Added README.md

diff --git a/README.txt b/README.md
similarity index 85%
rename from README.txt
rename to README.md
index 18266af..b1ac38d 100644 (file)
--- a/README.txt
+++ b/README.md
@@ -1,17 +1,13 @@
-
-                       Multi-Tracked Paths (MTP)
-                       -------------------------
-
-* INTRODUCTION
+# Introduction
 
 This is a very simple implementation of a variant of the k-shortest
 paths algorithm (KSP) applied to multi-target tracking, as described
 in
 
-  J. Berclaz, E. Turetken, F. Fleuret, and P. Fua. Multiple Object
-  Tracking using K-Shortest Paths Optimization. IEEE Transactions on
-  Pattern Analysis and Machine Intelligence (TPAMI), 33(9):1806-1819,
-  2011.
+ > J. Berclaz, E. Turetken, F. Fleuret, and P. Fua. Multiple Object
+ > Tracking using K-Shortest Paths Optimization. IEEE Transactions on
+ > Pattern Analysis and Machine Intelligence (TPAMI),
+ > 33(9):1806--1819, 2011.
 
 This implementation is not the reference implementation used for the
 experiments presented in this article. It does not require any
@@ -31,13 +27,15 @@ This software package provides two commands:
    for the mtp command. If you pass it the "stress" argument, it
    generates a larger and noisier problem.
 
-* INSTALLATION
+# Installation
 
 This software should compile with any C++ compiler. Under a unix-like
 environment, just execute
 
-  make
-  ./mtp_example
+```
+make
+./mtp_example
+```
 
 It will create a synthetic dummy example, save its description in
 tracker.dat, and print the optimal detected trajectories.
@@ -55,7 +53,7 @@ pdf from the latter with the dot command:
 
   dot < graph.dot -T pdf -o graph.pdf
 
-* IMPLEMENTATION
+# Implementation
 
 The two main classes are MTPGraph and MTPTracker.
 
@@ -72,9 +70,9 @@ computation is iterative.
 
 The MTPTracker takes as input
 
- (1) a number of locations and a number of time steps
+1. a number of locations and a number of time steps
 
- (2) a spatial topology composed of
+2. a spatial topology composed of
 
      - the allowed motions between locations (a Boolean flag for each
        pair of locations from/to)
@@ -83,14 +81,14 @@ The MTPTracker takes as input
 
      - the exits (a Boolean flag for each location and time step)
 
- (3) a detection score for every location and time, which stands for
+3. a detection score for every location and time, which stands for
 
              log( P(Y(l,t) = 1 | X) / P(Y(l,t) = 0 | X) )
 
-     where Y is the occupancy of location l at time t and X is the
-     available observation. In particular, this score is negative on
-     locations where the probability that the location is occupied is
-     close to 0, and positive when it is close to 1.
+   where Y is the occupancy of location l at time t and X is the
+   available observation. In particular, this score is negative on
+   locations where the probability that the location is occupied is
+   close to 0, and positive when it is close to 1.
 
 From this parameters, the MTPTracker can compute the best set of
 disjoint trajectories consistent with the defined topology, which
@@ -116,6 +114,7 @@ running the tracking.
 The tracker data file for MTPTracker::read has the following format,
 where L is the number of locations and T is the number of time steps:
 
+```
 ---------------------------- snip snip -------------------------------
   int:L int:T
 
@@ -135,15 +134,14 @@ where L is the number of locations and T is the number of time steps:
   ...
   float:detection_score_T_1 ... float:detection_score_T_L
 ---------------------------- snip snip -------------------------------
+```
 
 The method MTPTracker::write_trajectories writes first the number of
 trajectories, followed by one line per trajectory with the following
 structure
 
+```
 ---------------------------- snip snip -------------------------------
   int:traj_number int:entrance_time int:duration float:score int:location_1 ... int:location_duration
 ---------------------------- snip snip -------------------------------
-
---
-François Fleuret
-April 2013
+```