Python cv2.LINE_AA Examples

def drawSplinesOnImage(splines, color, im, pc, image_scale):
    for s in splines:
        # Get the shape of this spline and draw it on the image
        nds = []
        for wp in s["waypoints"]:
            nds.append(pc.tgcToCV2(wp["waypoint"]["x"], wp["waypoint"]["y"], image_scale))

        # Don't try to draw malformed splines
        if len(nds) == 0:
            continue

        # Uses points and not image pixels, so flip the x and y
        nds = np.array(nds)
        nds[:,[0, 1]] = nds[:,[1, 0]]
        nds = np.int32([nds]) # Bug with fillPoly, needs explict cast to 32bit

        thickness = int(s["width"])
        if(thickness < image_scale):
            thickness = int(image_scale)

        if s["isFilled"]:
            cv2.fillPoly(im, nds, color, lineType=cv2.LINE_AA)
        else:
            cv2.polylines(im, nds, s["isClosed"], color, thickness, lineType=cv2.LINE_AA) 

def plot_one_box(x, img, color=None, label=None, line_thickness=None):
    # Plots one bounding box on image img
    tl = line_thickness or round(0.002 * (img.shape[0] + img.shape[1]) / 2) + 1  # line thickness
    color = color or [random.randint(0, 255) for _ in range(3)]
    c1, c2 = (int(x[0]), int(x[1])), (int(x[2]), int(x[3]))
    cv2.rectangle(img, c1, c2, color, thickness=tl)
    if label:
        tf = max(tl - 1, 1)  # font thickness
        t_size = cv2.getTextSize(label, 0, fontScale=tl / 3, thickness=tf)[0]
        c2 = c1[0] + t_size[0], c1[1] - t_size[1] - 3
        cv2.rectangle(img, c1, c2, color, -1)  # filled
        cv2.putText(img, label, (c1[0], c1[1] - 2), 0, tl / 3, [225, 255, 255], thickness=tf, lineType=cv2.LINE_AA) 

def vis_class(img, pos, class_str, bg_color):
    """Visualizes the class."""
    font_color = cfg.VIS.SHOW_CLASS.COLOR
    font_scale = cfg.VIS.SHOW_CLASS.FONT_SCALE

    x0, y0 = int(pos[0]), int(pos[1])
    # Compute text size.
    txt = class_str
    font = cv2.FONT_HERSHEY_SIMPLEX
    ((txt_w, txt_h), _) = cv2.getTextSize(txt, font, font_scale, 1)
    # Place text background.
    back_tl = x0, y0 - int(1.3 * txt_h)
    back_br = x0 + txt_w, y0
    cv2.rectangle(img, back_tl, back_br, bg_color, -1)
    # Show text.
    txt_tl = x0, y0 - int(0.3 * txt_h)
    cv2.putText(img, txt, txt_tl, font, font_scale, font_color, lineType=cv2.LINE_AA)

    return img 

def vis_mask(img, mask, bbox_color, show_parss=False):
    """Visualizes a single binary mask."""
    img = img.astype(np.float32)
    idx = np.nonzero(mask)

    border_color = cfg.VIS.SHOW_SEGMS.BORDER_COLOR
    border_thick = cfg.VIS.SHOW_SEGMS.BORDER_THICK

    mask_color = bbox_color if cfg.VIS.SHOW_SEGMS.MASK_COLOR_FOLLOW_BOX else _WHITE
    mask_color = np.asarray(mask_color)
    mask_alpha = cfg.VIS.SHOW_SEGMS.MASK_ALPHA

