self.attribute error when changing from function to class - python

New to python and coding in general.. Not sure why the code is throwing this error:
File "c:\Users...\Python Projects\Trials\Trial 4\findClickPositions.py", line 18, in findclickpositions
AttributeError: 'numpy.ndarray' object has no attribute 'needle_img_path'
Line 18 being:
self.needle_img_path = str("./Trees/" + str(Tree) + ".png")
Here's the full code:
import cv2 as cv
import numpy as np
import os
from random import randint
from windowcapture import Windowcapture
from time import time
class find_object:
def __init__(self):
self.whatami = []
self.needle_img_path = str("")
def findclickpositions(self, img, Tree='tree', threshold=0.95, debug_mode=None):
os.makedirs('Trees', exist_ok=True)
self.needle_img_path = str("./Trees/" + str(Tree) + ".png")
self.treeimage = cv.imread(self.needle_img_path, cv.IMREAD_REDUCED_COLOR_2)
if not self.treeimage:
raise Exception('Image file of requested tree not found')
self.needle_img = cv.imread(self.needle_img_path, cv.IMREAD_REDUCED_COLOR_2)
self.method = cv.TM_CCOEFF_NORMED
self.result = cv.matchTemplate(self.img, self.needle_img, self.method)
#cv.imshow('Result', result)
#cv.waitKey()
self.min_val, self.max_val, self.min_loc, self.max_loc = cv.minMaxLoc(self.result) #gets the best match position
#print('Best match top left postion: %s' % str(max_loc))
#print('Best match confidence: %s' % str(max_val))
self.locations = np.where(self.result >=self.threshold)
self.locations = list(zip(*self.locations[::-1]))
#print(locations)
self.needle_w = self.needle_img.shape[1]
self.needle_h = self.needle_img.shape[0]
self.rectangles = []
for self.loc in self.locations:
self.rect = [int(loc[0]), int(self.loc[1]), self.needle_w, self.needle_h]
self.rectangles.append(self.rect)
self.rectangles.append(self.rect)
self.rectangles, self.weights = cv.groupRectangles(self.rectangles, 1, 0.5)
#print(rectangles)
if len(self.rectangles):
#print('Matches found')
line_colour = (0, 0, 255)
line_type = cv.LINE_4
self.marker_colour = (255, 0, 255)
self.marker_type = cv.MARKER_CROSS
for (x, y, w, h) in rectangles:
self.top_left = (x, y)
self.bottom_right = (x + w, y + h) #finding bottom right corner to draw the rectangle
cv.rectangle(self.screenshot_img, self.top_left, self.bottom_right, self.line_colour, 1, self.line_type)
self.centre_x = x + int(w/2)
self.centre_y = y + int(h/2)
self.points = []
self.points.append((centre_x, centre_y))
cv.drawMarker(self.screenshot_img, (self.centre_x, self.centre_y), self.marker_colour, self.marker_type)
#cv.imshow('Results', self.screenshot_img)
#cv.waitKey()
else:
print('No good match found')
return self.screenshot_img
I am running it from the main and passing the method an image for 'img' and 'tree' for 'tree'. I dont even know where numpy comes into this part of the code where saying there's an error. I've tried initialising it as a string (as you can see in this code) but it made no difference. Even when I comment it out on this line I get the exact same thing on the next line; when I type in the address the problem appears on 'self.treeimage'.

Related

ModuleNotFoundError: No module named 'gtk'

I've tried to follow several solutions on the internet also this one, but no luck. I'm in the process of implementing a object detection system. I am on Windows 10, and using PyCharm using python-3.8
I am getting errors for the packages, I've tried to add them through the package installer and through the terminal, no luck. Here's the error:
Traceback (most recent call last):
File "D:/CabaleGame/runner.py", line 2, in <module>
import processCards
File "D:\CabaleGame\processCards.py", line 1, in <module>
import gtk.gdk
ModuleNotFoundError: No module named 'gtk'
Process finished with exit code 1
I've downloaded the package from here and here, which one is correct?
