Vehicle Position Estimation with Aerial Imagery from Unmanned Aerial Vehicles

  title={Vehicle Position Estimation with Aerial Imagery from Unmanned Aerial Vehicles},
  author={Friedrich Kruber and Eduardo S'anchez Morales and Samarjit Chakraborty and Michael Botsch},
  journal={2020 IEEE Intelligent Vehicles Symposium (IV)},
The availability of real-world data is a key element for novel developments in the fields of automotive and traffic research. Aerial imagery has the major advantage of recording multiple objects simultaneously and overcomes limitations such as occlusions. However, there are only few data sets available. This work describes a process to estimate a precise vehicle position from aerial imagery. A robust object detection is crucial for reliable results, hence the state-of-the-art deep neural… 

Figures and Tables from this paper

A novel vehicle tracking and speed estimation with varying UAV altitude and video resolution

Simulation results and comparative studies with the state-of-the-art methods demonstrate superior performance of the proposed approach for vehicle tracking and speed estimation.

Comparison of Camera-Equipped Drones and Infrastructure Sensors for Creating Trajectory Datasets of Road Users

This work compares measurements of a drone-based system with a prototypical camera-based infrastructure sensor system and investigates the detection quality of both systems using a reference vehicle equipped with an inertial navigation system.

Micro- and Macroscopic Road Traffic Analysis using Drone Image Data

Methods to ex-ploit the remarkable opportunities of drone based image processing for joint macro- and microscopic traffic analysis for road traffic analysis are presented.

SIND: A Drone Dataset at Signalized Intersection in China

  • Yan XuWenbo Shao Hong Wang
  • Computer Science
    2022 IEEE 25th International Conference on Intelligent Transportation Systems (ITSC)
  • 2022
A pipeline is designed to construct a Signalized INtersection Dataset (SIND), which contains 7 hours of recording including over 13,000 TPs with 7 types and it is believed that SIND would be an effective supplement to existing datasets and can promote related research on autonomous driving.

Open-Set Recognition based on the Combination of Deep Learning and Ensemble Method for Detecting Unknown Traffic Scenarios

This work proposes a combination of Convolutional Neural Networks and Random Forest for open set recognition of traffic scenarios by exploring the vote patterns of trees in RF instead of just majority voting and inheriting the ensemble nature of RF.

Introduction to the Special Issue on Embedded Systems for Computer Vision

We provide a broad overview of some of the current research directions at the intersection of embedded systems and computer vision, in addition to intro-ducing the papers appearing in this special

A Review of Testing Object-Based Environment Perception for Safe Automated Driving

It is found that the realization of safety-oriented perception testing remains an open issue since challenges concerning the three testing axes and their interdependencies currently do not appear to be sufficiently solved.



Accuracy Characterization of the Vehicle State Estimation from Aerial Imagery

This work presents ways to minimize the errors of the most relevant sources and with these error reductions, camera-equipped UAVs are very attractive tools for traffic data acquisition.

R3-Net: A Deep Network for Multioriented Vehicle Detection in Aerial Images and Videos

A novel deep network, called a rotatable region-based residual network (R3-Net), to detect multioriented vehicles in aerial images and videos and its potential for vehicle tracking in aerial videos is proposed.

DroNet: Efficient convolutional neural network detector for real-time UAV applications

The paper presents a holistic approach for designing such systems; the data collection and training stages, the CNN architecture, and the optimizations necessary to efficiently map such a CNN on a lightweight embedded processing platform suitable for deployment on UAVs.

Vision meets robotics: The KITTI dataset

A novel dataset captured from a VW station wagon for use in mobile robotics and autonomous driving research, using a variety of sensor modalities such as high-resolution color and grayscale stereo cameras and a high-precision GPS/IMU inertial navigation system.

The highD Dataset: A Drone Dataset of Naturalistic Vehicle Trajectories on German Highways for Validation of Highly Automated Driving Systems

This work proposes a novel method to measure data from an aerial perspective for scenario-based validation fulfilling the mentioned requirements, and provides a large-scale naturalistic vehicle trajectory dataset from German highways called highD.

Vehicle Instance Segmentation From Aerial Image and Video Using a Multitask Learning Residual Fully Convolutional Network

A novel, more challenging problem of vehicle instance segmentation, which entails identifying, at a pixel level, where the vehicles appear as well as associating each pixel with a physical instance of a vehicle, is tackled with a semantic boundary-aware multitask learning network.

MLESAC: A New Robust Estimator with Application to Estimating Image Geometry

A new robust estimator MLESAC is presented which is a generalization of the RANSAC estimator which adopts the same sampling strategy as RANSac to generate putative solutions, but chooses the solution that maximizes the likelihood rather than just the number of inliers.

Parallel Multi-Hypothesis Algorithm for Criticality Estimation in Traffic and Collision Avoidance

A fully model-based algorithm that can evaluate the criticality of complex, multi-modal (vehicles and pedestrians) traffic scenarios by simulating millions of trajectory combinations and detecting collisions between objects is presented.

Machine Learning Architectures for the Estimation of Predicted Occupancy Grids in Road Traffic

A novel machine learning architecture for an efficient estimation of the probabilistic space-time representation of complex traffic scenarios, which includes uncertainties regarding the behaviour of the traffic participants and is termed as the Predicted Occupancy Grid (POG).