a cluster', type = float, required = True)
18 parser.add_argument('-c', dest = 'minClusterSize', help = 'minimum cluster size', type = int, default = None) 19 parser.add_argument('-c', dest = 'minClusterSize', help = 'minimum cluster size', type = int, default = None)
32 33
33 if args.trajectoryType == 'objectfeatures': 34 if args.trajectoryType == 'objectfeatures':
34 features = [] 35 features = []
35 for o in objects: 36 for o in objects:
36 tmp = utils.sortByLength(o.getFeatures(), reverse = True) 37 tmp = utils.sortByLength(o.getFeatures(), reverse = True)
37 features += tmp[:min(len(tmp), 3)] 38 features += tmp[:min(len(tmp), args.maxNObjectFeatures)]
38 objects = features 39 objects = features
39 40
40 trajectories = [o.getPositions().asArray().T for o in objects] 41 trajectories = [o.getPositions().asArray().T for o in objects]
41 42
42 lcss = utils.LCSS(metric = args.metric, epsilon = args.epsilon) 43 lcss = utils.LCSS(metric = args.metric, epsilon = args.epsilon)
48 # similarities[i,j] = lcss.computeNormalized(trajectories[i], trajectories[j]) 49 # similarities[i,j] = lcss.computeNormalized(trajectories[i], trajectories[j])
49 # similarities[j,i] = similarities[i,j] 50 # similarities[j,i] = similarities[i,j]
50 51
51 prototypeIndices, labels = ml.prototypeCluster(trajectories, similarities, args.minSimilarity, lambda x,y : lcss.computeNormalized(x, y), args.minClusterSize) # this line can be called again without reinitializing similarities 52 prototypeIndices, labels = ml.prototypeCluster(trajectories, similarities, args.minSimilarity, lambda x,y : lcss.computeNormalized(x, y), args.minClusterSize) # this line can be called again without reinitializing similarities
52 53
54 print(ml.computeClusterSizes(labels, prototypeIndices, -1))
55
53 if args.display: 56 if args.display:
54 from matplotlib.pyplot import figure 57 from matplotlib.pyplot import figure, show
55 figure() 58 figure()
56 for i,o in enumerate(objects): 59 for i,o in enumerate(objects):
57 if i not in prototypeIndices: 60 if i not in prototypeIndices:
58 if labels[i] < 0: 61 if labels[i] < 0:
59 o.plot('kx') 62 o.plot('kx')
60 else: 63 else:
61 o.plot(utils.colors[labels[i]]) 64 o.plot(utils.colors[labels[i]])
62 for i in prototypeIndices: 65 for i in prototypeIndices:
63 objects[i].plot(utils.colors[i]+'o') 66 objects[i].plot(utils.colors[i]+'o')
67 show()
64 68
65 # TODO store the prototypes (if features, easy, if objects, info must be stored about the type) 69 # TODO store the prototypes (if features, easy, if objects, info must be stored about the type)