My program file:
import gtk.gdk
import cv
import time
import os
import string
def takeScreenCapture(screenShotNum = ""):
time.sleep(1)
w = gtk.gdk.get_default_root_window()
sz = w.get_size()
#print "The size of the window is %d x %d" % sz
pb = gtk.gdk.Pixbuf(gtk.gdk.COLORSPACE_RGB,False,8,sz[0],sz[1])
pb = pb.get_from_drawable(w,w.get_colormap(),0,0,0,0,sz[0],sz[1])
# Convert gtk.PixelBuf to a NumPy array
array = pb.get_pixels_array()
# Convert NumPy array to CvMat
mat = cv.fromarray(array)
# Convert RGB to BGR
cv.CvtColor(mat, mat, cv.CV_RGB2BGR)
#cv.ShowImage("win",mat)
#cv.WaitKey(0)
return mat
def getMeaningFromCards(cards):
"""
This takes a dictionary of the form:
(x, y) : Card image
and returns a dictionary of the form:
(x, y) : (number, suit)
(x, y) are the coordinates of the top left of the card
"""
imgdir = "LibraryImages"
templatesNums = os.listdir(os.path.join(imgdir,"Numbers"))
templatesSuits = os.listdir(os.path.join(imgdir,"Suits"))
#templates = filter(lambda s: s[-4:] == ".png", templates)
templatesNums = map(lambda s: os.path.join(imgdir,"Numbers", s), templatesNums)
templatesSuits = map(lambda s: os.path.join(imgdir, "Suits", s), templatesSuits)
for k in cards.keys():
card = cards[k]
cardImg = cv.CreateImageHeader((card.width, card.height), 8, 3)
cv.SetData(cardImg, card.tostring())
numAndSuit3 = cv.GetSubRect(cardImg, (0,0,30,80))
numAndSuit1 = cv.CreateImage((numAndSuit3.width, numAndSuit3.height), 8, 1)
cv.CvtColor(numAndSuit3, numAndSuit1, cv.CV_RGB2GRAY)
# Convert the 1 channel grayscale to 3 channel grayscale
# (GRAY2RGB doesn't actually introduce color)
cv.CvtColor(numAndSuit1, numAndSuit3, cv.CV_GRAY2RGB)
num = findBestTemplateMatch(templatesNums, numAndSuit3)
suit = findBestTemplateMatch(templatesSuits, numAndSuit3)
#print num, suit
# If this image was recognized as a card, but didn't match
# any template, it shouldn't be in the list in the first place
if num == None or suit == None:
del cards[k]
continue
num = string.split(os.path.basename(num), '.')[0]
suit = string.split(os.path.basename(suit), '.')[0]
# The alternate file names have underscores
# after their names
if num[-1] == '_':
num = num[:-1]
if suit[-1] == '_':
suit = suit[:-1]
cards[k] = (num, suit)
#cv.ShowImage("NumandSuit", numAndSuit)
#cv.WaitKey(0)
print
cards
return cards
def findBestTemplateMatch(tplList, img):
"""
Compares img against a list of templates.
tplList is a list of string filenames of template images
Returns a tuple (num, suit) if a template is suitably matched
or None if not
"""
minTpl = 200 # arbitrarily large number
tString = None
for t in tplList:
tpl = cv.LoadImage(t)
w = img.width - tpl.width + 1
h = img.height - tpl.height + 1
result = cv.CreateImage((w,h), 32, 1)
cv.MatchTemplate(img, tpl, result, cv.CV_TM_SQDIFF_NORMED)
(minVal, maxVal, minLoc, maxLoc) = cv.MinMaxLoc(result)
#print t
#print (minVal, maxVal, minLoc, maxLoc)
# 0.2 found by experiment (the non-card images end up being around
# 0.25 - 0.28, and all the card images were much around 0.08 and less
if minVal < minTpl and minVal < 0.2:
minTpl = minVal
tString = t
#print minTpl, tString
#cv.ShowImage("win", img)
#cv.ShowImage("win2", result)
#cv.WaitKey(0)
return tString
def extractCards(fileName = None):
"""
Given an image, this will extract the cards from it.
This takes a filename as an optional argument
This filename should be the name of an image file.
This returns a dictionary of the form:
(x, y) : Card image
It is likely that the output from this will go to the
getMeaningFromCards() function.
"""
if fileName == None:
mat = takeScreenCapture()
else:
mat = cv.LoadImage(fileName)