    _, contours, _ = cv2.findContours(mask.copy(), cv2.RETR_CCOMP, cv2.CHAIN_APPROX_NONE)
    if cfg.VIS.SHOW_SEGMS.SHOW_BORDER:
        cv2.drawContours(img, contours, -1, border_color, border_thick, cv2.LINE_AA)

    if cfg.VIS.SHOW_SEGMS.SHOW_MASK and not show_parss:
        img[idx[0], idx[1], :] *= 1.0 - mask_alpha
        img[idx[0], idx[1], :] += mask_alpha * mask_color

    return img.astype(np.uint8) 

def vis_parsing(img, parsing, colormap, show_segms=True):
    """Visualizes a single binary parsing."""
    img = img.astype(np.float32)
    idx = np.nonzero(parsing)

    parsing_alpha = cfg.VIS.SHOW_PARSS.PARSING_ALPHA
    colormap = colormap_utils.dict2array(colormap)
    parsing_color = colormap[parsing.astype(np.int)]

    border_color = cfg.VIS.SHOW_PARSS.BORDER_COLOR
    border_thick = cfg.VIS.SHOW_PARSS.BORDER_THICK

    img[idx[0], idx[1], :] *= 1.0 - parsing_alpha
    # img[idx[0], idx[1], :] += alpha * parsing_color
    img += parsing_alpha * parsing_color

    if cfg.VIS.SHOW_PARSS.SHOW_BORDER and not show_segms:
        _, contours, _ = cv2.findContours(parsing.copy(), cv2.RETR_CCOMP, cv2.CHAIN_APPROX_NONE)
        cv2.drawContours(img, contours, -1, border_color, border_thick, cv2.LINE_AA)

    return img.astype(np.uint8) 

def drawWayOnImage(way, color, im, pc, image_scale, thickness=-1, x_offset=0.0, y_offset=0.0):
    # Get the shape of this way and draw it as a poly
    nds = []
    for node in way.get_nodes(resolve_missing=True): # Allow automatically resolving missing nodes, but this is VERY slow with the API requests, try to request them above instead
        nds.append(pc.latlonToCV2(node.lat, node.lon, image_scale, x_offset, y_offset))
    # Uses points and not image pixels, so flip the x and y
    nds = np.array(nds)
    nds[:,[0, 1]] = nds[:,[1, 0]]
    nds = np.int32([nds]) # Bug with fillPoly, needs explict cast to 32bit
    cv2.fillPoly(im, nds, color) 

    # Add option to draw shape again, but with thick line
    # Use this to automatically expand some shapes, for example water
    # For better masking
    if thickness > 0:
        # Need to draw again since fillPoly has no line thickness options that I've found
        cv2.polylines(im, nds, True, color, thickness, lineType=cv2.LINE_AA) 

def draw():
    filenames = [os.path.splitext(f)[0] for f in glob.glob("for_task3/*.txt")]
    txt_files = [s + ".txt" for s in filenames]
    for txt in txt_files:
        image = cv2.imread('test_original/'+ txt.split('/')[1].split('.')[0]+'.jpg', cv2.IMREAD_COLOR)
        with open(txt, 'r') as txt_file:
            for line in csv.reader(txt_file):
                box = [int(string, 10) for string in line[0:8]]
                if len(line) < 9:
                    print(txt)
                cv2.rectangle(image, (box[0], box[1]), (box[4], box[5]), (0,255,0), 2)
                font = cv2.FONT_HERSHEY_SIMPLEX
                cv2.putText(image, line[8].upper(), (box[0],box[1]), font, 0.5, (0, 0, 255), 1, cv2.LINE_AA)
        cv2.imwrite('task2_result_draw/'+ txt.split('/')[1].split('.')[0]+'.jpg', image) 

def add_coco_bbox(self, bbox, cat, conf=1, show_txt=True, img_id='default'): 
        bbox = np.array(bbox, dtype=np.int32)
        # cat = (int(cat) + 1) % 80
        cat = int(cat)
        # print('cat', cat, self.names[cat])
        c = self.colors[cat][0][0].tolist()
        if self.theme == 'white':
            c = (255 - np.array(c)).tolist()
        txt = '{}{:.1f}'.format(self.names[cat], conf)
        font = cv2.FONT_HERSHEY_SIMPLEX
        cat_size = cv2.getTextSize(txt, font, 0.5, 2)[0]
        cv2.rectangle(
          self.imgs[img_id], (bbox[0], bbox[1]), (bbox[2], bbox[3]), c, 2)
        if show_txt:
            cv2.rectangle(self.imgs[img_id],
                        (bbox[0], bbox[1] - cat_size[1] - 2),
                        (bbox[0] + cat_size[0], bbox[1] - 2), c, -1)
            cv2.putText(self.imgs[img_id], txt, (bbox[0], bbox[1] - 2), 
                      font, 0.5, (0, 0, 0), thickness=1, lineType=cv2.LINE_AA) 

