mmdetection中更改不同类别的检测框的颜色和字体

程小橙-CNN

于 2024-03-15 18:57:52 发布

阅读量585

点赞数 3

文章标签： python 人工智能算法

本文链接：https://blog.csdn.net/zzxy123456789/article/details/136747091

版权

mmdetection中更改不同类别的检测框的颜色和字体

1.在base.py文件修改字体大小

位置：mmdet/models/detectors/base.py

def show_result(self,
                    img,
                    result,
                    score_thr=0.3,
                    bbox_color=(72, 101, 241),
                    text_color=(72, 101, 241),
                    mask_color=None,
                    thickness=3,  ## 边框大小
                    font_size=18,  ### 这里修改字体
                    win_name='',
                    show=False,
                    wait_time=0,
                    out_file=None):
        """Draw `result` over `img`.

        Args:
            img (str or Tensor): The image to be displayed.
            result (Tensor or tuple): The results to draw over `img`
                bbox_result or (bbox_result, segm_result).
            score_thr (float, optional): Minimum score of bboxes to be shown.
                Default: 0.3.
            bbox_color (str or tuple(int) or :obj:`Color`):Color of bbox lines.
               The tuple of color should be in BGR order. Default: 'green'
            text_color (str or tuple(int) or :obj:`Color`):Color of texts.
               The tuple of color should be in BGR order. Default: 'green'
            mask_color (None or str or tuple(int) or :obj:`Color`):
               Color of masks. The tuple of color should be in BGR order.
               Default: None
            thickness (int): Thickness of lines. Default: 2
            font_size (int): Font size of texts. Default: 13
            win_name (str): The window name. Default: ''
            wait_time (float): Value of waitKey param.
                Default: 0.
            show (bool): Whether to show the image.
                Default: False.
            out_file (str or None): The filename to write the image.
                Default: None.

        Returns:
            img (Tensor): Only if not `show` or `out_file`
        """
        img = mmcv.imread(img)
        img = img.copy()
        if isinstance(result, tuple):
            bbox_result, segm_result = result
            if isinstance(segm_result, tuple):
                segm_result = segm_result[0]  # ms rcnn
        else:
            bbox_result, segm_result = result, None
        bboxes = np.vstack(bbox_result)
        labels = [
            np.full(bbox.shape[0], i, dtype=np.int32)
            for i, bbox in enumerate(bbox_result)
        ]
        labels = np.concatenate(labels)
        # draw segmentation masks
        segms = None
        if segm_result is not None and len(labels) > 0:  # non empty
            segms = mmcv.concat_list(segm_result)
            if isinstance(segms[0], torch.Tensor):
                segms = torch.stack(segms, dim=0).detach().cpu().numpy()
            else:
                segms = np.stack(segms, axis=0)
        # if out_file specified, do not show image in window
        if out_file is not None:
            show = False
        # draw bounding boxes
        img = imshow_det_bboxes(
            img,
            bboxes,
            labels,
            segms,
            class_names=self.CLASSES,
            score_thr=score_thr,
            bbox_color=bbox_color,
            text_color=text_color,
            mask_color=mask_color,
            thickness=thickness,
            font_size=font_size,
            win_name=win_name,
            show=show,
            wait_time=wait_time,
            out_file=out_file)

        if not (show or out_file):
            return img

2.主要修改imshow_det_bboxes函数，按照类别进行不同颜色的显示

位置：mmdet/core/visualization/image.py

// imshow_det_bboxes
def imshow_det_bboxes(img,
                      bboxes,
                      labels,
                      segms=None,
                      class_names=None,
                      score_thr=0,
                      bbox_color='green',
                    
                      text_color='green',
                      mask_color=None,
                      thickness=6,
                      font_size=36,
                      win_name='',
                      show=True,
                      wait_time=0,
                      out_file=None):
    """Draw bboxes and class labels (with scores) on an image.

    Args:
        img (str or ndarray): The image to be displayed.
        bboxes (ndarray): Bounding boxes (with scores), shaped (n, 4) or
            (n, 5).
        labels (ndarray): Labels of bboxes.
        segms (ndarray or None): Masks, shaped (n,h,w) or None
        class_names (list[str]): Names of each classes.
        score_thr (float): Minimum score of bboxes to be shown.  Default: 0
        bbox_color (str or tuple(int) or :obj:`Color`):Color of bbox lines.
           The tuple of color should be in BGR order. Default: 'green'
        text_color (str or tuple(int) or :obj:`Color`):Color of texts.
           The tuple of color should be in BGR order. Default: 'green'
        mask_color (str or tuple(int) or :obj:`Color`, optional):
           Color of masks. The tuple of color should be in BGR order.
           Default: None
        thickness (int): Thickness of lines. Default: 2
        font_size (int): Font size of texts. Default: 13
        show (bool): Whether to show the image. Default: True
        win_name (str): The window name. Default: ''
        wait_time (float): Value of waitKey param. Default: 0.
        out_file (str, optional): The filename to write the image.
            Default: None