# First crop the image: but only crop out the bottom.
# It is useful to have all dimensions accurate to the screen
# because otherwise they will throw off the mouse moving and clicking.
# Cropping out the bottom does not change anything in terms of the mouse.
unnec_top_distance = 130
unnec_bottom_distance = 40
margin = 50
submat = cv.GetSubRect(mat, (0,0,mat.width, mat.height - unnec_bottom_distance))
subImg = cv.CreateImageHeader((submat.width, submat.height), 8, 3)
cv.SetData(subImg, submat.tostring())
gray = cv.CreateImage((submat.width, submat.height), 8, 1)
cv.CvtColor(submat, gray, cv.CV_RGB2GRAY)
thresh = 250
max_value = 255
cv.Threshold(gray, gray, thresh, max_value, cv.CV_THRESH_BINARY)
cv.Not(gray,gray)
#cv.ShowImage("sub", submat)
#cv.WaitKey(0)
storage = cv.CreateMemStorage (0)
cpy = cv.CloneImage(gray)
contours = cv.FindContours( cpy, storage, cv.CV_RETR_LIST, cv.CV_CHAIN_APPROX_SIMPLE, (0,0) );
#contours = cv.ApproxPoly(contours, cv.CreateMemStorage(), cv.CV_POLY_APPROX_DP, 3, 1)
bboxes = []
if contours:
while(contours):
area = cv.ContourArea(contours)
# It turns out that all the cards are about 44000 in area...
# It would definitely be nice to have a better way to do this:
# ie, find the size of the card programmatically and use it then
if(area > 44000 and area < submat.width*submat.height*2/3):
bb = cv.BoundingRect(contours)
bboxes.append(bb)
contours = contours.h_next()
#drawBoundingBoxes(bboxes, submat)
# cards is a dictionary of the form:
# (x, y) : card
cards = {}
for box in bboxes:
card = cv.GetSubRect(subImg, box)
#cv.ShowImage("card", card)
#cv.WaitKey(0)
cards[(box[0], box[1])] = card
return cards
def drawBoundingBoxes(bb, img):
for b in bb:
x = b[0]
y = b[1]
width = b[2]
height = b[3]
cv.Rectangle(img, (x,y), (x+width, y+height), (0,255,0,0))
cv.ShowI
mage("bb", img)
cv.WaitKey(0)
def drawSquares(listWithPoints,img):
for l in listWithPoints:
for p in range(len(l)-1):
cv.Line(img, l[p], l[p+1], (0,0,255,0),2)
cv.Line(img, l[-1], l[0], (0,0,255,0),2)
#cv.ShowImage("sub", img)
#cv.WaitKey(0)
def contourToPointList(contour):
plist = []
for (x,y) in contour:
plist.append((x,y))
return plist
if __name__ == '__main__':
cards = extractCards('CardImages/4_heart.jpg')
print
cards
#c = cards[cards.keys()[0]]
#print c
Is it possible to add it manually through the folders?
Would it work if i put the package her:
C:\Users\User1\AppData\Local\Programs\Python\Python38\include
From python documentation :
Replace import gtk.gdk by :
import gi
gi.require_version("Gtk", "insert your gtk version")
from gi.repository import Gtk

Take full page screenshot in python without page breaking

I am trying to take full page screenshot but somehow it is not working.
First Attempt :
def screenshot(self):
self.driver.set_window_size(1920, 1080)
self.driver.save_screenshot("screen_1")
self.driver.get_screenshot_as_png()
What I am getting :
Second Attempt:
I also tried below code but it seems to break images in between when page length is long.
def save_fullpage_screenshot(self):
time.sleep(3)
# get dimensions
window_height = self.driver.execute_script('return window.innerHeight')
scroll_height = self.driver.execute_script('return document.body.parentNode.scrollHeight')
num = int(math.ceil(float(scroll_height) / float(window_height)))
# get temp files
tempfiles = []
for i in range(num):
fd, path = tempfile.mkstemp(prefix='{0}-{1:02}-'.format("ss_", i + 1), suffix=".png")
os.close(fd)
tempfiles.append(path)
pass
tempfiles_len = len(tempfiles)
try:
# take screenshots
for i, path in enumerate(tempfiles):
if i > 0:
self.driver.execute_script('window.scrollBy(%d,%d)' % (0, window_height))
self.driver.save_screenshot(path)
pass
# stitch images together
stiched = None
for i, path in enumerate(tempfiles):
img = Image.open(path)
w, h = img.size
y = i * window_height
if i == (tempfiles_len - 1) and num > 1:
img = img.crop((
0,
h - (scroll_height % h),
w,
h
))
w, h = img.size
pass
if stiched is None:
stiched = Image.new('RGB', (w, scroll_height))
stiched.paste(img, (
0, # x0
y, # y0
w, # x1
y + h # y1
))
pass
stiched.save("Y:\\ss\\s.png")
finally:
# cleanup
for path in tempfiles:
if os.path.isfile(path):
os.remove(path)
pass
What I am getting as output of above code :