def draw_box_label(id,img, bbox_cv2, box_color=(0, 255, 255), show_label=True):
    '''
    Helper funciton for drawing the bounding boxes and the labels
    bbox_cv2 = [left, top, right, bottom]
    '''
    #box_color= (0, 255, 255)
    font = cv2.FONT_HERSHEY_SIMPLEX
    font_size = 0.7
    font_color = (0, 0, 0)
    left, top, right, bottom = bbox_cv2[1], bbox_cv2[0], bbox_cv2[3], bbox_cv2[2]
    
    # Draw the bounding box
    cv2.rectangle(img, (left, top), (right, bottom), box_color, 4)
    
    if show_label:
        # Draw a filled box on top of the bounding box (as the background for the labels)
        cv2.rectangle(img, (left-2, top-45), (right+2, top), box_color, -1, 1)
        
        # Output the labels that show the x and y coordinates of the bounding box center.
        text_x= 'id='+str(id)
        cv2.putText(img,text_x,(left,top-25), font, font_size, font_color, 1, cv2.LINE_AA)
        text_y= 'y='+str((top+bottom)/2)
        cv2.putText(img,text_y,(left,top-5), font, font_size, font_color, 1, cv2.LINE_AA)
    
    return img 

def draw_str(dst, target, s):
    x, y = target
    cv2.putText(dst, s, (x+1, y+1), cv2.FONT_HERSHEY_PLAIN, 1.0, (0, 0, 0), thickness = 2, lineType=cv2.LINE_AA)
    cv2.putText(dst, s, (x, y), cv2.FONT_HERSHEY_PLAIN, 1.0, (255, 255, 255), lineType=cv2.LINE_AA) 

def draw_quads(self, img, quads, color = (0, 255, 0)):
        img_quads = cv2.projectPoints(quads.reshape(-1, 3), self.rvec, self.tvec, self.K, self.dist_coef) [0]
        img_quads.shape = quads.shape[:2] + (2,)
        for q in img_quads:
            cv2.fillConvexPoly(img, np.int32(q*4), color, cv2.LINE_AA, shift=2) 

def label_images(images, labels):
    font = cv.FONT_HERSHEY_SIMPLEX
    new_imgs = []
    for i, img in enumerate(images):
        new_img = ((img.copy() + 1.) * 127.5).astype(np.uint8)
        if new_img.shape[-1] == 3:
            new_img = new_img[..., ::-1]
            new_img = cv.resize(new_img, (100, 100), interpolation=cv.INTER_LINEAR)
            new_img = cv.putText(new_img, str(labels[i]), (10, 30), font, 1, (255, 255, 255), 2, cv.LINE_AA)
            new_img = cv.copyMakeBorder(new_img, top=2, bottom=2, left=2, right=2, borderType=cv.BORDER_CONSTANT,
                                        value=(255, 255, 255))
        else:
            new_img = np.squeeze(new_img)
            new_img = cv.resize(new_img, (100, 100), interpolation=cv.INTER_LINEAR)
            new_img = cv.putText(new_img, str(labels[i]), (10, 30), font, 1, (255), 2, cv.LINE_AA)
            new_img = new_img[..., None]

        new_img = (new_img / 127.5 - 1.0).astype(np.float32)
        new_imgs.append(new_img[..., ::-1])
    return np.stack(new_imgs, axis=0) 

def show_who_in_image(self, path, get_face: bool = True, show: bool = True, turn_rgb: bool = True):
		min_im, image, all_frames = self.detect_which(path, get_face)

