computer vision一些术语-目标识别、目标检测、目标分割、语义分割等

转自：http://blog.csdn.net/tina_ttl/article/details/51915618

• • object recognition目标识别
  • object detection目标检测
  • Object Segmentation目标分割
  • Image Segmentation图像分割
  • semantic segmentation语义分割
  • instance segmentation
  • 附一工具

What is the difference between object detection, semantic segmentation and localization?

---

object recognition（目标识别）

• 给定一幅图像
• 检测到图像中所有的目标（类别受限于训练集中的物体类别）
• 得到检测到的目标的矩形框，并对所有检测到的矩形框进行分类
  
  

  Object Recognition: In a given image you have to detect all objects (a restricted class of objects depend on your dataset), Localized them with a bounding box and label that bounding box with a label.

object detection（目标检测）

• 与object recognition目标类似
• 但只有两个类别，只需要找到目标所在的矩形框和非目标矩形框
• 例如，人脸检测（人脸为目标、背景为非目标）、汽车检测（汽车为目标、背景为非目标）
  
  
  

  Object Detection: it’s like Object recognition but in this task you have only two class of object classification which means object bounding boxes and non-object bounding boxes. For example Car detection: you have to Detect all cars in a given image with their bounding boxes.

Object Segmentation（目标分割）

• 与object recognition相似，检测到图像中的所有目标
• 但是像素级的，需要给出属于每一类的所有像素点，而不是矩形框
  

Object Segmentation: Like object recognition you will recognize all objects in an image but your output should show this object classifying pixels of the image.

---

• object recognition：（多类目标）矩形框+类别
• object detection：（两类目标）矩形框+类别
• Object Segmentation：（多类目标）像素集+类别

---

Image Segmentation(图像分割)

• 将给定的图像分割为多个区域
• 每个区域为一类，但不需要给出label
  
  

  Image Segmentation: In image segmentation you will segment regions of the image. your output will not label segments and region of an image that consistent with each other should be in same segment. Extracting super pixels from an image is an example of this task or foreground-background segmentation.

semantic segmentation（语义分割）

• 需要对图像的每一个像素点进行分类
• 这里的类别为：多个目标类别和多个非目标类别
  
  

  Semantic Segmentation: In semantic segmentation you have to label each pixel with a class of objects (Car, Person, Dog, …) and non-objects (Water, Sky, Road, …). I other words in Semantic Segmentation you will label each region of image.

instance segmentation

• 这个还没懂，待续…..

附一工具

Google Ngrams
https://books.google.com/ngrams/graph?content=crater+detection&year_start=1800&year_end=2000&corpus=15&smoothing=3&share=&direct_url=

---

reference:
[1]http://stackoverflow.com/questions/33947823/what-is-semantic-segmentation-compared-to-segmentation-and-scene-labeling
[2]http://computerblindness.blogspot.com/2010/06/object-detection-vs-semantic.html
[3]http://cs.stackexchange.com/questions/51387/what-is-the-difference-between-object-detection-semantic-segmentation-and-local
[4]cs231n.stanford.edu/slides/winter1516_lecture8.pdf