The first attempt failed because Selenium takes screenshots only of the view port. You can get the full page or specific element screenshot using request to the driver.command_executor. Using take_element_screenshot on <body> will produce the same results as take_full_page_screenshot
def __take_screenshot(self, clip=None):
def send(cmd, params):
url = f'{self.__driver.command_executor._url}/session/{self.__driver.session_id}/chromium/send_command_and_get_result'
body = json.dumps({'cmd': cmd, 'params': params})
return self.__driver.command_executor._request('POST', url, body).get('value')
script = '({width: Math.max(window.innerWidth, document.body.scrollWidth, document.documentElement.scrollWidth)|0,' \
'height: Math.max(innerHeight, document.body.scrollHeight, document.documentElement.scrollHeight)|0,' \
'deviceScaleFactor: window.devicePixelRatio || 1, mobile: typeof window.orientation !== "undefined"})'
data = {'format': 'png', 'fromSurface': True}
if clip:
data['clip'] = clip
response = send('Runtime.evaluate', {'returnByValue': True, 'expression': script})
send('Emulation.setDeviceMetricsOverride', response['result']['value'])
screenshot = send('Page.captureScreenshot', data)
send('Emulation.clearDeviceMetricsOverride', {})
to_save = base64.b64decode(screenshot['data']) # same object as returned by driver.get_screenshot_as_png()
im = Image.open(BytesIO(to_save))
im.save('screenshot.png')
def take_element_screenshot(self, element):
clip = self.__driver.execute_script('rect = arguments[0].getBoundingClientRect();'
'docRect = arguments[0].ownerDocument.documentElement.getBoundingClientRect();'
'return {x: rect.left - docRect.left, y: rect.top - docRect.top, width: rect.width, height: rect.height, scale: 1};', element)
self.__take_screenshot(clip)
def take_full_page_screenshot(self):
self.__take_screenshot()

python pyparrot image processing question

I'm trying to build code that wants to fly a drone with a camera with demoMamboVisionGUI.py below. When the code is executed, the camera screen comes up and press the button to start the flight. The code above displays four cam screens and detects a straight line while detecting a specified color value, blue (BGR2HSV). Using these two codes, the camera recognizes the blue straight line and flies forward little by little, and turns left and right at a certain angle, recognizes the bottom of the specified color (red), lands, and starts flying with another button. I want to make a code that recognizes green and lands. I would appreciate it if you could throw a simple hint.
enter image description here
import cv2
import numpy as np
def im_trim(img):
x = 160
y = 50
w = 280
h = 180
img_trim = img[y:y + h, x:x + w]
return img_trim
def go():
minimum = 9999;
min_theta=0;
try:
cap = cv2.VideoCapture(0)
except:
return
while True:
ret, P = cap.read()
img1 = P
cv2.imshow('asdf',img1)
img_HSV = cv2.cvtColor(img1, cv2.COLOR_BGR2HSV)
img_h, img_s, img_v = cv2.split(img_HSV)
cv2.imshow("HSV", img_HSV)
lower_b = np.array([100, 80, 100])
upper_b = np.array([120, 255, 255])
blue = cv2.inRange(img_HSV, lower_b, upper_b)
cv2.imshow('root',blue)
edges = cv2.Canny(blue, 50, 150, apertureSize =3)
lines = cv2.HoughLines(edges, 1, np.pi/180, threshold = 100)
if lines is not None:
for line in lines:
r, theta = line[0]
#if (r<minimum and r>0) and (np.rad2deg(theta)>-90 and np.rad2deg(theta)<90):
#minimum = r
#min_theta = theta
#if (r > 0 and r < 250) and (np.rad2deg(theta) > 170 or np.rad2deg(theta) < 10):
# self.drone_object.fly_direct(pitch=0, roll=-7, yaw=0, vertical_movement=0,
# duration=1)
#print("right")
#elif (r > 400 and r < 650) and (np.rad2deg(theta) > 170 or np.rad2deg(theta) < 10):
# self.drone_object.fly_direct(pitch=0, roll=7, yaw=0, vertical_movement=0,
# duration=1)
print(r, np.rad2deg(theta))
#이하 if문을 while 문을 통해 반복하여 길 경로를 직진경로로 만든 이후 진행
#if(np.rad2deg(min_theta)>=몇도이상 or 이하):
# 이하 -> 왼쪽턴, 이상 -> 오른쪽턴, 사이 -> 직진
a = np.cos(theta)
b = np.sin(theta)
x0 = a * r
y0 = b * r
x1 = int(x0 + 1000 * (-b))
y1 = int(y0 + 1000 * a)
x2 = int(x0 - 1000 * (-b))
y2 = int(y0 - 1000 * a)
cv2.line(img1, (x1,y1), (x2,y2), (0,255,0), 3)
cv2.imshow('hough',img1)
k = cv2.waitKey(1)
if k == 27:
break
cv2.destroyAllWindows()
if __name__ == "__main__":
go()
print("??")