		for (confidance, who), frame in zip(min_im, all_frames):
			color = self.colors[who]
			x1, x2, y1, y2 = frame
			cv2.rectangle(image, (x1, y1), (x2, y2), color, 4)
			cv2.putText(image, f"{who}", (x1, y1-10), cv2.FONT_HERSHEY_SIMPLEX, 1, color, 3, cv2.LINE_AA) # -{round(float(confidance), 2)}

		if turn_rgb:
			image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)

		if show:
			cv2.imshow("a", image)
			cv2.waitKey(0)

		return image 

def vis_class(img, pos, class_str, font_scale=0.35):
    """Visualizes the class."""
    img = img.astype(np.uint8)
    x0, y0 = int(pos[0]), int(pos[1])
    # Compute text size.
    txt = class_str
    font = cv2.FONT_HERSHEY_SIMPLEX
    ((txt_w, txt_h), _) = cv2.getTextSize(txt, font, font_scale, 1)
    # Place text background.
    back_tl = x0, y0 - int(1.3 * txt_h)
    back_br = x0 + txt_w, y0
    cv2.rectangle(img, back_tl, back_br, _GREEN, -1)
    # Show text.
    txt_tl = x0, y0 - int(0.3 * txt_h)
    cv2.putText(img, txt, txt_tl, font, font_scale, _GRAY, lineType=cv2.LINE_AA)
    return img 

def show_who_in_image(self, path, get_face: bool = True, show: bool = True, turn_rgb: bool = True):
		min_im, image, all_frames = self.index_image(path, get_face)

		for (confidance, who), frame in zip(min_im, all_frames):
			try:
				color = self.colors[str(who)]
				x1, x2, y1, y2 = frame
				cv2.rectangle(image, (x1, y1), (x2, y2), color, 4)
				cv2.putText(image, f"id: {str(who)}- conf:{abs(round(float(confidance), 2))}", (x1, y1-10), cv2.FONT_HERSHEY_SIMPLEX, 1, color, 3, cv2.LINE_AA) # -{round(float(confidance), 2)}
			except KeyError:
				continue

		if turn_rgb:
			image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)

		if show:
			cv2.imshow("a", image)
			cv2.waitKey(1)

		return image, min_im, all_frames 

def make_gif(image, iteration_number, save_path, model_name, max_frames_per_gif=100):

    # Make gif
    gif_frames = []

    # Read old gif frames
    try:
        gif_frames_reader = imageio.get_reader(os.path.join(save_path, model_name + ".gif"))
        for frame in gif_frames_reader:
            gif_frames.append(frame[:, :, :3])
    except:
        pass

    # Append new frame
    im = cv2.putText(np.concatenate((np.zeros((32, image.shape[1], image.shape[2])), image), axis=0),
                     'iter %s' % str(iteration_number), (10, 20), cv2.FONT_HERSHEY_SIMPLEX, .5, (255, 255, 255), 1, cv2.LINE_AA).astype('uint8')
    gif_frames.append(im)

    # If frames exceeds, save as different file
    if len(gif_frames) > max_frames_per_gif:
        print("Splitting the GIF...")
        gif_frames_00 = gif_frames[:max_frames_per_gif]
        num_of_gifs_already_saved = len(glob.glob(os.path.join(save_path, model_name + "_*.gif")))
        print("Saving", os.path.join(save_path, model_name + "_%05d.gif" % (num_of_gifs_already_saved)))
        imageio.mimsave(os.path.join(save_path, model_name + "_%05d.gif" % (num_of_gifs_already_saved)), gif_frames_00)
        gif_frames = gif_frames[max_frames_per_gif:]

