使用Python分析姿態(tài)估計(jì)數(shù)據(jù)集COCO的教程
點(diǎn)擊上方“小白學(xué)視覺”，選擇加"星標(biāo)"或“置頂”
重磅干貨，第一時(shí)間送達(dá)
本文轉(zhuǎn)自：AI算法與圖像處理
dataset_coco
|---annotations
|---person_keypoints_train2017.json
|---person_keypoints_val2017.json
|---train2017
|---*.jpg
|---val2017
|---*.jpg
from pycocotools.coco import COCO
...
train_annot_path = 'dataset_coco/annotations /person_keypoints_train2017.json'
val_annot_path = 'dataset_coco/annotations/person_keypoints_val2017.json'
train_coco = COCO(train_annot_path) # 加載訓(xùn)練集的注釋
val_coco = COCO(val_annot_path) # 加載驗(yàn)證集的注釋
...
# 函數(shù)遍歷一個(gè)人的所有數(shù)據(jù)庫(kù)并逐行返回相關(guān)數(shù)據(jù)
def get_meta(coco):
ids = list(coco.imgs.keys())
for i, img_id in enumerate(ids):
img_meta = coco.imgs[img_id]
ann_ids = coco.getAnnIds(imgIds=img_id)
# 圖像的基本參數(shù)
img_file_name = img_meta['file_name']
w = img_meta['width']
h = img_meta['height']
# 檢索當(dāng)前圖像中所有人的元數(shù)據(jù)
anns = coco.loadAnns(ann_ids)
yield [img_id, img_file_name, w, h, anns]
...
# 迭代圖像
for img_id, img_fname, w, h, meta in get_meta(train_coco):
...
# 遍歷圖像的所有注釋
for m in meta:
# m是字典
keypoints = m['keypoints']
...
...
讓我們將COCO元數(shù)據(jù)轉(zhuǎn)換為pandas數(shù)據(jù)幀，我們使用如matplotlib、sklearn 和pandas。
def convert_to_df(coco):
images_data = []
persons_data = []
# 遍歷所有圖像
for img_id, img_fname, w, h, meta in get_meta(coco):
images_data.append({
'image_id': int(img_id),
'path': img_fname,
'width': int(w),
'height': int(h)
})
# 遍歷所有元數(shù)據(jù)
for m in meta:
persons_data.append({
'image_id': m['image_id'],
'is_crowd': m['iscrowd'],
'bbox': m['bbox'],
'area': m['area'],
'num_keypoints': m['num_keypoints'],
'keypoints': m['keypoints'],
})
# 創(chuàng)建帶有圖像路徑的數(shù)據(jù)幀
images_df = pd.DataFrame(images_data)
images_df.set_index('image_id', inplace=True)
# 創(chuàng)建與人相關(guān)的數(shù)據(jù)幀
persons_df = pd.DataFrame(persons_data)
persons_df.set_index('image_id', inplace=True)
return images_df, persons_df
images_df, persons_df = convert_to_df(train_coco)
train_coco_df = pd.merge(images_df, persons_df, right_index=True, left_index=True)
train_coco_df['source'] = 0
images_df, persons_df = convert_to_df(val_coco)
val_coco_df = pd.merge(images_df, persons_df, right_index=True, left_index=True)
val_coco_df['source'] = 1
coco_df = pd.concat([train_coco_df, val_coco_df], ignore_index=True)
# 計(jì)數(shù)
annotated_persons_df = coco_df[coco_df['is_crowd'] == 0]
crowd_df = coco_df[coco_df['is_crowd'] == 1]
print("Number of people in total: " + str(len(annotated_persons_df)))
print("Number of crowd annotations: " + str(len(crowd_df)))
persons_in_img_df = pd.DataFrame({
'cnt': annotated_persons_df['path'].value_counts()
})
persons_in_img_df.reset_index(level=0, inplace=True)
persons_in_img_df.rename(columns = {'index':'path'}, inplace = True)
# 按cnt分組，這樣我們就可以在一張圖片中得到帶有注釋人數(shù)的數(shù)據(jù)幀
persons_in_img_df = persons_in_img_df.groupby(['cnt']).count()
# 提取數(shù)組
x_occurences = persons_in_img_df.index.values
y_images = persons_in_img_df['path'].values
# 繪圖
plt.bar(x_occurences, y_images)
plt.title('People on a single image ')
