Opencv code using cvlib-TypeError: Can't convert object of type 'numpy.ndarray' to 'str' for 'filename'

I am trying to read data from picamera in raspberry pi 4 using YOLOv4. Here is the code I wrote:

from picamera.array import PiRGBArray
from picamera import PiCamera
import time
import cv2
import cvlib as cv
from cvlib.object_detection import draw_bbox

def object_detection_with_bounding_boxes(filename, model="yolov3", confidence=0.2):
 
  # Read the image into a numpy array
    img = cv2.imread(filename)
     
    # Perform the object detection
    bbox, label, conf = cv.detect_common_objects(img, confidence=confidence, model=model)
     
    # Print current image's filename
    print(f"========================\nImage processed: {filename}\n")
     
    # Print detected objects with confidence level
    for l, c in zip(label, conf):
        print(f"Detected object: {l} with confidence level of {c}\n")
     
    # Create a new image that includes the bounding boxes
    output_image = draw_bbox(img, bbox, label, conf)
     
    # Save the image in the directory images_with_boxes
    cv2.imwrite(f'images_with_boxes/{filename}', output_image)
     
    # Display the image with bounding boxes
    display(Image(f'images_with_boxes/{filename}'))

camera = PiCamera()

camera.resolution=(1280,720)

camera.framerate=32

raw_capture=PiRGBArray(camera,size=(1280,720))

time.sleep(0.1)

for frame in camera.capture_continuous(raw_capture,format="bgr",use_video_port=True):
    image=frame.array
    img2 = object_detection_with_bounding_boxes(image)
    cv2.imshow("Frame",img2)
    key=cv2.waitKey(1) & 0xFF
    raw_capture.truncate(0)
    if key==ord("q"):
        break

I used the code from this link: Object Detection and Bounding Boxes with cvlib – Predictive Hacks

and I get the error below:
Traceback (most recent call last): File "/home/pi/Code_Files/objectdetect/Test2.py", line 44, in <module> img2 = object_detection_with_bounding_boxes(image) File "/home/pi/Code_Files/objectdetect/Test2.py", line 11, in object_detection_with_bounding_boxes img = cv2.imread(filename) TypeError: Can't convert object of type 'numpy.ndarray' to 'str' for 'filename'

objectdetection.py file is as below:

import cv2
import os
import numpy as np
from .utils import download_file

initialize = True
net = None
dest_dir = os.path.expanduser('~') + os.path.sep + '.cvlib' + os.path.sep + 'object_detection' + os.path.sep + 'yolo' + os.path.sep + 'yolov3'
classes = None
COLORS = np.random.uniform(0, 255, size=(80, 3))

def populate_class_labels():

    class_file_name = 'yolov3_classes.txt'
    class_file_abs_path = dest_dir + os.path.sep + class_file_name
    url = 'https://github.com/arunponnusamy/object-detection-opencv/raw/master/yolov3.txt'
    if not os.path.exists(class_file_abs_path):
        download_file(url=url, file_name=class_file_name, dest_dir=dest_dir)
    f = open(class_file_abs_path, 'r')
    classes = [line.strip() for line in f.readlines()]

    return classes


def get_output_layers(net):
    
    layer_names = net.getLayerNames()
    
    output_layers = [layer_names[i[0] - 1] for i in net.getUnconnectedOutLayers()]

    return output_layers


def draw_bbox(img, bbox, labels, confidence, colors=None, write_conf=False):
    """A method to apply a box to the image
    Args:
        img: An image in the form of a numPy array
        bbox: An array of bounding boxes
        labels: An array of labels
        colors: An array of colours the length of the number of targets(80)
        write_conf: An option to write the confidences to the image
    """

    global COLORS
    global classes

    if classes is None:
        classes = populate_class_labels()
    
    for i, label in enumerate(labels):

        if colors is None:
            color = COLORS[classes.index(label)]            
        else:
            color = colors[classes.index(label)]

        if write_conf:
            label += ' ' + str(format(confidence[i] * 100, '.2f')) + '%'

        cv2.rectangle(img, (bbox[i][0],bbox[i][1]), (bbox[i][2],bbox[i][3]), color, 2)