    # Save gif
    # print("Saving", os.path.join(save_path, model_name + ".gif"))
    imageio.mimsave(os.path.join(save_path, model_name + ".gif"), gif_frames) 

def draw_lidar_box3d_on_image(img, boxes3d, scores, gt_boxes3d=np.array([]),
                              color=(0, 255, 255), gt_color=(255, 0, 255), thickness=1, P2 = None, T_VELO_2_CAM=None, R_RECT_0=None):
    # Input:
    #   img: (h, w, 3)
    #   boxes3d (N, 7) [x, y, z, h, w, l, r]
    #   scores
    #   gt_boxes3d (N, 7) [x, y, z, h, w, l, r]
    img = img.copy()
    projections = lidar_box3d_to_camera_box(boxes3d, cal_projection=True, P2=P2, T_VELO_2_CAM=T_VELO_2_CAM, R_RECT_0=R_RECT_0)
    gt_projections = lidar_box3d_to_camera_box(gt_boxes3d, cal_projection=True, P2=P2, T_VELO_2_CAM=T_VELO_2_CAM, R_RECT_0=R_RECT_0)

    # draw projections
    for qs in projections:
        for k in range(0, 4):
            i, j = k, (k + 1) % 4
            cv2.line(img, (qs[i, 0], qs[i, 1]), (qs[j, 0],
                                                 qs[j, 1]), color, thickness, cv2.LINE_AA)

            i, j = k + 4, (k + 1) % 4 + 4
            cv2.line(img, (qs[i, 0], qs[i, 1]), (qs[j, 0],
                                                 qs[j, 1]), color, thickness, cv2.LINE_AA)

            i, j = k, k + 4
            cv2.line(img, (qs[i, 0], qs[i, 1]), (qs[j, 0],
                                                 qs[j, 1]), color, thickness, cv2.LINE_AA)
    # draw gt projections
    for qs in gt_projections:
        for k in range(0, 4):
            i, j = k, (k + 1) % 4
            cv2.line(img, (qs[i, 0], qs[i, 1]), (qs[j, 0],
                                                 qs[j, 1]), gt_color, thickness, cv2.LINE_AA)

            i, j = k + 4, (k + 1) % 4 + 4
            cv2.line(img, (qs[i, 0], qs[i, 1]), (qs[j, 0],
                                                 qs[j, 1]), gt_color, thickness, cv2.LINE_AA)

            i, j = k, k + 4
            cv2.line(img, (qs[i, 0], qs[i, 1]), (qs[j, 0],
                                                 qs[j, 1]), gt_color, thickness, cv2.LINE_AA)

    return cv2.cvtColor(img.astype(np.uint8), cv2.COLOR_BGR2RGB) 

def draw_pose(self, img, kps):
    """Draw the pose like https://github.com/xingyizhou/CenterNet/blob/master/src/lib/utils/debugger.py#L191
    Arguments
      img: uint8 BGR
      kps: (17, 2) keypoint [[x, y]] coordinates
    """
    kps = np.array(kps, dtype=np.int32).reshape(self.num_joints, 2)
    for j in range(self.num_joints):
      cv2.circle(img, (kps[j, 0], kps[j, 1]), 3, self.colors_hp[j], -1)
    for j, e in enumerate(self.edges):
      if kps[e].min() > 0:
        cv2.line(img, (kps[e[0], 0], kps[e[0], 1]), (kps[e[1], 0], kps[e[1], 1]), self.ec[j], 2,
                 lineType=cv2.LINE_AA)
    return img 

def vis_mask(img, mask, col, alpha=0.4, show_border=True, border_thick=1):
    """Visualizes a single binary mask."""

    img = img.astype(np.float32)
    idx = np.nonzero(mask)

    img[idx[0], idx[1], :] *= 1.0 - alpha
    img[idx[0], idx[1], :] += alpha * col

    if show_border:
        _, contours, _ = cv2.findContours(
            mask.copy(), cv2.RETR_CCOMP, cv2.CHAIN_APPROX_NONE)
        cv2.drawContours(img, contours, -1, _WHITE, border_thick, cv2.LINE_AA)

    return img.astype(np.uint8) 

