WIDER FACE转为COCO数据集格式标注

前言

WIDER FACE是一个人脸数据集，COCO是一个目标检测数据集。目前由很多针对COCO数据集格式的代码，因此将WIDER FACE的标注文件转换成COCO标注格式可以很方便的应用现有代码。
下面给出两个数据集的相关网址：
WIDER FACE: A Face Detection Benchmark
COCO

准备工作

我们需要准备两样东西：图片和对应标注文件，都可以在WIDERE FACE网站上进行获取，如下图所示。

从上到下依次是训练、验证、测试集图片和标注文件，最后一个是提交格式示例，不需要管。

这一步，我下载了上面的三个文件夹，获得了所有的图片数据。而标注文件，我选择了从https://github.com/vitoralbiero/img2pose/wiki/Annotations获取。

原因是他提供了json格式的标注文件，读取起来更加方便顺手。

代码

"""
将WIDER FACE数据集标注文件格式 转换为 COCO数据集格式
"""

import os
import json
import numpy as np
import pandas as pd
from PIL import Image
from tqdm import tqdm

g_samples = []
g_bboxes = []


def load_data(json_list, dataset_path):
    image_paths = pd.read_csv(json_list, delimiter=" ", header=None)
    image_paths = np.asarray(image_paths).squeeze()

    print("Loading frames paths...")

    for image_path in tqdm(image_paths):  # 遍历各个图片的json标注文件
        with open(image_path) as f:
            image_json = json.load(f)
        # path to the image
        img_path = image_json["image_path"]
        # if not absolute path, append the dataset path
        if dataset_path is not None:
            img_path = os.path.join(dataset_path, img_path)
        g_samples.append(img_path)
        g_bboxes.append(image_json["bboxes"])


def main():
    cnt = 0
    json_list = r".\annotations\WIDER_train_annotations.txt"
    dataset_path = r".\datasets\WIDER_Face\WIDER_train\images"
    print("Loading dataset from %s" % json_list)
    load_data(json_list, dataset_path)
    
    res = {
        "info": {},
        "licenses": {},
        "images": [],
        "annotations": [],
	    "categories": []
    }

    for index in tqdm(range(len(g_samples))):
        image_path = g_samples[index]
        img = Image.open(image_path)
        (w, h) = img.size
        # del img
        image_id = image_path.split("\\")[-1].split("/")[-1].split(".")[0]
        image = {
            "file_name": image_path.split("\\")[-1].split("/")[-1],
            "height": h,
            "width": w,
            "data_captured": "2022-07-08 17:02:52",
            "id": image_id,
        }
        res["images"].append(image)

        bboxes = g_bboxes[index]  # [[a, b, c, d], [a, b, c, d], ...]

        for i in range(len(bboxes)):
            bbox = np.asarray(bboxes[i])[:4].astype(float)
            x = bbox[0] + bbox[2]
            y = bbox[1] + bbox[3]
            bbox_w = bbox[2] - bbox[0]
            bbox_h = bbox[3] - bbox[1]
            annotation = {
                "segmentation": [],
                "area": 0,
                "iscrowd": 0,
                "image_id": image_id,
                "bbox": [x, y, bbox_w, bbox_h],
                "category_id": 1,
                "id": cnt,
            }
            cnt += 1
            res["annotations"].append(annotation)

    with open("instances_train2017_without_trans.json", "w") as f:
        json.dump(res, f)


if __name__ == '__main__':
    main()

代码看起来很长，但其实很简单，重要的只有四行：

x = bbox[0] + bbox[2]
y = bbox[1] + bbox[3]
bbox_w = bbox[2] - bbox[0]
bbox_h = bbox[3] - bbox[1]

这四行完成了bbox标注差异的转换。

代码中categories列表的内容是空的[ ]，可以换成附录中默认的内容，也可以自己仿照格式进行自定义。
由于WIDER FACE全是人脸，因此annotation中的category_id全是1，即默认person这个类别的id。

参考资料

http://shuoyang1213.me/WIDERFACE/
https://cocodataset.org/#format-data
MMDetection学习笔记-04自定义COCO数据集
【数据集转换】COCO数据集格式
SSD人脸检测实战：Wider Face数据集介绍、标注格式、下载等

附录

默认COCO的categories。

{
    "supercategory": "person",
    "id": 1,
    "name": "person"
},
{
    "supercategory": "vehicle",
    "id": 2,
    "name": "bicycle"
},
{
    "supercategory": "vehicle",
    "id": 3,
    "name": "car"
},
{
    "supercategory": "vehicle",
    "id": 4,
    "name": "motorcycle"
},
{
    "supercategory": "vehicle",
    "id": 5,
    "name": "airplane"
},
{
    "supercategory": "vehicle",
    "id": 6,
    "name": "bus"
},
{
    "supercategory": "vehicle",
    "id": 7,
    "name": "train"
},
{
    "supercategory": "vehicle",
    "id": 8,
    "name": "truck"
},
{
    "supercategory": "vehicle",
    "id": 9,
    "name": "boat"
},
{
    "supercategory": "outdoor",
    "id": 10,
    "name": "traffic light"
},
{
    "supercategory": "outdoor",
    "id": 11,
    "name": "fire hydrant"
},
{
    "supercategory": "outdoor",
    "id": 13,
    "name": "stop sign"
},
{
    "supercategory": "outdoor",
    "id": 14,
    "name": "parking meter"
},
{
    "supercategory": "outdoor",
    "id": 15,
    "name": "bench"
},
{
    "supercategory": "animal",
    "id": 16,
    "name": "bird"
},
{
    "supercategory": "animal",
    "id": 17,
    "name": "cat"
},
{
    "supercategory": "animal",
    "id": 18,
    "name": "dog"
},
{
    "supercategory": "animal",
    "id": 19,
    "name": "horse"
},
{
    "supercategory": "animal",
    "id": 20,
    "name": "sheep"
},
{
    "supercategory": "animal",
    "id": 21,
    "name": "cow"
},
{
    "supercategory": "animal",
    "id": 22,
    "name": "elephant"
},
{
    "supercategory": "animal",
    "id": 23,
    "name": "bear"
},
{
    "supercategory": "animal",
    "id": 24,
    "name": "zebra"
},
{
    "supercategory": "animal",
    "id": 25,
    "name": "giraffe"
},
{
    "supercategory": "accessory",
    "id": 27,
    "name": "backpack"
},
{
    "supercategory": "accessory",
    "id": 28,
    "name": "umbrella"
},
{
    "supercategory": "accessory",
    "id": 31,
    "name": "handbag"
},
{
    "supercategory": "accessory",
    "id": 32,
    "name": "tie"
},
{
    "supercategory": "accessory",
    "id": 33,
    "name": "suitcase"
},
{
    "supercategory": "sports",
    "id": 34,
    "name": "frisbee"
},
{
    "supercategory": "sports",
    "id": 35,
    "name": "skis"
},
{
    "supercategory": "sports",
    "id": 36,
    "name": "snowboard"
},
{
    "supercategory": "sports",
    "id": 37,
    "name": "sports ball"
},
{
    "supercategory": "sports",
    "id": 38,
    "name": "kite"
},
{
    "supercategory": "sports",
    "id": 39,
    "name": "baseball bat"
},
{
    "supercategory": "sports",
    "id": 40,
    "name": "baseball glove"
},
{
    "supercategory": "sports",
    "id": 41,
    "name": "skateboard"
},
{
    "supercategory": "sports",
    "id": 42,
    "name": "surfboard"
},
{
    "supercategory": "sports",
    "id": 43,
    "name": "tennis racket"
},
{
    "supercategory": "kitchen",
    "id": 44,
    "name": "bottle"
},
{
    "supercategory": "kitchen",
    "id": 46,
    "name": "wine glass"
},
{
    "supercategory": "kitchen",
    "id": 47,
    "name": "cup"
},
{
    "supercategory": "kitchen",
    "id": 48,
    "name": "fork"
},
{
    "supercategory": "kitchen",
    "id": 49,
    "name": "knife"
},
{
    "supercategory": "kitchen",
    "id": 50,
    "name": "spoon"
},
{
    "supercategory": "kitchen",
    "id": 51,
    "name": "bowl"
},
{
    "supercategory": "food",
    "id": 52,
    "name": "banana"
},
{
    "supercategory": "food",
    "id": 53,
    "name": "apple"
},
{
    "supercategory": "food",
    "id": 54,
    "name": "sandwich"
},
{
    "supercategory": "food",
    "id": 55,
    "name": "orange"
},
{
    "supercategory": "food",
    "id": 56,
    "name": "broccoli"
},
{
    "supercategory": "food",
    "id": 57,
    "name": "carrot"
},
{
    "supercategory": "food",
    "id": 58,
    "name": "hot dog"
},
{
    "supercategory": "food",
    "id": 59,
    "name": "pizza"
},
{
    "supercategory": "food",
    "id": 60,
    "name": "donut"
},
{
    "supercategory": "food",
    "id": 61,
    "name": "cake"
},
{
    "supercategory": "furniture",
    "id": 62,
    "name": "chair"
},
{
    "supercategory": "furniture",
    "id": 63,
    "name": "couch"
},
{
    "supercategory": "furniture",
    "id": 64,
    "name": "potted plant"
},
{
    "supercategory": "furniture",
    "id": 65,
    "name": "bed"
},
{
    "supercategory": "furniture",
    "id": 67,
    "name": "dining table"
},
{
    "supercategory": "furniture",
    "id": 70,
    "name": "toilet"
},
{
    "supercategory": "electronic",
    "id": 72,
    "name": "tv"
},
{
    "supercategory": "electronic",
    "id": 73,
    "name": "laptop"
},
{
    "supercategory": "electronic",
    "id": 74,
    "name": "mouse"
},
{
    "supercategory": "electronic",
    "id": 75,
    "name": "remote"
},
{
    "supercategory": "electronic",
    "id": 76,
    "name": "keyboard"
},
{
    "supercategory": "electronic",
    "id": 77,
    "name": "cell phone"
},
{
    "supercategory": "appliance",
    "id": 78,
    "name": "microwave"
},
{
    "supercategory": "appliance",
    "id": 79,
    "name": "oven"
},
{
    "supercategory": "appliance",
    "id": 80,
    "name": "toaster"
},
{
    "supercategory": "appliance",
    "id": 81,
    "name": "sink"
},
{
    "supercategory": "appliance",
    "id": 82,
    "name": "refrigerator"
},
{
    "supercategory": "indoor",
    "id": 84,
    "name": "book"
},
{
    "supercategory": "indoor",
    "id": 85,
    "name": "clock"
},
{
    "supercategory": "indoor",
    "id": 86,
    "name": "vase"
},
{
    "supercategory": "indoor",
    "id": 87,
    "name": "scissors"
},
{
    "supercategory": "indoor",
    "id": 88,
    "name": "teddy bear"
},
{
    "supercategory": "indoor",
    "id": 89,
    "name": "hair drier"
},
{
    "supercategory": "indoor",
    "id": 90,
    "name": "toothbrush"
}