        cv2.putText(img, label, (bbox[i][0],bbox[i][1]-10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, color, 2)

    return img
    
def detect_common_objects(image, confidence=0.5, nms_thresh=0.3, model='yolov4', enable_gpu=False):
    """A method to detect common objects
    Args:
        image: A colour image in a numpy array
        confidence: A value to filter out objects recognised to a lower confidence score
        nms_thresh: An NMS value
        model: The detection model to be used, supported models are: yolov3, yolov3-tiny, yolov4, yolov4-tiny
        enable_gpu: A boolean to set whether the GPU will be used

    """

    Height, Width = image.shape[:2]
    scale = 0.00392

    global classes
    global dest_dir

    if model == 'yolov3-tiny':
        config_file_name = 'yolov3-tiny.cfg'
        cfg_url = "https://github.com/pjreddie/darknet/raw/master/cfg/yolov3-tiny.cfg"
        weights_file_name = 'yolov3-tiny.weights'
        weights_url = 'https://pjreddie.com/media/files/yolov3-tiny.weights'
        blob = cv2.dnn.blobFromImage(image, scale, (416,416), (0,0,0), True, crop=False)

    elif model == 'yolov4':
        config_file_name = 'yolov4.cfg'
        cfg_url = 'https://raw.githubusercontent.com/AlexeyAB/darknet/master/cfg/yolov4.cfg'
        weights_file_name = 'yolov4.weights'
        weights_url = 'https://github.com/AlexeyAB/darknet/releases/download/darknet_yolo_v3_optimal/yolov4.weights'
        blob = cv2.dnn.blobFromImage(image, scale, (416,416), (0,0,0), True, crop=False)

    elif model == 'yolov4-tiny':
        config_file_name = 'yolov4-tiny.cfg'
        cfg_url = 'https://raw.githubusercontent.com/AlexeyAB/darknet/master/cfg/yolov4-tiny.cfg'
        weights_file_name = 'yolov4-tiny.weights'
        weights_url = 'https://github.com/AlexeyAB/darknet/releases/download/darknet_yolo_v4_pre/yolov4-tiny.weights'
        blob = cv2.dnn.blobFromImage(image, scale, (416,416), (0,0,0), True, crop=False)      

    else:
        config_file_name = 'yolov3.cfg'
        cfg_url = 'https://github.com/arunponnusamy/object-detection-opencv/raw/master/yolov3.cfg'
        weights_file_name = 'yolov3.weights'
        weights_url = 'https://pjreddie.com/media/files/yolov3.weights'
        blob = cv2.dnn.blobFromImage(image, scale, (416,416), (0,0,0), True, crop=False)    

    config_file_abs_path = dest_dir + os.path.sep + config_file_name
    weights_file_abs_path = dest_dir + os.path.sep + weights_file_name    
    
    if not os.path.exists(config_file_abs_path):
        download_file(url=cfg_url, file_name=config_file_name, dest_dir=dest_dir)

    if not os.path.exists(weights_file_abs_path):
        download_file(url=weights_url, file_name=weights_file_name, dest_dir=dest_dir)    

    global initialize
    global net

    if initialize:
        classes = populate_class_labels()
        net = cv2.dnn.readNet(weights_file_abs_path, config_file_abs_path)
        initialize = False

    # enables opencv dnn module to use CUDA on Nvidia card instead of cpu
    if enable_gpu:
        net.setPreferableBackend(cv2.dnn.DNN_BACKEND_CUDA)
        net.setPreferableTarget(cv2.dnn.DNN_TARGET_CUDA)

    net.setInput(blob)

    outs = net.forward(get_output_layers(net))

    class_ids = []
    confidences = []
    boxes = []

    for out in outs:
        for detection in out:
            scores = detection[5:]
            class_id = np.argmax(scores)
            max_conf = scores[class_id]
            if max_conf > confidence:
                center_x = int(detection[0] * Width)
                center_y = int(detection[1] * Height)
                w = int(detection[2] * Width)
                h = int(detection[3] * Height)
                x = center_x - (w / 2)
                y = center_y - (h / 2)
                class_ids.append(class_id)
                confidences.append(float(max_conf))
                boxes.append([x, y, w, h])


