changeset 1245:371c718e57d7

interface updates
author Nicolas Saunier <nicolas.saunier@polymtl.ca>
date Thu, 08 Feb 2024 16:10:54 -0500
parents 00b71da2baac
children 2397de73770d
files scripts/display-trajectories.py scripts/dltrack.py trafficintelligence/cvutils.py trafficintelligence/moving.py trafficintelligence/storage.py
diffstat 5 files changed, 32 insertions(+), 22 deletions(-) [+]
line wrap: on
line diff
--- a/scripts/display-trajectories.py	Thu Feb 08 15:04:56 2024 -0500
+++ b/scripts/display-trajectories.py	Thu Feb 08 16:10:54 2024 -0500
@@ -1,6 +1,7 @@
 #! /usr/bin/env python3
 
 import sys, argparse
+from math import inf
 
 from numpy.linalg import inv
 from numpy import loadtxt
@@ -18,7 +19,7 @@
 parser.add_argument('--undistorted-multiplication', dest = 'undistortedImageMultiplication', help = 'undistorted image multiplication', type = float)
 parser.add_argument('-u', dest = 'undistort', help = 'undistort the video (because features have been extracted that way)', action = 'store_true')
 parser.add_argument('-f', dest = 'firstFrameNum', help = 'number of first frame number to display', type = int)
-parser.add_argument('-l', dest = 'lastFrameNum', help = 'number of last frame number to save (for image saving, no display is made)', type = int)
+parser.add_argument('-l', dest = 'lastFrameNum', help = 'number of last frame number to save (for image saving, no display is made)', type = int, default = inf)
 parser.add_argument('-r', dest = 'rescale', help = 'rescaling factor for the displayed image', default = 1., type = float)
 parser.add_argument('-s', dest = 'nFramesStep', help = 'number of frames between each display', default = 1, type = int)
 parser.add_argument('-n', dest = 'nObjects', help = 'number of objects to display', type = int)
@@ -26,7 +27,6 @@
 parser.add_argument('--nzeros', dest = 'nZerosFilenameArg', help = 'number of digits in filenames', type = int)
 
 args = parser.parse_args()
-
 params, videoFilename, databaseFilename, invHomography, intrinsicCameraMatrix, distortionCoefficients, undistortedImageMultiplication, undistort, firstFrameNum = storage.processVideoArguments(args)
 
 if args.homographyFilename is not None:
@@ -39,6 +39,8 @@
     undistortedImageMultiplication = args.undistortedImageMultiplication
 if args.firstFrameNum is not None:
     firstFrameNum = args.firstFrameNum
+if args.lastFrameNum is not None:
+    lastFrameNum = args.lastFrameNum
 if args.nObjects is not None:
     nObjects = args.nObjects
 else:
@@ -46,4 +48,4 @@
 
 objects = storage.loadTrajectoriesFromSqlite(databaseFilename, args.trajectoryType, nObjects)
 boundingBoxes = storage.loadBoundingBoxTableForDisplay(databaseFilename)
-cvutils.displayTrajectories(videoFilename, objects, boundingBoxes, invHomography, firstFrameNum, args.lastFrameNum, rescale = args.rescale, nFramesStep = args.nFramesStep, saveAllImages = args.saveAllImages, nZerosFilenameArg = args.nZerosFilenameArg, undistort = (undistort or args.undistort), intrinsicCameraMatrix = intrinsicCameraMatrix, distortionCoefficients = distortionCoefficients, undistortedImageMultiplication = undistortedImageMultiplication)
+cvutils.displayTrajectories(videoFilename, objects, boundingBoxes, invHomography, firstFrameNum, lastFrameNum, rescale = args.rescale, nFramesStep = args.nFramesStep, saveAllImages = args.saveAllImages, nZerosFilenameArg = args.nZerosFilenameArg, undistort = (undistort or args.undistort), intrinsicCameraMatrix = intrinsicCameraMatrix, distortionCoefficients = distortionCoefficients, undistortedImageMultiplication = undistortedImageMultiplication)
--- a/scripts/dltrack.py	Thu Feb 08 15:04:56 2024 -0500
+++ b/scripts/dltrack.py	Thu Feb 08 16:10:54 2024 -0500
@@ -13,8 +13,9 @@
 from trafficintelligence import cvutils, moving, storage, utils
 