plt.xticks(x_occurences, x_occurences)
plt.xlabel('Number of people in a single image')
plt.ylabel('Number of images')
plt.show()
annotated_persons_nokp_df = coco_df[(coco_df['is_crowd'] == 0) & (coco_df['num_keypoints'] == 0)]
annotated_persons_kp_df = coco_df[(coco_df['is_crowd'] == 0) & (coco_df['num_keypoints'] > 0)]
print("Number of people (with keypoints) in total: " +
str(len(annotated_persons_kp_df)))
print("Number of people without any keypoints in total: " +
str(len(annotated_persons_nokp_df)))
persons_in_img_kp_df = pd.DataFrame({
'cnt': annotated_persons_kp_df[['path','source']].value_counts()
})
persons_in_img_kp_df.reset_index(level=[0,1], inplace=True)
persons_in_img_cnt_df = persons_in_img_kp_df.groupby(['cnt']).count()
x_occurences_kp = persons_in_img_cnt_df.index.values
y_images_kp = persons_in_img_cnt_df['path'].values
f = plt.figure(figsize=(14, 8))
width = 0.4
plt.bar(x_occurences_kp, y_images_kp, width=width, label='with keypoints')
plt.bar(x_occurences + width, y_images, width=width, label='no keypoints')
plt.title('People on a single image ')
plt.xticks(x_occurences + width/2, x_occurences)
plt.xlabel('Number of people in a single image')
plt.ylabel('Number of images')
plt.legend(loc = 'best')
plt.show()
from sklearn.base import BaseEstimator, TransformerMixin
class AttributesAdder(BaseEstimator, TransformerMixin):
def __init__(self, num_keypoints, w_ix, h_ix, bbox_ix, kp_ix):
"""
:param num_keypoints: 關(guān)鍵點(diǎn)的數(shù)量
:param w_ix: 包含圖像寬度的列索引
:param h_ix: 包含圖像高度的列索引
:param bbox_ix: 包含邊框數(shù)據(jù)的列索引
:param kp_ix: 包含關(guān)鍵點(diǎn)數(shù)據(jù)的列索引
"""
self.num_keypoints = num_keypoints
self.w_ix = w_ix
self.h_ix = h_ix
self.bbox_ix = bbox_ix
self.kp_ix = kp_ix
def fit(self, X, y=None):
return self
def transform(self, X):
# 檢索特定列
w = X[:, self.w_ix]
h = X[:, self.h_ix]
bbox = np.array(X[:, self.bbox_ix].tolist()) # to matrix
keypoints = np.array(X[:, self.kp_ix].tolist()) # to matrix
# 計(jì)算邊框的比例因子
scale_x = bbox[:,2] / w
scale_y = bbox[:,3] / h
aspect_ratio = w / h
# 計(jì)算規(guī)模類別
scale_cat = pd.cut(scale_y,
bins=[0., 0.4, 0.6, 0.8, np.inf],
labels=['S', 'M', 'L', 'XL'])
return np.c_[X, scale_x, scale_y, scale_cat, aspect_ratio, keypoints]
# 用于添加新列的transformer對(duì)象
attr_adder = AttributesAdder(num_keypoints=17, ...)
coco_extra_attribs = attr_adder.transform(coco_df.values)
# 創(chuàng)建列發(fā)新列表
keypoints_cols = [['x'+str(idx), 'y'+str(idx), 'v'+str(idx)]
for idx, k in enumerate(range(num_keypoints))]
keypoints_cols = np.concatenate(keypoints_cols).tolist()
# 創(chuàng)建新的更豐富的數(shù)據(jù)z幀
coco_extra_attribs_df = pd.DataFrame(
coco_extra_attribs,
columns=list(coco_df.columns) +
["scale_x", "scale_y", "scale_cat", "aspect_ratio"] +
keypoints_cols,
index=coco_df.index)
如果scale_y在[0–0.4）范圍內(nèi)，則類別為S 如果scale_y在[0.4–0.6）范圍內(nèi)，則類別為M 如果scale_y在[0.6–0.8）范圍內(nèi)，則類別為L(zhǎng) 如果scale_y在[0.8–1.0）范圍內(nèi)，則類別為XL
# 對(duì)水平圖像進(jìn)行關(guān)鍵點(diǎn)坐標(biāo)標(biāo)準(zhǔn)化
horiz_imgs_df = coco_extra_attribs_df[coco_extra_attribs_df['aspect_ratio'] >= 1.]