    indices = cv2.dnn.NMSBoxes(boxes, confidences, confidence, nms_thresh)

    bbox = []
    label = []
    conf = []

    for i in indices:
        i = i[0]
        box = boxes[i]
        x = box[0]
        y = box[1]
        w = box[2]
        h = box[3]
        bbox.append([int(x), int(y), int(x+w), int(y+h)])
        label.append(str(classes[class_ids[i]]))
        conf.append(confidences[i])
        
    return bbox, label, conf


class YOLO:

    def __init__(self, weights, config, labels, version='yolov3'):

        print('[INFO] Initializing YOLO ..')

        self.config = config
        self.weights = weights
        self.version = version

        with open(labels, 'r') as f:
            self.labels = [line.strip() for line in f.readlines()]

        self.colors = np.random.uniform(0, 255, size=(len(self.labels), 3))

        self.net = cv2.dnn.readNet(self.weights, self.config)
    
        layer_names = self.net.getLayerNames()
    
        self.output_layers = [layer_names[i[0] - 1] for i in self.net.getUnconnectedOutLayers()]


    def detect_objects(self, image, confidence=0.5, nms_thresh=0.3,
                       enable_gpu=False):

        if enable_gpu:
            net.setPreferableBackend(cv2.dnn.DNN_BACKEND_CUDA)
            net.setPreferableTarget(cv2.dnn.DNN_TARGET_CUDA)

        Height, Width = image.shape[:2]
        scale = 0.00392

        blob = cv2.dnn.blobFromImage(image, scale, (416,416), (0,0,0), True,
                                     crop=False)    

        self.net.setInput(blob)

        outs = self.net.forward(self.output_layers)

        class_ids = []
        confidences = []
        boxes = []

        for out in outs:
            for detection in out:
                scores = detection[5:]
                class_id = np.argmax(scores)
                max_conf = scores[class_id]
                if max_conf > confidence:
                    center_x = int(detection[0] * Width)
                    center_y = int(detection[1] * Height)
                    w = int(detection[2] * Width)
                    h = int(detection[3] * Height)
                    x = center_x - (w / 2)
                    y = center_y - (h / 2)
                    class_ids.append(class_id)
                    confidences.append(float(max_conf))
                    boxes.append([x, y, w, h])


        indices = cv2.dnn.NMSBoxes(boxes, confidences, confidence, nms_thresh)

        bbox = []
        label = []
        conf = []

        for i in indices:
            i = i[0]
            box = boxes[i]
            x = box[0]
            y = box[1]
            w = box[2]
            h = box[3]
            bbox.append([int(x), int(y), int(x+w), int(y+h)])
            label.append(str(self.labels[class_ids[i]]))
            conf.append(confidences[i])
            
        return bbox, label, conf


    def draw_bbox(self, img, bbox, labels, confidence, colors=None, write_conf=False):

        if colors is None:
            colors = self.colors

        for i, label in enumerate(labels):

            color = colors[self.labels.index(label)]

            if write_conf:
                label += ' ' + str(format(confidence[i] * 100, '.2f')) + '%'

            cv2.rectangle(img, (bbox[i][0],bbox[i][1]), (bbox[i][2],bbox[i][3]), color, 2)

            cv2.putText(img, label, (bbox[i][0],bbox[i][1]-10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, color, 2)


I don’t know how to solve the issue with this code. I am also not sure about the rest of the code. Can you help me with it?

it expects a filename, you gave it an image from the picam.

now what ? learn a lesson, that you’ve bitten off more, than you can chew ?
that copypaste coders never get anywhere ?

maybe you want to remove the imread() call, bc you already have a image ?

1 Like

Despite the useless and off topic chewing instructions,removing the imread() was a good clue,I succeeded to stream a video from the camera after doing some modifications. Thanks;)

1 Like

Dear Sir! I was in search of this answer and you have given it to me while chewing my soul. You answer and comment really made my day. I just created this account so that I could comment on it.

1 Like