szeliski——computer vision algorithm and application<一>introduction

 CV的实际应用包括下面重要的几方面;

Optical character recognition (OCR): reading handwritten postal codes on letters(Figure 1.4a) and automatic number plate recognition (ANPR);
Machine inspection: rapid parts inspection for quality assurance using stereo vision with specialized illumination to measure tolerances on aircraft wings or auto body parts(Figure 1.4b) or looking for defects in steel castings using X-ray vision;
Retail: object recognition for automated checkout lanes (Figure 1.4c);
3D model building (photogrammetry): fully automated construction of 3D models from aerial photographs used in systems such as Bing Maps;
Medical imaging: registering pre-operative and intra-operative imagery (Figure 1.4d) or performing long-term studies of people’s brain morphology as they age;
Automotive safety: detecting unexpected obstacles such as pedestrians on the street, under conditions where active vision techniques such as radar or lidar do not work well (Figure 1.4e; see also Miller, Campbell, Huttenlocher et al. (2008); Montemerlo,Becker, Bhat et al. (2008); Urmson, Anhalt, Bagnell et al. (2008) for examples of fully automated driving);
Match move: merging computer-generated imagery (CGI) with live action footage by tracking feature points in the source video to estimate the 3D camera motion and shape of the environment. Such techniques are widely used in Hollywood (e.g., in movies such as Jurassic Park) (Roble 1999; Roble and Zafar 2009); they also require the use of precise matting to insert new elements between foreground and background elements(Chuang, Agarwala, Curless et al. 2002).

Motion capture (mocap): using retro-reflective markers viewed from multiple cameras or other vision-based techniques to capture actors for computer animation;
Surveillance: monitoring for intruders, analyzing highway traffic (Figure 1.4f), and monitoring pools for drowning victims;
Fingerprint recognition and biometrics: for automatic access authentication as well as forensic applications.

David Lowe’s 工业视觉网站(http://www.cs.ubc.ca/spider/lowe/vision.html) 列出了很多视觉的工业应用，上面所介绍的计算机视觉应用都是在实际中很重要的应用方向。

szeliski在书中介绍的计算机视觉方面更加偏向于自己动手处理照片和视频，包括如下的方面：

Stitching:全景拼接 turning overlapping photos into a single seamlessly stitched panorama (Figure 1.5a), as described in Chapter 9;
Exposure bracketing: merging multiple exposures taken under challenging lighting
conditions (strong sunlight and shadows) into a single perfectly exposed image (Figure 1.5b), as described in Section 10.2;
Morphing: 变形turning a picture of one of your friends into another, using a seamless morph transition (Figure 1.5c);
3D modeling: 3D建模 converting one or more snapshots into a 3D model of the object or person you are photographing (Figure 1.5d), as described in Section 12.6
Video match move and stabilization: inserting 2D pictures or 3D models into your videos by automatically tracking nearby reference points (see Section 7.4.2)3 or using motion estimates to remove shake from your videos (see Section 8.2.1);
Photo-based walkthroughs: navigating a large collection of photographs, such as the interior of your house, by flying between different photos in 3D (see Sections 13.1.2 and 13.5.5)
Face detection: for improved camera focusing as well as more relevant image searching (see Section 14.1.1);
Visual authentication: automatically logging family members onto your home computer as they sit down in front of the webcam (see Section 14.2).

太好玩了吧，好有意思啊！！！必须学啊，本来就是这个领域的，啊，之前面试被批的体无完肤绝对是应该的啊！！！连这些都不知道，玩个锤锤的CV哦！！！

解决问题的时候，最好是从手上的问题去想合适的技术，而不是直接拿听过的技术。这种就是典型的工程师方法来学习视觉并且反映自己在该领域的技术背景。首先思考问题的详细定义以及约束和标准；然后找出已知的能够解决该问题的技术，实现一些，评估这些技术的性能，最后做出一个选择。为了能够使这个步骤工作，非常重要的是要有实际数据以及合成的数据，它们用来验证正确性以及分析噪声敏感度，实际数据就是该系统会最终使用处理的典型数据。

szeliski在整个书中的结构如下：

多看CVPR, ECCV,ICCV, and SIGGRAPH等顶级会议的文章，很能了解当前形势以及对问题的新的解决方案。