物体检测¶
计算机视觉中目标检测、跟踪、识别是最基本的几个task，尤其又以检测最为重要和基础。同时基本上所有的检测任务都需要在给出物体的bounding box之后，给出物体的类别（也就是给识别物体）。
其思想就是在目标区域用bounding box随机框出一些区域，验证该区域是否有可以检测到的物体，并在一次次的纠错训练中找到物体真正的所在位置。以下是针对灵活使用bounding box的一些练习。
练习一¶
1、为图片添加3*3个bounding box，并在每个bounding box 里添加3个bounding box。
2、在每个bounding box里随机嵌入更小的bounding box。
- 优点：为整张图片均匀地加了bounding box，不存在漏掉哪部份的情况。
- 缺点：bounding boxes 之间无重叠，相互独立，容易将完整的物体分割成几部分，容易破坏物体的完整性，加大了物体检测的难度。
In [25]:
import os
import sys
import cv2
import numpy as np
import IPython
#-------------------------------------------------------------------
def imshow(img):
_,ret = cv2.imencode('.jpg', img)
i = IPython.display.Image(data=ret)
IPython.display.display(i)
#-------------------------------------------------------------------
def grid_boxes(n,m,width,height):
h = width/n
v = height/m
boxes = []
for i in range(m):
for j in range(n):
xmin = h * j
ymin = v * i
xmax = h *(j+1)
ymax = v *(i+1)
box = [int(xmin),int(ymin),int(xmax),int(ymax)]
boxes.append(box)
return boxes
#-------------------------------------------------------------------
def random_boxes(numbers,width,height):
boxes = []
for i in range(numbers):
xmin = np.random.randint(width)
ymin = np.random.randint(height)
xmax = xmin + np.random.randint(100)*i
ymax = ymin + np.random.randint(50)*2*i
if xmax <= width and ymax <= height:
box = [xmin,ymin,xmax,ymax]
boxes.append(box)
return boxes
#-------------------------------------------------------------------
def draw_boxes(boxes,img):
for box in boxes:
b = np.random.randint(10,255)
g = np.random.randint(10,255)
r = np.random.randint(10,255)
img = cv2.rectangle(img,(box[0]+2,box[1]+2),(box[2]-2,box[3]-2),(b,g,r),2)
return img
def scaling(boxes):
scales = [1.0/8, 1.0/4, 0.3, 0.7, 0.4]
boxes1 = []
for box in boxes:
boxes1.append(box)
for s in scales:
w = int((box[2] - box[0])*s)
h = int((box[3] - box[1])*s)
b = [box[0] + w,
box[1] + h,
box[2] - w,
box[3] - h]
boxes1.append(b)
return boxes1
#-------------------------------------------------------------------
width = 800
height= 500
filename = "../test/images/shanghai.jpg"
img = cv2.imread(filename)
img = cv2.resize(img,(width,height))
boxes = random_boxes(100,width,height)
boxes = grid_boxes(3,3,width, height)
boxes = scaling(boxes)
img = draw_boxes(boxes,img)
imshow(img)
练习二¶
吸取上一训练的经验，这个练习里我在图片的任意位置上随机添加任意大小、任意颜色的bounding box。
- 优点：由于添加bounding box的位置以及bounding box的大小、方向都随机，提升了被检测物体的完整度，物体被检测到的几率更大。
- 缺点：由于bounding boxes都是随机添加的，这些边框容易集中在某些固定的区域，从而漏掉一些的部分，所以仍需改善。
In [24]:
import os
import sys
import cv2
import numpy as np
import IPython
#-------------------------------------------------------------------
def imshow(img):
_,ret = cv2.imencode('.jpg', img)
i = IPython.display.Image(data=ret)
IPython.display.display(i)
#-------------------------------------------------------------------
def grid_boxes(n,m,width,height):
h = width/n
v = height/m
boxes = []
for i in range(m):
for j in range(n):
xmin = h * j
ymin = v * i
xmax = h *(j+1)
ymax = v *(i+1)
box = [int(xmin),int(ymin),int(xmax),int(ymax)]
boxes.append(box)
return boxes
#-------------------------------------------------------------------
def random_boxes(numbers,width,height):
boxes = []
for i in range(numbers):
xmin = np.random.randint(width)
ymin = np.random.randint(height)
xmax = xmin + np.random.randint(100)*i
ymax = ymin + np.random.randint(50)*2*i
if xmax <= width and ymax <= height:
box = [xmin,ymin,xmax,ymax]
boxes.append(box)
return boxes
#-------------------------------------------------------------------
def draw_boxes(boxes,img):
for box in boxes:
b = np.random.randint(10,255)
g = np.random.randint(10,255)
r = np.random.randint(10,255)
img = cv2.rectangle(img,(box[0]+2,box[1]+2),(box[2]-2,box[3]-2),(b,g,r),2)
