The feed of my picamera2 is a bluish-greenish hue to it.
Blue-ish Image
As seen here the jacket appears blue, but the jacket is actually a burgundy color as seen below.
Normal Image
I thought it was this line in my code that was giving me issue.
frame_rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
However when I attempted to change it with lines like
frame_rgb = cv2.cvtColor(frame, cv2.COLOR_RGB2BGR
frame_rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV))
There was no difference to the image.
But when I attempt …
frame_rgb = cv2.cvtColor(frame, cv2.COLOR_GRAY2RGB
I would get the error…
FordMontana@raspberrypi:~/tflite1 $ python webcam.py --modeldir=custom_model_lite
INFO: Created TensorFlow Lite XNNPACK delegate for CPU.
[1:20:30.191125045] [63006] INFO Camera camera_manager.cpp:297 libcamera v0.0.5+83-bde9b04f
[1:20:30.221183718] [63010] WARN RPI vc4.cpp:383 Mismatch between Unicam and CamHelper for embedded data usage!
[1:20:30.222036114] [63010] INFO RPI vc4.cpp:437 Registered camera /base/soc/i2c0mux/i2c@1/imx219@10 to Unicam device /dev/media2 and ISP device /dev/media1
[1:20:30.222117798] [63010] INFO RPI pipeline_base.cpp:1101 Using configuration file '/usr/share/libcamera/pipeline/rpi/vc4/rpi_apps.yaml'
[1:20:30.228234194] [63006] INFO Camera camera.cpp:1033 configuring streams: (0) 1280x720-XBGR8888 (1) 1920x1080-SBGGR10_CSI2P
[1:20:30.228814816] [63010] INFO RPI vc4.cpp:565 Sensor: /base/soc/i2c0mux/i2c@1/imx219@10 - Selected sensor format: 1920x1080-SBGGR10_1X10 - Selected unicam format: 1920x1080-pBAA
Traceback (most recent call last):
File "/home/FordMontana/tflite1/webcam.py", line 164, in <module>
frame_rgb = cv2.cvtColor(frame, cv2.COLOR_GRAY2BGR)
cv2.error: OpenCV(4.5.1) ../modules/imgproc/src/color.simd_helpers.hpp:92: error: (-2:Unspecified error) in function 'cv::impl::{anonymous}::CvtHelper<VScn, VDcn, VDepth, sizePolicy>::CvtHelper(cv::InputArray, cv::OutputArray, int) [with VScn = cv::impl::{anonymous}::Set<1>; VDcn = cv::impl::{anonymous}::Set<3, 4>; VDepth = cv::impl::{anonymous}::Set<0, 2, 5>; cv::impl::{anonymous}::SizePolicy sizePolicy = cv::impl::<unnamed>::NONE; cv::InputArray = const cv::_InputArray&; cv::OutputArray = const cv::_OutputArray&]'
> Invalid number of channels in input image:
> 'VScn::contains(scn)'
> where
> 'scn' is 4
Also you can see that the format is 1920x1080, no matter what i put as my resolution it was always formatted this way.
My code is below.
import os
import argparse
import cv2
import numpy as np
import sys
import time
from threading import Thread
import importlib.util
from picamera2 import Picamera2, Preview
# Define VideoStream class to handle streaming of video from Picamera2 in separate processing thread
class VideoStream:
"""Camera object that controls video streaming from the Picamera2"""
def __init__(self, resolution=(20,10), framerate=30):
# Define and parse input arguments
parser = argparse.ArgumentParser()
parser.add_argument('--modeldir', help='Folder the .tflite file is located in',
required=True)
parser.add_argument('--graph', help='Name of the .tflite file, if different than detect.tflite',
default='detect.tflite')
parser.add_argument('--labels', help='Name of the labelmap file, if different than labelmap.txt',
default='labelmap.txt')
parser.add_argument('--threshold', help='Minimum confidence threshold for displaying detected objects',
default=0.5)
parser.add_argument('--resolution', help='Desired webcam resolution in WxH. If the webcam does not support the resolution entered, errors may occur.',
default='1280x720')
parser.add_argument('--edgetpu', help='Use Coral Edge TPU Accelerator to speed up detection',
action='store_true')
args = parser.parse_args()
MODEL_NAME = args.modeldir
GRAPH_NAME = args.graph
LABELMAP_NAME = args.labels
min_conf_threshold = float(args.threshold)
resW, resH = args.resolution.split('x')
imW, imH = int(resW), int(resH)
use_TPU = args.edgetpu
# Import TensorFlow libraries
# If tflite_runtime is installed, import interpreter from tflite_runtime, else import from regular tensorflow
# If using Coral Edge TPU, import the load_delegate library
pkg = importlib.util.find_spec('tflite_runtime')
if pkg:
from tflite_runtime.interpreter import Interpreter
if use_TPU:
from tflite_runtime.interpreter import load_delegate
else:
from tensorflow.lite.python.interpreter import Interpreter
if use_TPU:
from tensorflow.lite.python.interpreter import load_delegate
# If using Edge TPU, assign filename for Edge TPU model
if use_TPU:
# If user has specified the name of the .tflite file, use that name, otherwise use default 'edgetpu.tflite'
if (GRAPH_NAME == 'detect.tflite'):
GRAPH_NAME = 'edgetpu.tflite'
# Get path to current working directory
CWD_PATH = os.getcwd()
# Path to .tflite file, which contains the model that is used for object detection
PATH_TO_CKPT = os.path.join(CWD_PATH,MODEL_NAME,GRAPH_NAME)
# Path to label map file
PATH_TO_LABELS = os.path.join(CWD_PATH,MODEL_NAME,LABELMAP_NAME)
# Load the label map
with open(PATH_TO_LABELS, 'r') as f:
labels = [line.strip() for line in f.readlines()]
# Have to do a weird fix for label map if using the COCO "starter model" from
# https://www.tensorflow.org/lite/models/object_detection/overview
# First label is '???', which has to be removed.
if labels[0] == '???':
del(labels[0])