================================================================================================
"""
Demo of the Bebop vision using DroneVisionGUI that relies on libVLC. It is a different
multi-threaded approach than DroneVision
Author: Amy McGovern
"""
from pyparrot.Minidrone import Mambo
from pyparrot.DroneVisionGUI import DroneVisionGUI
import cv2
# set this to true if you want to fly for the demo
testFlying = True
class UserVision:
def __init__(self, vision):
self.index = 0
self.vision = vision
def save_pictures(self, args):
# print("in save pictures on image %d " % self.index)
img = self.vision.get_latest_valid_picture()
if (img is not None):
filename = "test_image_%06d.png" % self.index
# uncomment this if you want to write out images every time you get a new one
#cv2.imwrite(filename, img)
self.index +=1
#print(self.index)
def demo_mambo_user_vision_function(mamboVision, args):
"""
Demo the user code to run with the run button for a mambo
:param args:
:return:
"""
mambo = args[0]
if (testFlying):
print("taking off!")
mambo.safe_takeoff(5)
if (mambo.sensors.flying_state != "emergency"):
print("flying state is %s" % mambo.sensors.flying_state)
print("Flying direct: going up")
mambo.fly_direct(roll=0, pitch=0, yaw=0, vertical_movement=15, duration=2)
print("flip left")
print("flying state is %s" % mambo.sensors.flying_state)
success = mambo.flip(direction="left")
print("mambo flip result %s" % success)
mambo.smart_sleep(5)
print("landing")
print("flying state is %s" % mambo.sensors.flying_state)
mambo.safe_land(5)
else:
print("Sleeeping for 15 seconds - move the mambo around")
mambo.smart_sleep(15)
# done doing vision demo
print("Ending the sleep and vision")
mamboVision.close_video()
mambo.smart_sleep(5)
print("disconnecting")
mambo.disconnect()
if __name__ == "__main__":
# you will need to change this to the address of YOUR mambo
mamboAddr = "B0:FC:36:F4:37:F9"
# make my mambo object
# remember to set True/False for the wifi depending on if you are using the wifi or the BLE to connect
mambo = Mambo(mamboAddr, use_wifi=True)
print("trying to connect to mambo now")
success = mambo.connect(num_retries=3)
print("connected: %s" % success)
if (success):
# get the state information
print("sleeping")
mambo.smart_sleep(1)
mambo.ask_for_state_update()
mambo.smart_sleep(1)
print("Preparing to open vision")
mamboVision = DroneVisionGUI(mambo, is_bebop=False, buffer_size=200,
user_code_to_run=demo_mambo_user_vision_function, user_args=(mambo, ))
userVision = UserVision(mamboVision)
mamboVision.set_user_callback_function(userVision.save_pictures, user_callback_args=None)
mamboVision.open_video()
==========================================================================

Creating trail from YOLO v2 + deep_sort object tracking with tensorflow

I'm trying to create trails and map of trails of all ID like this video: https://www.youtube.com/watch?v=tq0BgncuMhs
So far I haven't been able to, I'm currently using this repo from bendidi https://github.com/bendidi/Tracking-with-darkflow which I modifies to also show the trails.
