Object tracking for Autonomous Vehicles Using Lidar Data

Background of thesis project

Volvo Construction Equipment (VCE) is one of the world's largest manufacturers of construction equipment. With enhancing the artificial intelligent area and learning-based approaches, there is a big trend for shifting towards autonomous vehicles, which can localize themselves in the environment, perceive and plan. In the construction domain, object detection is an essential mean to enable autonomous driving where machines can detect and locate obstacles, human in the environment, and other moving vehicles in the surrounding. To maintain a leading position, it is essential for Volvo to develop innovative and cost-efficient, and high-performance solutions for object classification.
Object tracking is one of the most critical components in the autonomous driving pipeline. The goal of object tracking is to estimate the states of an object in subsequent frames. There are a lot of researches for object tracking in RGB image sequences[1, 2]. Although, point-cloud information captured by Lidar sensors has a better performance in order to present more accurate estimation about objects' distances and movement characteristics. [3] proposed a novel method for object tracking in point-cloud data, which represented objects by their center point to eliminate non-important features like object size and aspect ratio.

Description of thesis work

This master thesis is suitable for one student completing his/her studies in software engineer or computer science. This thesis is in collaboration with MDU and Volvo Construction Equipment. Desired start date is Jan 2022.
This project aims to develop a reliable 3D object tracking framework for VOLVO construction vehicles using novel 3D data representation methods. The original dataset will be provided by VCE containing point cloud video frames obtained in a real environment. To achieve maximum accuracy, we intended to use point cloud data obtained in a simulated environment. The student is preferably knowledgeable in deep learning, and Python is meriting. The main activities are:
  1. Review related studies on using object tracking techniques.
  2. Prepare dataset (labeling, normalization, etc.) from raw LiDAR point cloud data provided by VOLVO.
  3. Implement state-of-the-art 3D object tracking model; then, train the model with the augmented data samples.
  4. Evaluate the efficiency and accuracy of the object tracking model on a GPU device.
  5. Discuss the effect of novel 3D data representation methods on the efficiency and accuracy of the object tracking

A full report of the work carried out will be prepared and presented to staff at Volvo CE. It will be required for the student to perform the thesis at Volvo CE facilities in Eskilstuna.

Reference
  1. Kristan, M., et al. The visual object tracking vot2015 challenge results. in Proceedings of the IEEE international conference on computer vision workshops. 2015.
  2. Bertinetto, L., et al. Fully-convolutional siamese networks for object tracking. in European conference on computer vision. 2016. Springer.
  3. Yin, T., X. Zhou, and P. Krahenbuhl. Center-based 3d object detection and tracking. in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2021.
Thesis Level: Master

Language: English

Starting date: Jan. 2022

Number of students: 1

Tutor
Volvo Construction Equipment: Sara Afshar, Research Engineer, 0165415707
Mälardalen University: Masoud Daneshtalab, Professor in electronics, 0736620918

The Volvo Group drives prosperity through transport solutions, offering trucks, buses, construction equipment, power solutions for marine and industrial applications, financing and services that increase our customers’ uptime and productivity. Founded in 1927, the Volvo Group is committed to shaping the future landscape of sustainable transport and infrastructure solutions. Countless career opportunities are offered across the group’s leading brands and entities that share a culture of Trust, Passion, High Performance, Change and Customer Success. 
www.volvogroup.com/career. 

Volvo Construction Equipment is a global company driven by passion, curiosity and by our purpose: to build the world we want to live in. We believe that only through imagination and teamwork can we develop a world that is cleaner, smarter and more connected. Our company culture reflects this belief through the care and trust it places in our customers, employees and suppliers. People are at the heart of our business. It is through our strong network of talented, enquiring and innovative minds that we have been able to pave the way towards a more sustainable future. The global construction industry is our arena and our employees are our greatest assets.

We can only continue to stand out as industry leaders through the people driving us forwards. Come be a part of our team and help us build tomorrow.

欢迎加入我们

申请流程

申请

您提交申请之后,即会收到一封确认邮件。点击确认之后,您仍然可以更新您的个人资料。

Testimonials

类似职位

Verification Engineer 技术 Eskilstuna, 瑞典 发布日期: 
System engineer Thermal management 技术 Eskilstuna, 瑞典 发布日期: 
Agile Program Manager - UX and HMI 技术 Eskilstuna, 瑞典 发布日期: