如何使用yolo3 keras显示边界框的坐标？

Question

我需要在 yolo3 keras 代码中添加 function 代码，该代码打印出形成的框的边界框坐标

https://github.com/experiencor/keras-yolo3/blob/master/yolo3_one_file_to_detect_them_all.py

我不确定是否必须更改现有的 function 才能完成

def preprocess_input(image, net_h, net_w):
    new_h, new_w, _ = image.shape

    # determine the new size of the image
    if (float(net_w)/new_w) < (float(net_h)/new_h):
        new_h = (new_h * net_w)/new_w
        new_w = net_w
    else:
        new_w = (new_w * net_h)/new_h
        new_h = net_h

    # resize the image to the new size
    resized = cv2.resize(image[:,:,::-1]/255., (int(new_w), int(new_h)))

    # embed the image into the standard letter box
    new_image = np.ones((net_h, net_w, 3)) * 0.5
    new_image[int((net_h-new_h)//2):int((net_h+new_h)//2), int((net_w-new_w)//2):int((net_w+new_w)//2), :] = resized
    new_image = np.expand_dims(new_image, 0)

    return new_image

def decode_netout(netout, anchors, obj_thresh, nms_thresh, net_h, net_w):
    grid_h, grid_w = netout.shape[:2]
    nb_box = 3
    netout = netout.reshape((grid_h, grid_w, nb_box, -1))
    nb_class = netout.shape[-1] - 5

    boxes = []

    netout[..., :2]  = _sigmoid(netout[..., :2])
    netout[..., 4:]  = _sigmoid(netout[..., 4:])
    netout[..., 5:]  = netout[..., 4][..., np.newaxis] * netout[..., 5:]
    netout[..., 5:] *= netout[..., 5:] > obj_thresh

    for i in range(grid_h*grid_w):
        row = i / grid_w
        col = i % grid_w

        for b in range(nb_box):
            # 4th element is objectness score
            objectness = netout[int(row)][int(col)][b][4]
            #objectness = netout[..., :4]

            if(objectness.all() <= obj_thresh): continue

            # first 4 elements are x, y, w, and h
            x, y, w, h = netout[int(row)][int(col)][b][:4]

            x = (col + x) / grid_w # center position, unit: image width
            y = (row + y) / grid_h # center position, unit: image height
            w = anchors[2 * b + 0] * np.exp(w) / net_w # unit: image width
            h = anchors[2 * b + 1] * np.exp(h) / net_h # unit: image height  

            # last elements are class probabilities
            classes = netout[int(row)][col][b][5:]

            box = BoundBox(x-w/2, y-h/2, x+w/2, y+h/2, objectness, classes)
            #box = BoundBox(x-w/2, y-h/2, x+w/2, y+h/2, None, classes)


            boxes.append(box)

    return boxes

def correct_yolo_boxes(boxes, image_h, image_w, net_h, net_w):
    if (float(net_w)/image_w) < (float(net_h)/image_h):
        new_w = net_w
        new_h = (image_h*net_w)/image_w
    else:
        new_h = net_w
        new_w = (image_w*net_h)/image_h

    for i in range(len(boxes)):
        x_offset, x_scale = (net_w - new_w)/2./net_w, float(new_w)/net_w
        y_offset, y_scale = (net_h - new_h)/2./net_h, float(new_h)/net_h

        boxes[i].xmin = int((boxes[i].xmin - x_offset) / x_scale * image_w)
        boxes[i].xmax = int((boxes[i].xmax - x_offset) / x_scale * image_w)
        boxes[i].ymin = int((boxes[i].ymin - y_offset) / y_scale * image_h)
        boxes[i].ymax = int((boxes[i].ymax - y_offset) / y_scale * image_h)



def do_nms(boxes, nms_thresh):
    if len(boxes) > 0:
        nb_class = len(boxes[0].classes)
    else:
        return

    for c in range(nb_class):
        sorted_indices = np.argsort([-box.classes[c] for box in boxes])

        for i in range(len(sorted_indices)):
            index_i = sorted_indices[i]

            if boxes[index_i].classes[c] == 0: continue

            for j in range(i+1, len(sorted_indices)):
                index_j = sorted_indices[j]

                if bbox_iou(boxes[index_i], boxes[index_j]) >= nms_thresh:
                    boxes[index_j].classes[c] = 0

def draw_boxes(image, boxes, labels, obj_thresh):
    for box in boxes:
        label_str = ''
        label = -1

        for i in range(len(labels)):
            if box.classes[i] > obj_thresh:
                label_str += labels[i]
                label = i
                print(labels[i] + ': ' + str(box.classes[i]*100) + '%')

        if label >= 0:
            cv2.rectangle(image, (box.xmin,box.ymin), (box.xmax,box.ymax), (0,255,0), 3)
            cv2.putText(image, 
                        label_str + ' ' + str(box.get_score()), 
                        (box.xmin, box.ymin - 13), 
                        cv2.FONT_HERSHEY_SIMPLEX, 
                        1e-3 * image.shape[0], 
                        (0,255,0), 2)

    return image      

output 应采用以下形式

Box : (s,t),(u,v),(x,y),(w,z)

Answer 1

我认为您正在寻找cv2.rectangle(image, (box.xmin,box.ymin), (box.xmax,box.ymax), (0,255,0), 3)部分。

您可以使用 for 循环，即：

for i in range(len(labels)):
        if box.classes[i] > obj_thresh:
            label_str += labels[i]
            label = i
            print(labels[i] + ': ' + str(box.classes[i]*100) + '%')

使用i的索引来操作您要获取(box.xmin,box.ymin), (box.xmax, box.ymax)和 append 的坐标的 label 的坐标，以获取整个边界框。

例如：

def draw_boxes(image, boxes, labels, obj_thresh):
    dummy_array = []
    for box in boxes:
        label_str = ''
        label = -1

        for i in range(len(labels)):
            if box.classes[i] > obj_thresh:
                label_str += labels[i]
                label = i
                print(labels[i] + ': ' + str(box.classes[i]*100) + '%')

        if label >= 0:
            cv2.rectangle(image, (box.xmin,box.ymin), (box.xmax,box.ymax), (0,255,0), 3)
            dummy_array.append([(box.xmin, box.ymin), (box.xmax, box.ymax)])
            cv2.putText(image, 
                        label_str + ' ' + str(box.get_score()), 
                        (box.xmin, box.ymin - 13), 
                        cv2.FONT_HERSHEY_SIMPLEX, 
                        1e-3 * image.shape[0], 
                        (0,255,0), 2)
            cv2.boundingRect()

    return image, dummy_array

笔记：

我不完全确定示例代码是否完美运行，我想尝试的只是给人一种做这种工作的感觉。 如果代码不能完美运行，您可以尝试其他具有这种意义的东西。