I did try using cv2.line and extract it from track.to_tlbr() but right now the result look like this:
Here's the code that I modified to get the current result:
darkflow/darkflow/net/yolov2/predict.py
from collections import deque
import numpy as np
import math
import cv2
import os
import json
#from scipy.special import expit
#from utils.box import BoundBox, box_iou, prob_compare
#from utils.box import prob_compare2, box_intersection
from ...utils.box import BoundBox
from ...cython_utils.cy_yolo2_findboxes import box_constructor
ds = True
try :
from deep_sort.application_util import preprocessing as prep
from deep_sort.application_util import visualization
from deep_sort.deep_sort.detection import Detection
except :
ds = False
def expit(x):
return 1. / (1. + np.exp(-x))
def _softmax(x):
e_x = np.exp(x - np.max(x))
out = e_x / e_x.sum()
return out
def findboxes(self, net_out):
# meta
meta = self.meta
boxes = list()
boxes=box_constructor(meta,net_out)
return boxes
def extract_boxes(self,new_im):
cont = []
new_im=new_im.astype(np.uint8)
ret, thresh=cv2.threshold(new_im, 127, 255, 0)
p, contours, hierarchy=cv2.findContours(
thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
for i in range(0, len(contours)):
cnt=contours[i]
x, y, w, h=cv2.boundingRect(cnt)
if w*h > 30**2 and ((w < new_im.shape[0] and h <= new_im.shape[1]) or (w <= new_im.shape[0] and h < new_im.shape[1])):
if self.FLAGS.tracker == "sort":
cont.append([x, y, x+w, y+h])
else : cont.append([x, y, w, h])
return cont
def postprocess(self,net_out, im,frame_id = 0,csv_file=None,csv=None,mask = None,encoder=None,tracker=None):
"""
Takes net output, draw net_out, save to disk
"""
boxes = self.findboxes(net_out)
# meta
meta = self.meta
nms_max_overlap = 0.1
threshold = meta['thresh']
colors = meta['colors']
labels = meta['labels']
if type(im) is not np.ndarray:
imgcv = cv2.imread(im)
else: imgcv = im
h, w, _ = imgcv.shape
thick = int((h + w) // 300)
resultsForJSON = []
if not self.FLAGS.track :
for b in boxes:
boxResults = self.process_box(b, h, w, threshold)
if boxResults is None:
continue
left, right, top, bot, mess, max_indx, confidence = boxResults
if self.FLAGS.json:
resultsForJSON.append({"label": mess, "confidence": float('%.2f' % confidence), "topleft": {"x": left, "y": top}, "bottomright": {"x": right, "y": bot}})
continue
if self.FLAGS.display or self.FLAGS.saveVideo:
cv2.rectangle(imgcv,
(left, top), (right, bot),
colors[max_indx], thick)
cv2.putText(imgcv, mess, (left, top - 12),
0, 1e-3 * h, colors[max_indx],thick//3)
else :
if not ds :
print("ERROR : deep sort or sort submodules not found for tracking please run :")
print("\tgit submodule update --init --recursive")
print("ENDING")
exit(1)
detections = []
scores = []
lines = deque(maxlen=64)
for b in boxes:
boxResults = self.process_box(b, h, w, threshold)
if boxResults is None:
continue
left, right, top, bot, mess, max_indx, confidence = boxResults
if mess not in self.FLAGS.trackObj :
continue
if self.FLAGS.tracker == "deep_sort":
detections.append(np.array([left,top,right-left,bot-top]).astype(np.float64))
scores.append(confidence)
elif self.FLAGS.tracker == "sort":
detections.append(np.array([left,top,right,bot]).astype(np.float64))
if len(detections) < 3 and self.FLAGS.BK_MOG:
detections = detections + extract_boxes(self,mask)
detections = np.array(detections)
if detections.shape[0] == 0 :
return imgcv
if self.FLAGS.tracker == "deep_sort":
scores = np.array(scores)
features = encoder(imgcv, detections.copy())
detections = [
Detection(bbox, score, feature) for bbox,score, feature in
zip(detections,scores, features)]
# Run non-maxima suppression.
boxes = np.array([d.tlwh for d in detections])
scores = np.array([d.confidence for d in detections])
indices = prep.non_max_suppression(boxes, nms_max_overlap, scores)
detections = [detections[i] for i in indices]
tracker.predict()
tracker.update(detections)
trackers = tracker.tracks
elif self.FLAGS.tracker == "sort":
trackers = tracker.update(detections)
for track in trackers:
if self.FLAGS.tracker == "deep_sort":
if not track.is_confirmed() or track.time_since_update > 1:
continue
bbox = track.to_tlbr()
center = (int(bbox[0]) + ((int(bbox[2]) - int(bbox[0])) // 2)), (int(bbox[1]) + ((int(bbox[3]) - int(bbox[1])) // 2)) # X + Width / 2, Y + Height / 2
lines.appendleft(center)
id_num = str(track.track_id)
elif self.FLAGS.tracker == "sort":
bbox = [int(track[0]),int(track[1]),int(track[2]),int(track[3])]
id_num = str(int(track[4]))
if self.FLAGS.csv:
csv.writerow([frame_id,id_num,int(bbox[0]),int(bbox[1]),int(bbox[2])-int(bbox[0]),int(bbox[3])-int(bbox[1])])
csv_file.flush()
if self.FLAGS.display or self.FLAGS.saveVideo:
cv2.rectangle(imgcv, (int(bbox[0]), int(bbox[1])), (int(bbox[2]), int(bbox[3])),
(255,255,255), thick//3)
cv2.putText(imgcv, id_num,(int(bbox[0]), int(bbox[1]) - 12),0, 1e-3 * h, (255,255,255),thick//6)
for i in range(1, len(lines)):
cv2.line(imgcv, lines[i - 1], lines[i], (255,255,255), thick//3)
return imgcv
Or just the code that I added:
...