def plot_one_box(x, img, color=None, label=None, line_thickness=None):
    # Plots one bounding box on image img
    tl = line_thickness or round(0.002 * max(img.shape[0:2])) + 1  # line thickness
    color = color or [random.randint(0, 255) for _ in range(3)]
    c1, c2 = (int(x[0]), int(x[1])), (int(x[2]), int(x[3]))
    cv2.rectangle(img, c1, c2, color, thickness=tl)
    if label:
        tf = max(tl - 1, 1)  # font thickness
        t_size = cv2.getTextSize(label, 0, fontScale=tl / 3, thickness=tf)[0]
        c2 = c1[0] + t_size[0], c1[1] - t_size[1] - 3
        cv2.rectangle(img, c1, c2, color, -1)  # filled
        cv2.putText(img, label, (c1[0], c1[1] - 2), 0, tl / 3, [225, 255, 255], thickness=tf, lineType=cv2.LINE_AA) 

def visualize_bbox(img, bbox, class_id, class_idx_to_name, color=BOX_COLOR, thickness=2):
    x_min, y_min, x_max, y_max = bbox
    x_min, x_max, y_min, y_max = int(x_min), int(x_max), int(y_min), int(y_max)
    cv2.rectangle(img, (x_min, y_min), (x_max, y_max),
                  color=color, thickness=thickness)
    # class_name = class_idx_to_name[class_id]
    # ((text_width, text_height), _) = cv2.getTextSize(class_name, cv2.FONT_HERSHEY_SIMPLEX, 0.35, 1)
    # cv2.rectangle(img, (x_min, y_min - int(1.3 * text_height)), (x_min + text_width, y_min), BOX_COLOR, -1)
    # cv2.putText(img, class_name, (x_min, y_min - int(0.3 * text_height)), cv2.FONT_HERSHEY_SIMPLEX, 0.35,TEXT_COLOR, lineType=cv2.LINE_AA)
    return img 

def draw_marks(image, marks, color=(255, 255, 255), thick=1):
        """Draw mark points on image"""
        for mark in marks:
            cv2.circle(image, (int(mark[0]), int(
                mark[1])), thick, color, -1, cv2.LINE_AA) 

def draw_text(coordinates, image_array, text, color, x_offset=0, y_offset=0,
                                                font_scale=2, thickness=2):
    x, y = coordinates[:2]
    cv2.putText(image_array, text, (x + x_offset, y + y_offset),
                cv2.FONT_HERSHEY_SIMPLEX,
                font_scale, color, thickness, cv2.LINE_AA) 

def draw_box(image, box, color, thickness=1):
    """ Draws a box on an image with a given color.

    # Arguments
        image     : The image to draw on.
        box       : A list of 4 elements (x1, y1, x2, y2).
        color     : The color of the box.
        thickness : The thickness of the lines to draw a box with.
    """
    b = np.array(box).astype(int)
    cv2.rectangle(image, (b[0], b[1]), (b[2], b[3]), color, thickness, cv2.LINE_AA) 

def drawFloorCrop(event, x, y, flags, params):
    global perspectiveMatrix, name, RENEW_TETRAGON
    imgCroppingPolygon = np.zeros_like(params['imgFloorCorners'])
    if event == cv2.EVENT_RBUTTONUP:
        cv2.destroyWindow(f'Floor Corners for {name}')
    if len(params['croppingPolygons'][name]) > 4 and event == cv2.EVENT_LBUTTONUP:
        RENEW_TETRAGON = True
        h = params['imgFloorCorners'].shape[0]
        # delete 5th extra vertex of the floor cropping tetragon
        params['croppingPolygons'][name] = np.delete(params['croppingPolygons'][name], -1, 0)
        params['croppingPolygons'][name] = params['croppingPolygons'][name] - [h,0]
        