return img
def scaling(boxes):
scales = [1.0/8, 1.0/4, 0.3, 0.7, 0.4]
boxes1 = []
for box in boxes:
boxes1.append(box)
for s in scales:
w = int((box[2] - box[0])*s)
h = int((box[3] - box[1])*s)
b = [box[0] + w,
box[1] + h,
box[2] - w,
box[3] - h]
boxes1.append(b)
return boxes1
def aspect_ratio(boxes,width,height):
scales = [1.0/8, 1.0/4]
boxes1 = []
for box in boxes:
boxes1.append(box)
for s in scales:
w = int((box[2] - box[0])*s)
h = int((box[3] - box[1])*s)
X1 = max(box[0] + w, 0)
Y1 = max(box[1] - h, 0)
X2 = min(box[2] - w, width)
Y2 = min(box[3] + h, height)
b = [X1,Y1,X2,Y2]
x1 = max(box[0] - w, 0)
y1 = max(box[1] + h, 0)
x2 = min(box[2] + w, width)
y2 = min(box[3] - h, height)
b1 = [x1,y1,x2,y2]
boxes1.append(b)
boxes1.append(b1)
return boxes1
#-------------------------------------------------------------------
width = 800
height= 500
filename = "../test/images/shanghai.jpg"
img = cv2.imread(filename)
img = cv2.resize(img,(width,height))
boxes = random_boxes(100,width,height)
# boxes = grid_boxes(3,3,width, height)
boxes1 = scaling(boxes)
boxes2 = aspect_ratio(boxes,width,height)
boxes = boxes1 + boxes2
img = draw_boxes(boxes,img)
imshow(img)
练习三¶
1、结合练习一和练习二，首先为图片整体一层一层添加可重叠的边框，从横向纵向来说考虑到每个位置，没有漏掉哪部份。
2、再结合练习二，在任意位置随机添加大小不一的边框，更能提升检测率。
In [45]:
import os
import sys
import cv2
import numpy as np
import IPython
#-------------------------------------------------------------------
def imshow(img):
_,ret = cv2.imencode('.jpg', img)
i = IPython.display.Image(data=ret)
IPython.display.display(i)
#-------------------------------------------------------------------
def sliding(img,w,h,stride_w,stride_h):
boxes = []
width = img.shape[1]
height= img.shape[0]
for i in range(0,height-h,stride_h):
for j in range(0,width-w,stride_w):
xmin = j
ymin = i
xmax = w + j
ymax = h + i
box = [int(xmin),int(ymin),int(xmax),int(ymax)]
boxes.append(box)
return boxes
#-------------------------------------------------------------------
def random_boxes(numbers,width,height):
boxes = []
for i in range(numbers):
xmin = np.random.randint(width)
ymin = np.random.randint(height)
xmax = xmin + np.random.randint(100)*i
ymax = ymin + np.random.randint(50)*2*i
if xmax <= width and ymax <= height:
box = [xmin,ymin,xmax,ymax]
boxes.append(box)
return boxes
#-------------------------------------------------------------------
def draw_boxes(boxes,img):
for box in boxes:
b = np.random.randint(10,255)
g = np.random.randint(10,255)
r = np.random.randint(10,255)
img = cv2.rectangle(img,(box[0]+2,box[1]+2),(box[2]-2,box[3]-2),(b,g,r),2)
return img
def scaling(boxes):
scales = [1.0/8, 1.0/4, 0.3, 0.7, 0.4]
boxes1 = []
for box in boxes:
boxes1.append(box)
for s in scales:
w = int((box[2] - box[0])*s)
h = int((box[3] - box[1])*s)
b = [box[0] + w,
box[1] + h,
box[2] - w,
box[3] - h]
boxes1.append(b)
return boxes1
def aspect_ratio(boxes,width,height):
scales = [1.0/8, 1.0/4]
boxes1 = []
for box in boxes:
boxes1.append(box)
for s in scales:
w = int((box[2] - box[0])*s)
h = int((box[3] - box[1])*s)
X1 = max(box[0] + w, 0)
Y1 = max(box[1] - h, 0)
X2 = min(box[2] - w, width)
Y2 = min(box[3] + h, height)
b = [X1,Y1,X2,Y2]
x1 = max(box[0] - w, 0)
y1 = max(box[1] + h, 0)
x2 = min(box[2] + w, width)
y2 = min(box[3] - h, height)
b1 = [x1,y1,x2,y2]
boxes1.append(b)
boxes1.append(b1)
return boxes1
#-------------------------------------------------------------------
width = 800
height= 500
filename = "../test/images/shanghai.jpg"
img = cv2.imread(filename)
img = cv2.resize(img,(width,height))
# boxes = random_boxes(100,width,height)
boxes = sliding(img,200,100,50,20)
boxes1 = scaling(boxes)
boxes2 = aspect_ratio(boxes,width,height)
boxes = boxes1 + boxes2
img = draw_boxes(boxes[:60],img)
imshow(img)
