Order from us for quality, customized work in due time of your choice.
Assignment Brief
The Scenario
Picture yourself as an engineer at a trailblazin
Assignment Brief
The Scenario
Picture yourself as an engineer at a trailblazing tech company that will revolutionise urban mobility with a combined autonomous taxi and delivery service. Your goal is to provide a seamless, safe, and efficient way for people and goods to get from point A to point B in urban environments. The key to making this possible? An impeccable navigation system.
A key component of this navigation system is robust and safe visual odometry.
In order to decide which visual odometry approach to choose for the autonomous vehicle, you are tasked with implementing a visual odometry pipeline, and testing and analysing its performance.
Assumptions
When solving the task, you can make the following assumptions:
The autonomous vehicle is equipped with a front-facing stereo camera with known calibration parameters, as in the KITTI dataset.
Your Tasks
This assignment consists of three Tasks. We summarise them below, followed by more comprehensive description further down.
Implement a full visual odometry pipeline, using a feature-based approach of your choice.
Experimentally evaluate and discuss the performance of your implemented system on the KITTI dataset (more about KITTI below).
Add an experiment of your choice, for example:Compare your performance with another algorithm from a publicly available VO system (it is ok to simply download from github or install via pip, you do not have to reimplement this 3rd party method yourself).
Combine your VO with place recognition or localisation to obtain a full visual SLAM system.
Conduct a detailed ablation study of your chosen algorithm, i.e. systematically vary a meaningful selection of parameters and discuss the observed influence on the performance.
If you have other ideas, talk to your lecturer.
Task 1 Description – Implementation
Implement a full visual odometry pipeline, using a feature-based approach of your choice.
In your report, clearly describe the approach you implemented, including the underlying algorithmic and mathematical concepts.
In your report, discuss the differences of your method compared to relevant other approaches. Explain the advantages and disadvantages of your chosen method, compared to the other methods, in the context of an urban autonomous driving scenario.
Clearly state the weaknesses you expect from your chosen method, e.g. the failure cases you expect in certain conditions.
Remarks:
Since you have access to a calibrated stereo camera, you can choose between very different VO approaches, based on different types of correspondences: 2D-2D, 2D-3D, and 3D-3D.
You will not be marked for the choice of method, but for the discussion of advantages and disadvantages.
You can use all existing functions of OpenCV or other libraries and do not have to reimplement everything from scratch. You should however clearly describe what algorithm is used by the functions you call. For example, if you use OpenCVs PnP solver, you should explain the PnP problem in your descriptions (see point 2 above).
Task 2 Description – Evaluation
Experimentally evaluate the performance of your implemented system on the KITTI dataset by comparing against the ground truth pose information.Choose meaningful test sequences from the KITTI dataset and meaningful evaluation metrics.
In your report, clearly explain your experimental setup and evaluation protocol. This should contain the following points:Explain which sequences from the KITTI dataset you chose and why.
Discuss the metrics you used and why you chose them.
Discuss the obtained results of your evaluation, including the following:Clearly present the performance of your algorithm and interpret the results.
Discuss failure cases, and the relative strengths and weaknesses of your algorithm.
Discuss if your experimental findings were aligned with the strengths and weaknesses you expected and discussed as part of Task 1.
Remarks:
You will not be marked on the performance of your algorithm, but on the provided discussion.
Task 3 Description – An Experiment of Your Choice
We give you the freedom to choose an interesting experiment you want to add to your report. We list three ideas to choose from below. If you want to do something not listed here, talk to us first.
In your report, clearly describe the conducted experiment, including used datset, evaluation protocol and metrics. Provide a motivation for your choice of experiment. Present the results and draw meaningful conclusions.
Ideas to choose from:
Compare your performance with another algorithm from a publicly available VO system.It is ok to download from github or install via pip, you do not have to reimplement this 3rd party method yourself.
Combine your visual odometry with place recognition or localization to obtain a full visual SLAM system.
Conduct a detailed ablation study of your chosen algorithm, i.e. systematically vary a meaningful selection of parameters and discuss the observed influence on the performance.
Expectations for the Report
Length of Report
Your report must not exceed 6 pages, excluding references.
Your report can contain an appendix with additional qualitative results (e.g. illustrations) and additional supplementary material (e.g. experiments and results of secondary importance). The appendix must not exceed 10 pages.
The report must be self-contained in the sense that the marker will not have to take the content of the optional appendix into account when marking.
Expected Format
Your report must follow professional standards in all of its content, including text and illustrations.
Your report should be in a two-column format commonly seen in academic papers.
You can use a text processor of your choice, Word.
Your report must contain the following sections:Abstract – follow academic writing standards and provide an abstract that summarises your report and the gained insights.
Introduction – write a short introduction (two paragraphs are fine) that introduce what your report is about
Method – see description of Task 1 for the expected content. Make sure to use meaningful subsections to structure this section.
Evaluation – see description of Task 2 for the expected content. Make sure to use meaningful subsections to structure this section.
Task 3 – see description of Task 3 for the expected content. Make sure to use meaningful subsections to structure this section.
Conclusions – provide a short (one paragraph) summary of the report.
References – the properly formatted list of referenced literature.
The KITTI Dataset
For this assessment, you will work with selected sequences of the KITTI datasetLinks an external site.. This is a famous and widely used dataset in computer vision and robotics. It contains sensor recordings from two stereo cameras (grey and RGB), a number of Velodyne laser scanners, and a highly accurate GPS/IMU sensor.
Selected Sequences
We recommend you select various sequences of the KITTI dataset for your project. You do not have to use all of them, but your analysis will. be more meaningful if you have sequences that cover different driving scenarios. Think about the commonly encountered scenarios in autonomous driving and what you would want to test.
Instructions:
Use the notebook from the Week 1 Prac as a starting point. Replace or add the download links for the dataset sequences you want to download in the curl command.
Notice how these two commands download the image data (first command) and the calibration data (second command) for the 2011_09_26_drive_0035 sequence:
!cd ../kitti && curl -O https://s3.eu-central-1.amazonaws.com/avg-kitti/ra…
!cd ../kitti && curl -O https://s3.eu-central-1.amazonaws.com/avg-kitti/ra…
You always need to download both the image data ([synced+rectified data] in the table below) and the calibration data.
More sequences can be obtained via the dataset websiteLinks to an external site.. This might require you to create a (free) account to get access.
Order from us for quality, customized work in due time of your choice.