lines = deque(maxlen=64)
...
center = (int(bbox[0]) + ((int(bbox[2]) - int(bbox[0])) // 2)), (int(bbox[1]) + ((int(bbox[3]) - int(bbox[1])) // 2)) # X + Width / 2, Y + Height / 2
lines.appendleft(center)
...
for i in range(1, len(lines)):
cv2.line(imgcv, lines[i - 1], lines[i], (255,255,255), thick//3)
Could someone help me out on this? Or should I do something with the data first instead of plug in straight into cv2.line? If you also have any suggestion for using external software rather than using Python, that's also welcome (I have frame_id, track_id, x, y, w, h data)

mapnik generate_tiles.py returns memory error

I am trying to create tiles using generate_tiles.py and every time I run the script, I get following error:
Exception in thread Thread-2:
Traceback (most recent call last):
File "/usr/lib/python2.7/threading.py", line 552, in __bootstrap_inner
self.run()
File "/usr/lib/python2.7/threading.py", line 505, in run
self.__target(*self.__args, **self.__kwargs)
File "render_tiles.py", line 114, in loop
self.render_tile(tile_uri, x, y, z)
File "render_tiles.py", line 96, in render_tile
mapnik.render(self.m, im)
MemoryError
Here is my script.
#!/usr/bin/python
from math import pi,cos,sin,log,exp,atan
from subprocess import call
import sys, os
from Queue import Queue
import mapnik
import threading
import random
import argparse
custom_fonts_dir = '/usr/share/fonts/'
mapnik.register_fonts(custom_fonts_dir)
DEG_TO_RAD = pi/180
RAD_TO_DEG = 180/pi
# Default number of rendering threads to spawn, should be roughly equal to number of CPU cores available
NUM_THREADS = 4
def minmax (a,b,c):
a = max(a,b)
a = min(a,c)
return a
class GoogleProjection:
def __init__(self,levels=18):
self.Bc = []
self.Cc = []
self.zc = []
self.Ac = []
c = 256
for d in range(0,levels):
e = c/2;
self.Bc.append(c/360.0)
self.Cc.append(c/(2 * pi))
self.zc.append((e,e))
self.Ac.append(c)
c *= 2
def fromLLtoPixel(self,ll,zoom):
d = self.zc[int(zoom)]
e = round(d[0] + float(ll[0]) * self.Bc[zoom])
f = minmax(sin(DEG_TO_RAD * float(ll[1])),-0.9999,0.9999)
g = round(d[1] + 0.5*log((1+f)/(1-f))*-self.Cc[zoom])
return (e,g)
def fromPixelToLL(self,px,zoom):
e = self.zc[zoom]
f = (px[0] - e[0])/self.Bc[zoom]
g = (px[1] - e[1])/-self.Cc[zoom]
h = RAD_TO_DEG * ( 2 * atan(exp(g)) - 0.5 * pi)
return (f,h)
class RenderThread:
def __init__(self, tile_dir, mapfile, q, printLock, maxZoom):
self.tile_dir = tile_dir
self.q = q
self.m = mapnik.Map(256, 256)
self.printLock = printLock
# Load style XML
mapnik.load_map(self.m, mapfile)
# Obtain projection
self.prj = mapnik.Projection(self.m.srs)
# Projects between tile pixel co-ordinates and LatLong (EPSG:4326)
self.tileproj = GoogleProjection(maxZoom+1)
def render_tile(self, tile_uri, x, y, z):
# Calculate pixel positions of bottom-left & top-right
p0 = (x * 256, (y + 1) * 256)
p1 = ((x + 1) * 256, y * 256)
# Convert to LatLong (EPSG:4326)
l0 = self.tileproj.fromPixelToLL(p0, z);
l1 = self.tileproj.fromPixelToLL(p1, z);
# Convert to map projection (e.g. mercator co-ords EPSG:900913)
c0 = self.prj.forward(mapnik.Coord(l0[0],l0[1]))
c1 = self.prj.forward(mapnik.Coord(l1[0],l1[1]))
# Bounding box for the tile
if hasattr(mapnik,'mapnik_version') and mapnik.mapnik_version() >= 800:
bbox = mapnik.Box2d(c0.x,c0.y, c1.x,c1.y)
else:
bbox = mapnik.Envelope(c0.x,c0.y, c1.x,c1.y)
render_size = 256
self.m.resize(render_size, render_size)
self.m.zoom_to_box(bbox)
self.m.buffer_size = 128
# Render image with default Agg renderer
im = mapnik.Image(render_size, render_size)
mapnik.render(self.m, im)
im.save(tile_uri, 'png256')
def loop(self):
while True:
#Fetch a tile from the queue and render it
r = self.q.get()