    Returns:
        ndarray: The image with bboxes drawn on it.
    """
    assert bboxes.ndim == 2, \
        f' bboxes ndim should be 2, but its ndim is {bboxes.ndim}.'
    assert labels.ndim == 1, \
        f' labels ndim should be 1, but its ndim is {labels.ndim}.'
    assert bboxes.shape[0] == labels.shape[0], \
        'bboxes.shape[0] and labels.shape[0] should have the same length.'
    assert bboxes.shape[1] == 4 or bboxes.shape[1] == 5, \
        f' bboxes.shape[1] should be 4 or 5, but its {bboxes.shape[1]}.'
    img = mmcv.imread(img).astype(np.uint8)

    if score_thr > 0:
        assert bboxes.shape[1] == 5
        scores = bboxes[:, -1]
        inds = scores > score_thr
        bboxes = bboxes[inds, :]
        labels = labels[inds]
        if segms is not None:
            segms = segms[inds, ...]

    mask_colors = []
    if labels.shape[0] > 0:
        if mask_color is None:
            # random color
            np.random.seed(42)
            mask_colors = [
                np.random.randint(0, 256, (1, 3), dtype=np.uint8)
                for _ in range(max(labels) + 1)
            ]
        else:
            # specify  color
            mask_colors = [
                np.array(mmcv.color_val(mask_color)[::-1], dtype=np.uint8)
            ] * (
                max(labels) + 1)
    # 在这里修改颜色,如果添加多个颜色可设置多个 变量
    bbox_color1 = color_val_matplotlib('Blue') 
    bbox_color2 = color_val_matplotlib('color_1')  #####可更改为第三步中自己在color.py中自己设置的颜色

    ###
    text_color = color_val_matplotlib('white')

    img = mmcv.bgr2rgb(img)
    width, height = img.shape[1], img.shape[0]
    img = np.ascontiguousarray(img)

    fig = plt.figure(win_name, frameon=False)
    plt.title(win_name)
    canvas = fig.canvas
    dpi = fig.get_dpi()
    # add a small EPS to avoid precision lost due to matplotlib's truncation
    # (https://github.com/matplotlib/matplotlib/issues/15363)
    fig.set_size_inches((width + EPS) / dpi, (height + EPS) / dpi)

    # remove white edges by set subplot margin
    plt.subplots_adjust(left=0, right=1, bottom=0, top=1)
    ax = plt.gca()
    ax.axis('off')

    polygonsA = []
    polygonsB =[]
    color1 = []
    color2 = []
    for i, (bbox, label) in enumerate(zip(bboxes, labels)):
        bbox_int = bbox.astype(np.int32)
       
        label_text = class_names[
            label] if class_names is not None else f'class {label}'
        
        if len(bbox) > 4:
            label_text += f'  {bbox[-1]:.02f}'
        
        if  'A' in label_text:
            poly = [[bbox_int[0], bbox_int[1]], [bbox_int[0], bbox_int[3]],
                [bbox_int[2], bbox_int[3]], [bbox_int[2], bbox_int[1]]]
            np_poly = np.array(poly).reshape((4, 2))
            polygonsA.append(Polygon(np_poly))
            
            color1.append(bbox_color1)
        
            ax.text(
                bbox_int[0],
                bbox_int[1]-font_size,
                f'{label_text}',
                bbox={
                    'facecolor': bbox_color1 ,  #####该处更改字体框背景和类别框背景一致
                    'alpha': 1,
                    'pad': 1,
                    'edgecolor': 'none'
                },
                color=text_color,
                fontsize=font_size,
                verticalalignment='top',
                horizontalalignment='left')
                
        elif 'B' in label_text:
            poly = [[bbox_int[0], bbox_int[1]], [bbox_int[0], bbox_int[3]],
                [bbox_int[2], bbox_int[3]], [bbox_int[2], bbox_int[1]]]
            np_poly = np.array(poly).reshape((4, 2))
            polygonsB.append(Polygon(np_poly))
            
            color2.append(bbox_color2)
            
            ax.text(
            bbox_int[0],
            bbox_int[1]-font_size,
            f'{label_text}',
            bbox={
                'facecolor': bbox_color2, ######同上
                'alpha':1,
                'pad': 1,
                'edgecolor': 'none'
            },
            color=text_color,
            fontsize=font_size,
            verticalalignment='top',
            horizontalalignment='left')
        
        if segms is not None:
            color_mask = mask_colors[labels[i]]
            mask = segms[i].astype(bool)
            img[mask] = img[mask] * 0.5 + color_mask * 0.5
        
    
        

    plt.imshow(img)
    #######################设置

    pA = PatchCollection(
        polygonsA, facecolor='none', edgecolors=color1, linewidths=thickness)
    pB = PatchCollection(
        polygonsB, facecolor='none', edgecolors=color2, linewidths=thickness)
    ax.add_collection(pA)
    ax.add_collection(pB)

    stream, _ = canvas.print_to_buffer()
    buffer = np.frombuffer(stream, dtype='uint8')
    img_rgba = buffer.reshape(height, width, 4)
    rgb, alpha = np.split(img_rgba, [3], axis=2)
    img = rgb.astype('uint8')
    img = mmcv.rgb2bgr(img)

    if show:
        # We do not use cv2 for display because in some cases, opencv will
        # conflict with Qt, it will output a warning: Current thread
        # is not the object's thread. You can refer to
        # https://github.com/opencv/opencv-python/issues/46 for details
        if wait_time == 0:
            plt.show()
        else:
            plt.show(block=False)
            plt.pause(wait_time)
    if out_file is not None:
        mmcv.imwrite(img, out_file)

    plt.close()

    return img