# 獲取平均寬度和高度-用于縮放關(guān)鍵點(diǎn)坐標(biāo)
avg_w = int(horiz_imgs_df['width'].mean())
avg_h = int(horiz_imgs_df['height'].mean())
class NoseAttributesAdder(BaseEstimator, TransformerMixin):
def __init__(self, avg_w, avg_h, w_ix, h_ix, x1_ix, y1_ix, v1_ix):
self.avg_w = avg_w
self.avg_h = avg_h
self.w_ix = w_ix
self.h_ix = h_ix
self.x1_ix = x1_ix
self.y1_ix = y1_ix
self.v1_ix = v1_ix
def fit(self, X, y=None):
return self
def transform(self, X):
w = X[:, self.w_ix]
h = X[:, self.h_ix]
x1 = X[:, self.x1_ix]
y1 = X[:, self.y1_ix]
# 標(biāo)準(zhǔn)化鼻子坐標(biāo)，提供平均寬度和高度
scale_x = self.avg_w / w
scale_y = self.avg_h / h
nose_x = x1 * scale_x
nose_y = y1 * scale_y
return np.c_[X, nose_x, nose_y]
# 用于標(biāo)準(zhǔn)化鼻子坐標(biāo)列的transformer對(duì)象
w_ix = horiz_imgs_df.columns.get_loc('width')
h_ix = horiz_imgs_df.columns.get_loc('height')
x1_ix = horiz_imgs_df.columns.get_loc('x0') # 鼻子的x坐標(biāo)在'x0'列中
y1_ix = horiz_imgs_df.columns.get_loc('y0') # 鼻子的y坐標(biāo)在'y0'列中
v1_ix = horiz_imgs_df.columns.get_loc('v0') # 鼻頭的可見性
attr_adder = NoseAttributesAdder(avg_w, avg_h, w_ix, h_ix, x1_ix, y1_ix, v1_ix)
coco_noses = attr_adder.transform(horiz_imgs_df.values)
# 使用標(biāo)準(zhǔn)化的數(shù)據(jù)創(chuàng)建新數(shù)據(jù)幀
coco_noses_df = pd.DataFrame(
coco_noses,
columns=list(horiz_imgs_df.columns) + ["normalized_nose_x", "normalized_nose_y"],
index=horiz_imgs_df.index)
# 過濾-只有可見的鼻子
coco_noses_df = coco_noses_df[coco_noses_df["v0"] == 2]
coco_noses_df.plot(kind="scatter", x="normalized_nose_x",
y="normalized_nose_y", alpha=0.3).invert_yaxis()
low_noses_df = coco_noses_df[coco_noses_df['normalized_nose_y'] > 430 ]
low_noses_df
y_images = coco_extra_attribs_df['num_keypoints'].value_counts()
x_keypoints = y_images.index.values
# 繪圖
plt.figsize=(10,5)
plt.bar(x_keypoints, y_images)
plt.title('Histogram of keypoints')
plt.xticks(x_keypoints)
plt.xlabel('Number of keypoints')
plt.ylabel('Number of bboxes')
plt.show()
# 帶有若干關(guān)鍵點(diǎn)(行)的bboxes(列)百分比
kp_df = pd.DataFrame({
"Num keypoints %": coco_extra_attribs_df[
"num_keypoints"].value_counts() / len(coco_extra_attribs_df)
}).sort_index()
persons_df = coco_extra_attribs_df[coco_extra_attribs_df['num_keypoints'] > 0]
persons_df['scale_cat'].hist()
scales_props_df = pd.DataFrame({
"Scales": persons_df["scale_cat"].value_counts() / len(persons_df)
})
scales_props_df
persons_df = coco_extra_attribs_df[coco_extra_attribs_df['num_keypoints'] > 0]
train_df = persons_df[persons_df['source'] == 0]
val_df = persons_df[persons_df['source'] == 1]
scales_props_df = pd.DataFrame({
"Scales in train set %": train_df["scale_cat"].value_counts() / len(train_df),
"Scales in val set %": val_df["scale_cat"].value_counts() / len(val_df)
})
scales_props_df["Diff 100%"] = 100 * \
np.absolute(scales_props_df["Scales in train set %"] -
scales_props_df["Scales in val set %"])
train_df = coco_extra_attribs_df[coco_extra_attribs_df['source'] == 0]
val_df = coco_extra_attribs_df[coco_extra_attribs_df['source'] == 1]
kp_props_df = pd.DataFrame({
"Num keypoints in train set %": train_df["num_keypoints"].value_counts() /
len(train_df),
"Num keypoints in val set %": val_df["num_keypoints"].value_counts() /
len(val_df)
}).sort_index()
kp_props_df["Diff 100%"] = 100 * \
np.absolute(kp_props_df["Num keypoints in train set %"] -
kp_props_df["Num keypoints in val set %"])
總結(jié)
交流群
歡迎加入公眾號(hào)讀者群一起和同行交流，目前有SLAM、三維視覺、傳感器、自動(dòng)駕駛、計(jì)算攝影、檢測(cè)、分割、識(shí)別、醫(yī)學(xué)影像、GAN、算法競(jìng)賽等微信群（以后會(huì)逐漸細(xì)分），請(qǐng)掃描下面微信號(hào)加群，備注：”昵稱+學(xué)校/公司+研究方向“，例如：”張三 + 上海交大 + 視覺SLAM“。請(qǐng)按照格式備注，否則不予通過。添加成功后會(huì)根據(jù)研究方向邀請(qǐng)進(jìn)入相關(guān)微信群。請(qǐng)勿在群內(nèi)發(fā)送廣告，否則會(huì)請(qǐng)出群，謝謝理解~
評(píng)論
圖片
表情