        # Sort cropping tetragon vertices counter-clockwise starting with top left
        params['croppingPolygons'][name] = counterclockwiseSort(params['croppingPolygons'][name])
        # Get the matrix of perspective transformation
        params['croppingPolygons'][name] = np.reshape(params['croppingPolygons'][name], (4,2))
        tetragonVertices = np.float32(params['croppingPolygons'][name])
        tetragonVerticesUpd = np.float32([[0,0], [0,h], [h,h], [h,0]])
        perspectiveMatrix[name] = cv2.getPerspectiveTransform(tetragonVertices, tetragonVerticesUpd)
    if event == cv2.EVENT_LBUTTONDOWN:
        if len(params['croppingPolygons'][name]) == 4 and RENEW_TETRAGON:
            params['croppingPolygons'][name] = np.array([[0,0]])
            RENEW_TETRAGON = False
        if len(params['croppingPolygons'][name]) == 1:
            params['croppingPolygons'][name][0] = [x,y]
        params['croppingPolygons'][name] = np.append(params['croppingPolygons'][name], [[x,y]], axis=0)
    if event == cv2.EVENT_MOUSEMOVE and not (len(params['croppingPolygons'][name]) == 4 and RENEW_TETRAGON):
        params['croppingPolygons'][name][-1] = [x,y]
        if len(params['croppingPolygons'][name]) > 1:
            cv2.fillPoly(
                imgCroppingPolygon,
                [np.reshape(
                    params['croppingPolygons'][name],
                    (len(params['croppingPolygons'][name]),2)
                )],
                BGR_COLOR['green'], cv2.LINE_AA)
            imgCroppingPolygon = cv2.addWeighted(params['imgFloorCorners'], 1.0, imgCroppingPolygon, 0.5, 0.)
            cv2.imshow(f'Floor Corners for {name}', imgCroppingPolygon) 

def real_time_object_detection(sess, colors):
    camera = cv2.VideoCapture(0)

    while camera.isOpened():
        start = time.time()
        ret, frame = camera.read() 

        if ret:
            image_data = preprocess_image(frame, model_image_size=(300,300))
            out_scores, out_boxes, out_classes = run_detection(image_data, sess)
            # Draw bounding boxes on the image file
            result = draw_boxes(frame, out_scores, out_boxes, out_classes, class_names, colors)
            end = time.time()

            # fps
            t = end - start
            fps  = "Fps: {:.2f}".format(1 / t)
            # display a piece of text to the frame
            cv2.putText(frame, fps, (10, 30),
		                cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2, cv2.LINE_AA)
            cv2.imshow("Object detection - ssd_mobilenet_v1", frame)
            if cv2.waitKey(1) & 0xFF == ord('q'):
                break
            
    camera.release()
    cv2.destroyAllWindows() 

def real_time_object_detection(interpreter, colors):
    camera = cv2.VideoCapture(0)

    while camera.isOpened():
        start = time.time()
        ret, frame = camera.read() 

        if ret:
            image_data = preprocess_image_for_tflite(frame, model_image_size=300)
            out_scores, out_boxes, out_classes = run_detection(image_data, interpreter)
            # Draw bounding boxes on the image file
            result = draw_boxes(frame, out_scores, out_boxes, out_classes, class_names, colors)
            end = time.time()

            # fps
            t = end - start
            fps  = "Fps: {:.2f}".format(1 / t)
            cv2.putText(result, fps, (10, 30),
		                cv2.FONT_HERSHEY_SIMPLEX, 1, (0, 255, 0), 2, cv2.LINE_AA)
        
            cv2.imshow("Object detection - ssdlite_mobilenet_v2", frame)
            if cv2.waitKey(1) & 0xFF == ord('q'):
                break
            
    camera.release()
    cv2.destroyAllWindows() 

def draw_boxes(image, out_scores, out_boxes, out_classes, class_names, colors):
    h, w, _ = image.shape

    for i, c in reversed(list(enumerate(out_classes))):
        predicted_class = class_names[c]
        box = out_boxes[i]
        score = out_scores[i]

        label = '{} {:.2f}'.format(predicted_class, score)

        top, left, bottom, right = box
        top = max(0, np.floor(top + 0.5).astype('int32'))
        left = max(0, np.floor(left + 0.5).astype('int32'))
        bottom = min(h, np.floor(bottom + 0.5).astype('int32'))
        right = min(w, np.floor(right + 0.5).astype('int32'))
        print(label, (left, top), (right, bottom))
                
