utils_yolo.py

import datetime
import numpy as np
import cv2


CONF_THRESHOLD = 0.5
NMS_THRESHOLD = 0.4
IMG_WIDTH = 416
IMG_HEIGHT = 416


COLOR_BLUE = (255, 0, 0)
COLOR_GREEN = (0, 255, 0)
COLOR_RED = (0, 0, 255)
COLOR_WHITE = (255, 255, 255)
COLOR_YELLOW = (0, 255, 255)


def get_outputs_names(net):
    layers_names = net.getLayerNames()
    return [layers_names[i[0] - 1] for i in net.getUnconnectedOutLayers()]


# Draw the predicted bounding box
def draw_predict(frame, conf, left, top, right, bottom):
    cv2.rectangle(frame, (left, top), (right, bottom), COLOR_YELLOW, 2)
    text = '{:.2f}'.format(conf)
    label_size, base_line = cv2.getTextSize(text, cv2.FONT_HERSHEY_SIMPLEX, 0.5, 1)

    top = max(top, label_size[1])
    cv2.putText(frame, text, (left, top - 4), cv2.FONT_HERSHEY_SIMPLEX, 0.4,
                COLOR_WHITE, 1)


def post_process(frame, outs, conf_threshold, nms_threshold):
    frame_height = frame.shape[0]
    frame_width = frame.shape[1]

    # Scan through all the bounding boxes output from the network and keep only
    # the ones with high confidence scores. Assign the box's class label as the
    # class with the highest score.
    confidences = []
    boxes = []
    final_boxes = []
    for out in outs:
        for detection in out:
            scores = detection[5:]
            class_id = np.argmax(scores)
            confidence = scores[class_id]
            if confidence > conf_threshold:
                center_x = int(detection[0] * frame_width)
                center_y = int(detection[1] * frame_height)
                width = int(detection[2] * frame_width)
                height = int(detection[3] * frame_height)
                left = int(center_x - width / 2)
                top = int(center_y - height / 2)
                confidences.append(float(confidence))
                boxes.append([left, top, width, height])

    # Perform non maximum suppression to eliminate redundant
    # overlapping boxes with lower confidences.
    indices = cv2.dnn.NMSBoxes(boxes, confidences, conf_threshold,
                               nms_threshold)

    for i in indices:
        i = i[0]
        box = boxes[i]
        final_boxes.append(box)
    return final_boxes, confidences


class FPS:
    def __init__(self):
        self._start = None
        self._end = None
        self._num_frames = 0

    def start(self):
        self._start = datetime.datetime.now()
        return self

    def stop(self):
        self._end = datetime.datetime.now()

    def update(self):
        self._num_frames += 1

    def elapsed(self):
        return (self._end - self._start).total_seconds()

    def fps(self):
        return self._num_frames / self.elapsed()