 parser = argparse.ArgumentParser(description='The program tracks objects using the ultralytics models and trakcers.')
-parser.add_argument('-i', dest = 'videoFilename', help = 'name of the video file', required = True)
-parser.add_argument('-d', dest = 'databaseFilename', help = 'name of the Sqlite database file', required = True)
+parser.add_argument('--cfg', dest = 'configFilename', help = 'name of the configuration file')
+parser.add_argument('-d', dest = 'databaseFilename', help = 'name of the Sqlite database file (overrides the configuration file)')
+parser.add_argument('-i', dest = 'videoFilename', help = 'name of the video file (overrides the configuration file)')
 parser.add_argument('-m', dest = 'detectorFilename', help = 'name of the detection model file', required = True)
 parser.add_argument('-t', dest = 'trackerFilename', help = 'name of the tracker file', required = True)
 parser.add_argument('-o', dest = 'homographyFilename', help = 'filename of the homography matrix', default = 'homography.txt')
@@ -23,6 +24,7 @@
 parser.add_argument('--intrinsic', dest = 'intrinsicCameraMatrixFilename', help = 'name of the intrinsic camera file')
 parser.add_argument('--distortion-coefficients', dest = 'distortionCoefficients', help = 'distortion coefficients', nargs = '*', type = float)
 parser.add_argument('--display', dest = 'display', help = 'show the raw detection and tracking results', action = 'store_true')
+parser.add_argument('--no-image-coordinates', dest = 'notSavingImageCoordinates', help = 'not saving the raw detection and tracking results', action = 'store_true')
 parser.add_argument('-f', dest = 'firstFrameNum', help = 'number of first frame number to process', type = int, default = 0)
 parser.add_argument('-l', dest = 'lastFrameNum', help = 'number of last frame number to process', type = int, default = float('Inf'))
 parser.add_argument('--conf', dest = 'confindence', help = 'object confidence threshold for detection', type = float, default = 0.25)
@@ -30,9 +32,21 @@
 parser.add_argument('--cyclist-iou', dest = 'cyclistIou', help = 'IoU threshold to associate a bike and ped bounding box', type = float, default = 0.15)
 parser.add_argument('--cyclist-match-prop', dest = 'cyclistMatchingProportion', help = 'minimum proportion of time a bike exists and is associated with a pedestrian to be merged as cyclist', type = float, default = 0.3)
 parser.add_argument('--max-temp-overal', dest = 'maxTemporalOverlap', help = 'maximum proportion of time to merge 2 bikes associated with same pedestrian', type = float, default = 0.05)
+
 args = parser.parse_args()
+params, videoFilename, databaseFilename, invHomography, intrinsicCameraMatrix, distortionCoefficients, undistortedImageMultiplication, undistort, firstFrameNum = storage.processVideoArguments(args)
+
+if args.intrinsicCameraMatrixFilename is not None:
+    intrinsicCameraMatrix = loadtxt(args.intrinsicCameraMatrixFilename)
+if args.distortionCoefficients is not None:
+    distortionCoefficients = args.distortionCoefficients
+if args.firstFrameNum is not None:
+    firstFrameNum = args.firstFrameNum
+if args.lastFrameNum is not None:
+    lastFrameNum = args.lastFrameNum
 
 # TODO add option to refine position with mask for vehicles
+# TODO work with optical flow (farneback or RAFT) https://pytorch.org/vision/main/models/raft.html
 
 # use 2 x bytetrack track buffer to remove objects from existing ones
 
@@ -57,10 +71,9 @@
 if not success:
     print('Input {} could not be read. Exiting'.format(args.videoFilename))
     import sys; sys.exit()
+
 results = model.track(frame, tracker=args.trackerFilename, classes=list(moving.cocoTypeNames.keys()), persist=True, verbose=False)
-# create object with user type and list of 3 features (bottom ones and middle) + projection
 while capture.isOpened() and success and frameNum <= lastFrameNum:
-#for frameNum, result in enumerate(results):
     result = results[0]
     if frameNum %10 == 0:
         print(frameNum, len(result.boxes), 'objects')
@@ -103,8 +116,8 @@
 # add quality control: avoid U-turns
     
 # merge bikes and people
-twowheels = [num for num, obj in objects.items() if obj.getUserType() in (3,4)]
-pedestrians = [num for num, obj in objects.items() if obj.getUserType() == 2]
+twowheels = [num for num, obj in objects.items() if obj.getUserType() in (moving.userType2Num['motorcyclist'],moving.userType2Num['cyclist'])]
+pedestrians = [num for num, obj in objects.items() if obj.getUserType() == moving.userType2Num['pedestrian']]
 
 def mergeObjects(obj1, obj2):
     obj1.features = obj1.features+obj2.features
@@ -134,8 +147,8 @@
     nMatchedBikes = (costs[:,pedInd] < -args.cyclistMatchingProportion).sum()
     if nMatchedBikes == 0: # peds that have no bike matching: see if they have been classified as bikes sometimes
         userTypeStats = Counter(obj.userTypes)
-        if (4 in userTypeStats or (3 in userTypeStats and 4 in userTypeStats and userTypeStats[3]<=userTypeStats[4])) and userTypeStats[3]+userTypeStats[4] > args.bikeProportion*userTypeStats.total(): # 3 is motorcycle and 4 is cyclist (verif if not turning all motorbike into cyclists)
-            obj.setUserType(4)
+        if (moving.userType2Num['cyclist'] in userTypeStats or (moving.userType2Num['motorcyclist'] in userTypeStats and moving.userType2Num['cyclist'] in userTypeStats and userTypeStats[moving.userType2Num['motorcyclist']]<=userTypeStats[moving.userType2Num['cyclist']])) and userTypeStats[moving.userType2Num['motorcyclist']]+userTypeStats[moving.userType2Num['cyclist']] > args.bikeProportion*userTypeStats.total(): # verif if not turning all motorbike into cyclists
+            obj.setUserType(moving.userType2Num['cyclist'])
     elif nMatchedBikes > 1: # try to merge bikes first
         twIndices = np.nonzero(costs[:,pedInd] < -args.cyclistMatchingProportion)[0]
         # we have to compute temporal overlaps of all 2 wheels among themselves, then remove the ones with the most overlap (sum over column) one by one until there is little left
--- a/trafficintelligence/cvutils.py	Thu Feb 08 15:04:56 2024 -0500
+++ b/trafficintelligence/cvutils.py	Thu Feb 08 16:10:54 2024 -0500
@@ -4,7 +4,7 @@
 from sys import stdout
 from os import listdir
 from subprocess import run
-from math import floor, log10, ceil
+from math import floor, log10, ceil, inf
 from time import time
 
