yolov3_huanta/yolo.py

import numpy as np
import time
import cv2
import os
from PIL import Image

min_confidence = 0.3
nm_threshold = 0.3
classIDs = []
boxes = []

labelsPath = os.path.sep.join(['yolo-config', "bot.names"])
# weightsPath = os.path.sep.join(['yolo-config', "yolov3-tiny-bot_2000.weights"])
weightsPath = os.path.sep.join(['yolo-config', "yolov3-tiny-bot_2500.weights"])
# weightsPath = os.path.sep.join(['yolo-config', "yolov3-tiny-bot_1600.weights"])
# weightsPath = os.path.sep.join(['yolo-config', "yolov3-tiny-bot_1700.weights"])
# weightsPath = os.path.sep.join(['yolo-config', "yolov3-tiny-bot_400.weights"])
# weightsPath = os.path.sep.join(['yolo-config', "yolov3-tiny-bot_6000.weights"])
# weightsPath = os.path.sep.join(['yolo-config', "yolov3-tiny-bot_2700.weights"])
configPath = os.path.sep.join(['yolo-config', "yolov3-tiny-bot.cfg"])

LABELS = open(labelsPath).read().strip().split("\n")
COLORS = np.random.randint(0, 255, size=(len(LABELS), 3), dtype="uint8")
net = cv2.dnn.readNetFromDarknet(configPath, weightsPath)


def yolo_detect(image):
    (H, W) = image.shape[:2]

    # determine only the *output* layer names that we need from YOLO
    ln = net.getLayerNames()
    ln = [ln[i[0] - 1] for i in net.getUnconnectedOutLayers()]

    # construct a blob from the input image and then perform a forward
    # pass of the YOLO object detector, giving us our bounding boxes and
    # associated probabilities
    blob = cv2.dnn.blobFromImage(image, 1 / 255.0, (416, 416), swapRB=True, crop=False)
    net.setInput(blob)
    start = time.time()
    layerOutputs = net.forward(ln)
    end = time.time()

    # show timing information on YOLO
    print("[INFO] YOLO took {:.6f} seconds".format(end - start))

    # initialize our lists of detected bounding boxes, confidences, and
    # class IDs, respectively
    boxes = []
    positions = []
    confidences = []
    classIDs = []

    # loop over each of the layer outputs
    for output in layerOutputs:
        # loop over each of the detections
        for detection in output:
            # extract the class ID and confidence (i.e., probability) of
            # the current object detection
            scores = detection[5:]
            classID = np.argmax(scores)
            confidence = scores[classID]

            # filter out weak predictions by ensuring the detected
            # probability is greater than the minimum probability
            if confidence > min_confidence:
                # scale the bounding box coordinates back relative to the
                # size of the image, keeping in mind that YOLO actually
                # returns the center (x, y)-coordinates of the bounding
                # box followed by the boxes' width and height
                box = detection[0:4] * np.array([W, H, W, H])
                (centerX, centerY, width, height) = box.astype("int")

                # use the center (x, y)-coordinates to derive the top and
                # and left corner of the bounding box
                x = int(centerX - (width / 2))
                y = int(centerY - (height / 2))

                # update our list of bounding box coordinates, confidences,
                # and class IDs
                boxes.append([x, y, int(width), int(height)])
                confidences.append(float(confidence))
                classIDs.append(classID)

    # apply non-maxima suppression to suppress weak, overlapping bounding
    # boxes
    idxs = cv2.dnn.NMSBoxes(boxes, confidences, min_confidence, nm_threshold)

    # ensure at least one detection exists
    flag = 0
    if len(idxs) > 0:
        # loop over the indexes we are keeping
        for i in idxs.flatten():
            # extract the bounding box coordinates
            (x, y) = (boxes[i][0], boxes[i][1])
            (w, h) = (boxes[i][2], boxes[i][3])
            flag = 1
            # draw a bounding box rectangle and label on the image
            color = [int(c) for c in COLORS[classIDs[i]]]
            cv2.rectangle(image, (x, y), (x + w, y + h), color, 2)
            position = [(x + w / 2) - (W / 2), (H / 2) - (y + h / 2)]
            positions.append(position)
            text = "{}: {:.4f} {}".format(LABELS[classIDs[i]], confidences[i], position)
            cv2.putText(image, text, (x, y - 5), cv2.FONT_HERSHEY_SIMPLEX, 0.5, color, 2)

    return image, boxes, positions, confidences, classIDs


def get_postition(classId):
    global classIDs
    global boxes

    i = 0
    exits = False
    for v in classIDs:
        if v == classId:
            exits = True
            break
        i += 1
    if not exits:
        return [0, 0, 0, 0]

    box = boxes[i]
    print("classid", classId, "x is", box[0], "y is ", box[1])
    return box


if __name__ == "__main__":
    im = Image.open('16.png')
    im_array = np.array(im)
    im_array = cv2.cvtColor(im_array, cv2.COLOR_BGR2RGB)
    image_detection, boxes, positions, confidences, classIDs = yolo_detect(im_array)

    print(positions)  # [[350.5, 27.0], [242.0, -13.0], [-3.5, -59.5]]
    print(classIDs)  # [2, 2, 0]
    print(confidences)  # [0.9958043098449707, 0.9548179507255554, 0.8634780645370483]
    print(boxes)  # [[1135, 412, 31, 22], [1025, 451, 34, 24], [761, 371, 71, 277]];
    # [761, 371, 71, 277]代表,x,y,宽,高(坐标以左上角为原点)
    box = get_postition(0)
    print(box)

    cv2.imshow('detection', image_detection)
    cv2.waitKey(0)
    cv2.destroyAllWindows()