modify readme

README.md

@@ -1,3 +1,2 @@
 ## Introduction
-
-To solve the problem of sensor calibration for autonomous vehicles, we provide a sensors calibration toolbox. The calibration toolbox can be used to calibrate sensors such as  IMU, GPS, Lidar, Camera, and Radar.
+Sensor calibration is the foundation block of any autonomous system and its constituent sensors and must be performed correctly before sensor fusion may be implemented. Precise calibrations are vital for further processing steps, such as sensor fusion and implementation of algorithms for obstacle detection, localization and mapping, and control. Further, sensor fusion is one of the essential tasks in AD applications that fuses information obtained from multiple sensors to reduce the uncertainties compared to when sensors are used individually. To solve the problem of sensor calibration for autonomous vehicles, we provide a sensors calibration toolbox. The calibration toolbox can be used to calibrate sensors such as  IMU, Lidar, Camera, and Radar.

camera_intrinsic/README.md

@@ -0,0 +1,37 @@
+## Introduction
+
+This is a project for intrinsic calibration and evalution.
+
+It mainly includes two part: intrinsic calibration, distortion measurement. 
+
+## Dependecies
+
+- opencv 2.4
+- eigen 3
+
+## Compile
+Compile in their respective folders
+
+```shell
+# mkdir build
+mkdir -p build && cd build
+# build
+cmake .. && make
+```
+
+## Input data
+- <calibration_image_dir>: contains only seleted chessboard calibration image
+- <distortion_image_path>: distortion harp image
+
+## How to run
+run command:
+```shell
+# run intrinsic calibration
+./bin/run_intrinsic_calibration <calibration_image_dir>
+# run distortion measurement
+./bin/run_distortion_measure <distortion_image_path>
+```
+
+- **Intrinsic Calibration:** Program will automatically run intrinsic calibration. Corner-detect result will be displayed. All input calibration images will be undistorted and save to `<calibration_image_dir>/undistort/` dir.
+
+- **Distortion Evaluation:** Sampled points of original and undistorted images will be displayed. Undistorted distortion_image will be save to `<output_dir>`.

lidar2camera/auto_calib/README.md

@@ -1,4 +1,4 @@
-## Introduction
+# Introduction
 
 This automatic and user-friendly calibration tool is for calibrating the extrinsic parameter of LiDAR and camera in road scenes. Line  features  from  static  straight-line-shaped  objects  such  as  road lanes, lights, and telegraphy poles are extracted for both image and LiDAR point cloud, later on, calibration will be achieved by aligning those two kind of features. 
 
@@ -8,7 +8,7 @@ This automatic and user-friendly calibration tool is for calibrating the extrins
 
 <img src="./data/mask.jpg" width="100%" height="100%" alt="Line Feature for Image" div align=center /><br>
 
-## Prerequisites
+# Prerequisites
 
 **C++ libraries for main calibration project **
 
@@ -24,7 +24,7 @@ This automatic and user-friendly calibration tool is for calibrating the extrins
 * tensorflow 1.15 (with CUDA 10.0 cudnn 7.6) `pip3 install tensorflow-gpu=1.15`
 * [pydensecrf](https://github.com/lucasb-eyer/pydensecrf)  `pip3 install git+https://github.com/lucasb-eyer/pydensecrf.git`
 
-## Usage
+# Usage
 
 1. Five Input files: 
 

lidar2camera/auto_calib/tool/README.md

@@ -1,7 +1,7 @@
-## Introduction
+# Introduction
 This project is used to extract features of lane lines and pillars in the picture.
 
-## Requirements
+# Requirements
 It is recommended to use the conda environment, created by the following command:
 ```
 conda env create -f lidar2camera.yaml
@@ -10,7 +10,7 @@ Pull the model by the following command: (pretrained network for semantic segmen
 ```
 wget http://download.tensorflow.org/models/deeplabv3_cityscapes_train_2018_02_06.tar.gz
 ```
-## Usage
+# Usage
 ```
 python merge_mask.py calib.png mask.png
 ```