 from numpy import dot, array, append, float32, loadtxt, savetxt, append, zeros, ones, identity, abs as npabs, logical_and, unravel_index, sum as npsum, isnan, mgrid, median, floor as npfloor, ceil as npceil, nonzero, dtype
@@ -312,7 +312,7 @@
         else:
             run(cmd)
         
-    def displayTrajectories(videoFilename, objects, boundingBoxes = {}, homography = None, firstFrameNum = 0, lastFrameNumArg = None, printFrames = True, rescale = 1., nFramesStep = 1, saveAllImages = False, nZerosFilenameArg = None, undistort = False, intrinsicCameraMatrix = None, distortionCoefficients = None, undistortedImageMultiplication = 1., annotations = [], gtMatches = {}, toMatches = {}, colorBlind = False, **kwargs):
+    def displayTrajectories(videoFilename, objects, boundingBoxes = {}, homography = None, firstFrameNum = 0, lastFrameNum = None, printFrames = True, rescale = 1., nFramesStep = 1, saveAllImages = False, nZerosFilenameArg = None, undistort = False, intrinsicCameraMatrix = None, distortionCoefficients = None, undistortedImageMultiplication = 1., annotations = [], gtMatches = {}, toMatches = {}, colorBlind = False, **kwargs):
         '''Displays the objects overlaid frame by frame over the video '''
         if colorBlind:
             colorType = 'colorblind'
@@ -334,12 +334,8 @@
             ret = True
             frameNum = firstFrameNum
             capture.set(cv2.CAP_PROP_POS_FRAMES, firstFrameNum)
-            if lastFrameNumArg is None:
-                lastFrameNum = float("inf")
-            else:
-                lastFrameNum = lastFrameNumArg
             if nZerosFilenameArg is None:
-                if lastFrameNumArg is None:
+                if lastFrameNum is None or lastFrameNum == inf:
                     nZerosFilename = int(ceil(log10(objects[-1].getLastInstant())))
                 else:
                     nZerosFilename = int(ceil(log10(lastFrameNum)))
--- a/trafficintelligence/moving.py	Thu Feb 08 15:04:56 2024 -0500
+++ b/trafficintelligence/moving.py	Thu Feb 08 16:10:54 2024 -0500
@@ -1400,7 +1400,7 @@
 userTypeNames = ['unknown',
                  'car',
                  'pedestrian',
-                 'motorcycle',
+                 'motorcyclist',
                  'cyclist',
                  'bus',
                  'truck',
@@ -1847,7 +1847,7 @@
             arrow(p.x, p.y, v.x, v.y, width=arrowWidth)
 
     def play(self, videoFilename, homography = None, undistort = False, intrinsicCameraMatrix = None, distortionCoefficients = None, undistortedImageMultiplication = 1.):
-        cvutils.displayTrajectories(videoFilename, [self], homography = homography, firstFrameNum = self.getFirstInstant(), lastFrameNumArg = self.getLastInstant(), undistort = undistort, intrinsicCameraMatrix = intrinsicCameraMatrix, distortionCoefficients = distortionCoefficients, undistortedImageMultiplication = undistortedImageMultiplication)
+        cvutils.displayTrajectories(videoFilename, [self], homography = homography, firstFrameNum = self.getFirstInstant(), lastFrameNum = self.getLastInstant(), undistort = undistort, intrinsicCameraMatrix = intrinsicCameraMatrix, distortionCoefficients = distortionCoefficients, undistortedImageMultiplication = undistortedImageMultiplication)
 
     def speedDiagnostics(self, framerate = 1., display = False, nInstantsIgnoredAtEnds=0):
         speeds = framerate*self.getSpeeds(nInstantsIgnoredAtEnds)
--- a/trafficintelligence/storage.py	Thu Feb 08 15:04:56 2024 -0500
+++ b/trafficintelligence/storage.py	Thu Feb 08 16:10:54 2024 -0500
@@ -1690,8 +1690,7 @@
         undistort = False
         firstFrameNum = 0
 
-    # override video and database filenames if present on command line
-    # if not absolute, make all filenames relative to the location of the configuration filename
+    # override video and database filenames if present on command line (path is relative to command line location)
     if args.videoFilename is not None:
         videoFilename = args.videoFilename
     else: