Mercurial > hg > nsaunier > traffic-intelligence

comparison scripts/learn-motion-patterns.py @ 921:630934595871

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
work in progress with prototype class
author Nicolas Saunier <nicolas.saunier@polymtl.ca>
date Wed, 05 Jul 2017 18:01:43 -0400
parents 499154254f37
children acb5379c5fd7
comparison
equal deleted inserted replaced
920:499154254f37 921:630934595871
3 import sys, argparse 3 import sys, argparse
4 4
5 #import matplotlib.pyplot as plt 5 #import matplotlib.pyplot as plt
6 import numpy as np 6 import numpy as np
7 7
8 import ml, utils, storage 8 import ml, utils, storage, moving
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('-r', dest = 'initialPrototypeDatabaseFilename', help = 'name of the Sqlite database file for prototypes to start the algorithm with') 13 parser.add_argument('-o', dest = 'outputPrototypeDatabaseFilename', help = 'name of the Sqlite database file to save prototypes')
14 parser.add_argument('-i', dest = 'inputPrototypeDatabaseFilename', help = 'name of the Sqlite database file for prototypes to start the algorithm with')
14 parser.add_argument('-t', dest = 'trajectoryType', help = 'type of trajectories to learn from', choices = ['objectfeatures', 'feature', 'object'], default = 'objectfeatures') 15 parser.add_argument('-t', dest = 'trajectoryType', help = 'type of trajectories to learn from', choices = ['objectfeatures', 'feature', 'object'], default = 'objectfeatures')
15 parser.add_argument('--max-nobjectfeatures', dest = 'maxNObjectFeatures', help = 'maximum number of features per object to load', type = int, default = 1) 16 parser.add_argument('--max-nobjectfeatures', dest = 'maxNObjectFeatures', help = 'maximum number of features per object to load', type = int, default = 1)
16 parser.add_argument('-n', dest = 'nTrajectories', help = 'number of the object or feature trajectories to load', type = int, default = None) 17 parser.add_argument('-n', dest = 'nTrajectories', help = 'number of the object or feature trajectories to load', type = int, default = None)
17 parser.add_argument('-e', dest = 'epsilon', help = 'distance for the similarity of trajectory points', type = float, required = True) 18 parser.add_argument('-e', dest = 'epsilon', help = 'distance for the similarity of trajectory points', type = float, required = True)
18 parser.add_argument('--metric', dest = 'metric', help = 'metric for the similarity of trajectory points', default = 'cityblock') # default is manhattan distance 19 parser.add_argument('--metric', dest = 'metric', help = 'metric for the similarity of trajectory points', default = 'cityblock') # default is manhattan distance
32 # 2. load proto, load objects, update proto, save proto 33 # 2. load proto, load objects, update proto, save proto
33 # 3. assign objects from one db to proto 34 # 3. assign objects from one db to proto
34 # 4. load objects from several files, save in another -> see metadata: site with view and times 35 # 4. load objects from several files, save in another -> see metadata: site with view and times
35 # 5. keep prototypes, with positions/velocities, in separate db (keep link to original data through filename, type and index) 36 # 5. keep prototypes, with positions/velocities, in separate db (keep link to original data through filename, type and index)
36 37
37 # TODO add possibility to cluter with velocities 38 # TODO add possibility to clutesr with velocities
38 # TODO add possibility to start with saved prototypes so that one can incrementally learn from several databases 39 # TODO add possibility to start with saved prototypes so that one can incrementally learn from several databases
39 # save the objects that match the prototypes 40 # save the objects that match the prototypes
40 # write an assignment function for objects 41 # write an assignment function for objects
41 42
42 trajectoryType = args.trajectoryType 43 trajectoryType = args.trajectoryType
52 featureNumbers += numbers[:min(len(numbers), args.maxNObjectFeatures)] 53 featureNumbers += numbers[:min(len(numbers), args.maxNObjectFeatures)]
53 objects = storage.loadTrajectoriesFromSqlite(args.databaseFilename, 'feature', objectNumbers = featureNumbers, timeStep = args.positionSubsamplingRate) 54 objects = storage.loadTrajectoriesFromSqlite(args.databaseFilename, 'feature', objectNumbers = featureNumbers, timeStep = args.positionSubsamplingRate)
54 else: 55 else:
55 objects = storage.loadTrajectoriesFromSqlite(args.databaseFilename, trajectoryType, withFeatures = (args.trajectoryType == 'objectfeatures'), objectNumbers = args.nTrajectories, timeStep = args.positionSubsamplingRate) 56 objects = storage.loadTrajectoriesFromSqlite(args.databaseFilename, trajectoryType, withFeatures = (args.trajectoryType == 'objectfeatures'), objectNumbers = args.nTrajectories, timeStep = args.positionSubsamplingRate)
56 57
58 if args.inputPrototypeDatabaseFilename is not None:
59 prototypeIndices, dbFilenames, trajectoryTypes, nMatchings, prototypes = storage.loadPrototypesFromSqlite(args.inputPrototypeDatabaseFilename, True)
60
57 trajectories = [o.getPositions().asArray().T for o in objects] 61 trajectories = [o.getPositions().asArray().T for o in objects]
58 62
59 lcss = utils.LCSS(metric = args.metric, epsilon = args.epsilon) 63 lcss = utils.LCSS(metric = args.metric, epsilon = args.epsilon)
60 nTrajectories = len(trajectories) 64 nTrajectories = len(trajectories)
61 65
64 prototypeIndices, labels = ml.prototypeCluster(trajectories, similarities, args.minSimilarity, lambda x,y : lcss.computeNormalized(x, y), args.minClusterSize, args.optimizeCentroid, args.randomInitialization, True, None) # this line can be called again without reinitializing similarities 68 prototypeIndices, labels = ml.prototypeCluster(trajectories, similarities, args.minSimilarity, lambda x,y : lcss.computeNormalized(x, y), args.minClusterSize, args.optimizeCentroid, args.randomInitialization, True, None) # this line can be called again without reinitializing similarities
65 69
66 clusterSizes = ml.computeClusterSizes(labels, prototypeIndices, -1) 70 clusterSizes = ml.computeClusterSizes(labels, prototypeIndices, -1)
67 print(clusterSizes) 71 print(clusterSizes)
68 72
69 prototypes = [objects[i] for i in prototypeIndices] 73
70 storage.savePrototypesToSqlite(args.databaseFilename, [p.getNum() for p in prototypes], prototypeType, [clusterSizes[i] for i in prototypeIndices]) # if saving filenames, add for example [objects[i].dbFilename for i in prototypeIndices] 74 prototypes = [moving.Prototype(objects[i].getNum(), args.databaseFilename, prototypeType, clusterSizes[i]) for i in prototypeIndices]
75 if args.outputPrototypeDatabaseFilename is None:
76 outputPrototypeDatabaseFilename = args.databaseFilename
77 else:
78 outputPrototypeDatabaseFilename = args.outputPrototypeDatabaseFilename
79 storage.savePrototypesToSqlite(outputPrototypeDatabaseFilename, prototypes)
71 80
72 if args.saveSimilarities: 81 if args.saveSimilarities:
73 np.savetxt(utils.removeExtension(args.databaseFilename)+'-prototype-similarities.txt.gz', similarities, '%.4f') 82 np.savetxt(utils.removeExtension(args.databaseFilename)+'-prototype-similarities.txt.gz', similarities, '%.4f')
74 83
75 # if args.saveMatches: 84 # if args.saveMatches: