October 2014
Intermediate to advanced
336 pages
14h 42m
English
Content preview from Architectures for Computer Vision: From Algorithm to Chip with Verilog
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.
9 Dynamic Programming for Energy Minimization
As is the case with the relaxation algorithm and the BP algorithm, dynamic programming (DP) (Bellman 1954) is an important algorithm that can solve, under general settings, many problems in energy functions (Amini et al. 1990; Felzenszwalb and Zabih 2011). Dynamic programming is extremely fast and uses less memory space than other algorithms, but unfortunately, DP can only solve one-dimensional problems, such as line-by-line processing, until it finds local optimal solutions. Given that DP can only solve one-dimensional problems, this type of algorithm is especially useful for stereo matching, where the search space is limited to the epipolar line (Gong and Yang 2005; Jeong and Yuns 2000; Ohta and Kanade 1985). DP is also an important construct of the hidden Markov model (HMM), where hidden states must be recovered in decoding problems.
In this chapter, we study DP as a method for solving energy minimization problems. In addition to standard DP, we study various forms of DP: parallel DP, serial DP, and extended DP (EDP). Parallel and serial DPs are designed for extracting multiple best solutions in parallel and in series, respectively. The extended DP is tailored to solve multiple image lines by introducing the product space. We also study HMM and the inside-outside algorithm, which can be used in higher-level processing, such as image interpretation or image understanding.
In this chapter, we will examine the computation structures ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access
More than 5,000 organizations count on O’Reilly
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.Julian F.
I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.Addison B.
I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.Amir M.
I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.