Welcome to the final project of the camera course. By completing all the lessons, you now have a solid understanding of keypoint detectors, descriptors, and methods to match them between successive images. Also, you know how to detect objects in an image using the YOLO deep-learning framework. And finally, you know how to associate regions in a camera image with Lidar points in 3D space. Let's take a look at our program schematic to see what we already have accomplished and what's still missing.
In this final project, you will implement the missing parts in the schematic. To do this, you will complete four major tasks:
- First, you will develop a way to match 3D objects over time by using keypoint correspondences.
- Second, you will compute the TTC based on Lidar measurements.
- You will then proceed to do the same using the camera, which requires to first associate keypoint matches to regions of interest and then to compute the TTC based on those matches.
- And lastly, you will conduct various tests with the framework. Your goal is to identify the most suitable detector/descriptor combination for TTC estimation and also to search for problems that can lead to faulty measurements by the camera or Lidar sensor. In the last course of this Nanodegree, you will learn about the Kalman filter, which is a great way to combine the two independent TTC measurements into an improved version which is much more reliable than a single sensor alone can be. But before we think about such things, let us focus on your final project in the camera course.
- cmake >= 2.8
- All OSes: click here for installation instructions
- make >= 4.1 (Linux, Mac), 3.81 (Windows)
- Linux: make is installed by default on most Linux distros
- Mac: install Xcode command line tools to get make
- Windows: Click here for installation instructions
- Git LFS
- Weight files are handled using LFS
- OpenCV >= 4.1
- This must be compiled from source using the
-D OPENCV_ENABLE_NONFREE=ON
cmake flag for testing the SIFT and SURF detectors. - The OpenCV 4.1.0 source code can be found here
- This must be compiled from source using the
- gcc/g++ >= 5.4
- Linux: gcc / g++ is installed by default on most Linux distros
- Mac: same deal as make - install Xcode command line tools
- Windows: recommend using MinGW
- Clone this repo.
- Make a build directory in the top level project directory:
mkdir build && cd build
- Compile:
cmake .. && make
- Run it:
./3D_object_tracking
.
FP.1 Match 3D Objects Refer to line 226- 229 in FinalProject_Camera.cpp
FP.2 Compute Lidar-based TTC Refer to line 264- 267 in FinalProject_Camera.cpp
FP.3 Associate Keypoint Correspondences with Bounding Boxes Refer to line 271 in FinalProject_Camera.cpp
FP.4 Compute Camera-based TTC Refer to line 274-275 in FinalProject_Camera.cpp
The detail of functions listed above are in camFusion_Student.cpp.
FP.5 Performance Evaluation 1 Find examples where the TTC estimate of the Lidar sensor does not seem plausible. Describe your observations and provide a sound argumentation why you think this happened.
when both car and ego vehicle slow down and close to stationary, the TTC estimation does not seem plausible. It is mainly result from the calculation of relative velocity, which becomes noisy and sometime it could be negative. An alternative way could be adding a low pass filter for relative velocity when it lower than certain threshold.
FP.6 Performance Evaluation 2 Run several detector / descriptor combinations and look at the differences in TTC estimation. Find out which methods perform best and also include several examples where camera-based TTC estimation is way off. As with Lidar, describe your observations again and also look into potential reasons.
In this project, SIFT Detector and BRISK descriptor works relative faster than other, such as FREAK and Others. SIFT Dectector and SIFT descriptor get relative accurate estimation for TTC. Their camera-based TTC is calculated close to LiDAR-based TTC, comparing with other combination of detectors/descriptors.