#!/usr/bin/env python3

from pathlib import Path
import sys
import cv2
import depthai as dai
import numpy as np

# Get argument first
nnPath = str((Path(__file__).parent / Path('../models/mobilenet-ssd_openvino_2021.4_6shave.blob')).resolve().absolute())
if len(sys.argv) > 1:
    nnPath = sys.argv[1]

if not Path(nnPath).exists():
    import sys
    raise FileNotFoundError(f'Required file/s not found, please run "{sys.executable} install_requirements.py"')

# MobilenetSSD label texts
labelMap = ["background", "aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat", "chair", "cow",
            "diningtable", "dog", "horse", "motorbike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor"]

# Create pipeline
pipeline = dai.Pipeline()

# Define sources and outputs
camRgb = pipeline.create(dai.node.ColorCamera)
videoEncoder = pipeline.create(dai.node.VideoEncoder)
nn = pipeline.create(dai.node.MobileNetDetectionNetwork)

xoutRgb = pipeline.create(dai.node.XLinkOut)
videoOut = pipeline.create(dai.node.XLinkOut)
nnOut = pipeline.create(dai.node.XLinkOut)

xoutRgb.setStreamName("rgb")
videoOut.setStreamName("h265")
nnOut.setStreamName("nn")

# Properties
camRgb.setBoardSocket(dai.CameraBoardSocket.CAM_A)
camRgb.setResolution(dai.ColorCameraProperties.SensorResolution.THE_1080_P)
camRgb.setPreviewSize(300, 300)
camRgb.setInterleaved(False)

videoEncoder.setDefaultProfilePreset(30, dai.VideoEncoderProperties.Profile.H265_MAIN)

nn.setConfidenceThreshold(0.5)
nn.setBlobPath(nnPath)
nn.setNumInferenceThreads(2)
nn.input.setBlocking(False)

# Linking
camRgb.video.link(videoEncoder.input)
camRgb.preview.link(xoutRgb.input)
camRgb.preview.link(nn.input)
videoEncoder.bitstream.link(videoOut.input)
nn.out.link(nnOut.input)

# Connect to device and start pipeline
with dai.Device(pipeline) as device, open('video.h265', 'wb') as videoFile:

    # Queues
    queue_size = 8
    qRgb = device.getOutputQueue("rgb", queue_size)
    qDet = device.getOutputQueue("nn", queue_size)
    qRgbEnc = device.getOutputQueue('h265', maxSize=30, blocking=True)

    frame = None
    detections = []

    def frameNorm(frame, bbox):
        normVals = np.full(len(bbox), frame.shape[0])
        normVals[::2] = frame.shape[1]
        return (np.clip(np.array(bbox), 0, 1) * normVals).astype(int)

    def displayFrame(name, frame):
        color = (255, 0, 0)
        for detection in detections:
            bbox = frameNorm(frame, (detection.xmin, detection.ymin, detection.xmax, detection.ymax))
            cv2.putText(frame, labelMap[detection.label], (bbox[0] + 10, bbox[1] + 20), cv2.FONT_HERSHEY_TRIPLEX, 0.5, color)
            cv2.putText(frame, f"{int(detection.confidence * 100)}%", (bbox[0] + 10, bbox[1] + 40), cv2.FONT_HERSHEY_TRIPLEX, 0.5, color)
            cv2.rectangle(frame, (bbox[0], bbox[1]), (bbox[2], bbox[3]), color, 2)
        # Show the frame
        cv2.imshow(name, frame)

    while True:
        inRgb = qRgb.tryGet()
        inDet = qDet.tryGet()

        while qRgbEnc.has():
            qRgbEnc.get().getData().tofile(videoFile)

        if inRgb is not None:
            frame = inRgb.getCvFrame()

        if inDet is not None:
            detections = inDet.detections

        if frame is not None:
            displayFrame("rgb", frame)

        if cv2.waitKey(1) == ord('q'):
            break

print("To view the encoded data, convert the stream file (.h265) into a video file (.mp4), using a command below:")
print("ffmpeg -framerate 30 -i video.h265 -c copy video.mp4")