# Load the Tensorflow Lite model.
# If using Edge TPU, use special load_delegate argument
if use_TPU:
interpreter = Interpreter(model_path=PATH_TO_CKPT,
experimental_delegates=[load_delegate('libedgetpu.so.1.0')])
print(PATH_TO_CKPT)
else:
interpreter = Interpreter(model_path=PATH_TO_CKPT)
interpreter.allocate_tensors()
# Get model details
input_details = interpreter.get_input_details()
output_details = interpreter.get_output_details()
height = input_details[0]['shape'][1]
width = input_details[0]['shape'][2]
floating_model = (input_details[0]['dtype'] == np.float32)
input_mean = 127.5
input_std = 127.5
# Check output layer name to determine if this model was created with TF2 or TF1,
# because outputs are ordered differently for TF2 and TF1 models
outname = output_details[0]['name']
if ('StatefulPartitionedCall' in outname): # This is a TF2 model
boxes_idx, classes_idx, scores_idx = 1, 3, 0
else: # This is a TF1 model
boxes_idx, classes_idx, scores_idx = 0, 1, 2
# Initialize frame rate calculation
frame_rate_calc = 1
freq = cv2.getTickFrequency()
# Initialize video stream
videostream = VideoStream(resolution=(imW,imH),framerate=30).start()
time.sleep(1)
#for frame1 in camera.capture_continuous(rawCapture, format="bgr",use_video_port=True):
while True:
# Start timer (for calculating frame rate)
t1 = cv2.getTickCount()
# Grab frame from video stream
frame1 = videostream.read()
# Acquire frame and resize to expected shape [1xHxWx3]
frame = frame1.copy()
frame_rgb = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
frame_resized = cv2.resize(frame_rgb, (width, height))
input_data = np.expand_dims(frame_resized, axis=0)
# Normalize pixel values if using a floating model (i.e. if model is non-quantized)
if floating_model:
input_data = (np.float32(input_data) - input_mean) / input_std
# Perform the actual detection by running the model with the image as input
interpreter.set_tensor(input_details[0]['index'],input_data)
interpreter.invoke()
# Retrieve detection results
boxes = interpreter.get_tensor(output_details[boxes_idx]['index'])[0] # Bounding box coordinates of detected objects
classes = interpreter.get_tensor(output_details[classes_idx]['index'])[0] # Class index of detected objects
scores = interpreter.get_tensor(output_details[scores_idx]['index'])[0] # Confidence of detected objects
# Loop over all detections and draw detection box if confidence is above minimum threshold
for i in range(len(scores)):
if ((scores[i] > min_conf_threshold) and (scores[i] <= 1.0)):
# Get bounding box coordinates and draw box
# Interpreter can return coordinates that are outside of image dimensions, need to force them to be within image using max() and min()
ymin = int(max(1,(boxes[i][0] * imH)))
xmin = int(max(1,(boxes[i][1] * imW)))
ymax = int(min(imH,(boxes[i][2] * imH)))
xmax = int(min(imW,(boxes[i][3] * imW)))
cv2.rectangle(frame, (xmin,ymin), (xmax,ymax), (10, 255, 0), 2)
# Draw label
object_name = labels[int(classes[i])] # Look up object name from "labels" array using class index
label = '%s: %d%%' % (object_name, int(scores[i]*100)) # Example: 'person: 72%'
labelSize, baseLine = cv2.getTextSize(label, cv2.FONT_HERSHEY_SIMPLEX, 0.7, 2) # Get font size
label_ymin = max(ymin, labelSize[1] + 10) # Make sure not to draw label too close to top of window
cv2.rectangle(frame, (xmin, label_ymin-labelSize[1]-10), (xmin+labelSize[0], label_ymin+baseLine-10), (255, 255, 255), cv2.FILLED) # Draw white box to put label text in
cv2.putText(frame, label, (xmin, label_ymin-7), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 0, 0), 2) # Draw label text
# Draw framerate in corner of frame
cv2.putText(frame,'FPS: {0:.2f}'.format(frame_rate_calc),(30,50),cv2.FONT_HERSHEY_SIMPLEX,1,(255,255,0),2,cv2.LINE_AA)
# All the results have been drawn on the frame, so it's time to display it.
cv2.imshow('Object detector', frame)
# Calculate framerate
t2 = cv2.getTickCount()
time1 = (t2-t1)/freq
frame_rate_calc= 1/time1
# Press 'q' to quit
if cv2.waitKey(1) == ord('q'):
break
# Clean up
cv2.destroyAllWindows()
videostream.stop()
Help would be greatly appreciated. Thank you.