        # colors: RGB, opencv: BGR
        cv2.rectangle(image, (left, top), (right, bottom), tuple(reversed(colors[c])), 6)

        font_face = cv2.FONT_HERSHEY_SIMPLEX
        font_scale = 1
        font_thickness = 2

        label_size = cv2.getTextSize(label, font_face, font_scale, font_thickness)[0]
        label_rect_left, label_rect_top = int(left - 3), int(top - 3)
        label_rect_right, label_rect_bottom = int(left + 3 + label_size[0]), int(top - 5 - label_size[1])
        cv2.rectangle(image, (label_rect_left, label_rect_top), (label_rect_right, label_rect_bottom), tuple(reversed(colors[c])), -1)

        cv2.putText(image, label, (left, int(top - 4)), font_face, font_scale, (0, 0, 0), font_thickness, cv2.LINE_AA)
        
    return image 

def draw_str(dst, target, s):
    x, y = target
    cv.putText(dst, s, (x + 1, y + 1), cv.FONT_HERSHEY_PLAIN, 1.0, (0, 0, 0), thickness=2, lineType=cv.LINE_AA)
    cv.putText(dst, s, (x, y), cv.FONT_HERSHEY_PLAIN, 1.0, (255, 255, 255), lineType=cv.LINE_AA) 

def draw_lidar_box3d_on_image(img, boxes3d, gt_boxes3d=np.array([]),
                              color=(0, 255, 255), gt_color=(255, 0, 255), thickness=1, P2 = None, T_VELO_2_CAM=None, R_RECT_0=None):
    # Input:
    #   img: (h, w, 3)
    #   boxes3d (N, 7) [x, y, z, h, w, l, r]
    #   scores
    #   gt_boxes3d (N, 7) [x, y, z, h, w, l, r]
    img = img.copy()
    projections = lidar_box3d_to_camera_box(boxes3d, cal_projection=True, P2=P2, T_VELO_2_CAM=T_VELO_2_CAM, R_RECT_0=R_RECT_0)
    gt_projections = lidar_box3d_to_camera_box(gt_boxes3d, cal_projection=True, P2=P2, T_VELO_2_CAM=T_VELO_2_CAM, R_RECT_0=R_RECT_0)

    # draw projections
    for qs in projections:
        for k in range(0, 4):
            i, j = k, (k + 1) % 4
            cv2.line(img, (qs[i, 0], qs[i, 1]), (qs[j, 0],
                                                 qs[j, 1]), color, thickness, cv2.LINE_AA)

            i, j = k + 4, (k + 1) % 4 + 4
            cv2.line(img, (qs[i, 0], qs[i, 1]), (qs[j, 0],
                                                 qs[j, 1]), color, thickness, cv2.LINE_AA)

            i, j = k, k + 4
            cv2.line(img, (qs[i, 0], qs[i, 1]), (qs[j, 0],
                                                 qs[j, 1]), color, thickness, cv2.LINE_AA)
    # draw gt projections
    for qs in gt_projections:
        for k in range(0, 4):
            i, j = k, (k + 1) % 4
            cv2.line(img, (qs[i, 0], qs[i, 1]), (qs[j, 0],
                                                 qs[j, 1]), gt_color, thickness, cv2.LINE_AA)

            i, j = k + 4, (k + 1) % 4 + 4
            cv2.line(img, (qs[i, 0], qs[i, 1]), (qs[j, 0],
                                                 qs[j, 1]), gt_color, thickness, cv2.LINE_AA)

            i, j = k, k + 4
            cv2.line(img, (qs[i, 0], qs[i, 1]), (qs[j, 0],
                                                 qs[j, 1]), gt_color, thickness, cv2.LINE_AA)

    return cv2.cvtColor(img.astype(np.uint8), cv2.COLOR_BGR2RGB)