if (r == None):
self.q.task_done()
break
else:
(name, tile_uri, x, y, z) = r
exists= ""
if os.path.isfile(tile_uri):
exists= "exists"
else:
self.render_tile(tile_uri, x, y, z)
bytes=os.stat(tile_uri)[6]
empty= ''
if bytes == 103:
empty = " Empty Tile "
self.printLock.acquire()
print name, ":", z, x, y, exists, empty
self.printLock.release()
self.q.task_done()
def render_tiles(bbox, mapfile, tile_dir, minZoom=1,maxZoom=18, name="unknown", num_threads=NUM_THREADS):
print "render_tiles(",bbox, mapfile, tile_dir, minZoom, maxZoom, name,")"
# Launch rendering threads
queue = Queue(32)
printLock = threading.Lock()
renderers = {}
for i in range(num_threads):
renderer = RenderThread(tile_dir, mapfile, queue, printLock, maxZoom)
render_thread = threading.Thread(target=renderer.loop)
render_thread.start()
#print "Started render thread %s" % render_thread.getName()
renderers[i] = render_thread
if not os.path.isdir(tile_dir):
os.mkdir(tile_dir)
gprj = GoogleProjection(maxZoom+1)
ll0 = (bbox[0],bbox[3])
ll1 = (bbox[2],bbox[1])
for z in range(minZoom,maxZoom + 1):
px0 = gprj.fromLLtoPixel(ll0,z)
px1 = gprj.fromLLtoPixel(ll1,z)
print "fromlattolon"
# check if we have directories in place
zoom = "%s" % z
if not os.path.isdir(tile_dir + zoom):
os.mkdir(tile_dir + zoom)
for x in range(int(px0[0]/256.0),int(px1[0]/256.0)+1):
# Validate x co-ordinate
if (x = 2**z):
continue
# check if we have directories in place
str_x = "%s" % x
if not os.path.isdir(tile_dir + zoom + '/' + str_x):
os.mkdir(tile_dir + zoom + '/' + str_x)
for y in range(int(px0[1]/256.0),int(px1[1]/256.0)+1):
# Validate x co-ordinate
if (y = 2**z):
continue
str_y = "%s" % y
tile_uri = tile_dir + zoom + '/' + str_x + '/' + str_y + '.png'
# Submit tile to be rendered into the queue
t = (name, tile_uri, x, y, z)
queue.put(t)
# Signal render threads to exit by sending empty request to queue
for i in range(num_threads):
queue.put(None)
# wait for pending rendering jobs to complete
queue.join()
for i in range(num_threads):
renderers[i].join()
if __name__ == "__main__":
MIN_LON = '29.5732';
MAX_LON = '35.0360';
MIN_LAT = '-1.4840';
MAX_LAT = '4.2144';
bbox = ( MIN_LON, MIN_LAT,MAX_LON, MAX_LAT)
style_file="/home/mossplix/projects/Dev/mapit/map/static/tilemill/uganda_districts.xml"
tile_dir="/home/mossplix/projects/UnicefDev/mapit/map/static/tiles/"
min_zoom=7
max_zoom=14
render_tiles(bbox, style_file, tile_dir, min_zoom, max_zoom)
Here is the mapnik config file
mapnik config
and here is the shapefile. I compiled mapnik from source , so it should be good. what could be the problem?
I can tell that is generate_tiles.py originally, modified slightly.
A MemoryError indicates that you either are requesting an abnormally large image to be rendered or you have found a Mapnik bug.
Since the former is more likely I figure that you have made a mistake during modification of generate_tiles.py. So I took your script, overwrote the latest version in svn and got out a diff of the differences: https://gist.github.com/1197587.
On line #106 and #115 you likely want to use == not = because otherwise you are making very large x and y values that are invalid and may be the cause of very large image requests (that are wrong for a given tile).
Default number of rendering threads to spawn, should be roughly equal to number of CPU cores available
NUM_THREADS = 4
I had exactly the same error with NUM_THREADS=4.
Change the default value of NUM_THREADS to 1. I have an i5 (4 cores/1 thread per core) and NUM_THREADS=4 is very unstable. With NUM_THREADS=1 it works fine. If it works with NUM_THREADS=1 for you, try with NUM_THREADS=2 and NUM_THREADS=3 if nothing crashed.

Categories