Object Detection and Tracking for Autonomous Navigation in Dynamic Environments

@article{Ess2010ObjectDA,
  title={Object Detection and Tracking for Autonomous Navigation in Dynamic Environments},
  author={Andreas Ess and Konrad Schindler and B. Leibe and Luc Van Gool},
  journal={The International Journal of Robotics Research},
  year={2010},
  volume={29},
  pages={1707 - 1725}
}
We address the problem of vision-based navigation in busy inner-city locations, using a stereo rig mounted on a mobile platform. In this scenario semantic information becomes important: rather than modeling moving objects as arbitrary obstacles, they should be categorized and tracked in order to predict their future behavior. To this end, we combine classical geometric world mapping with object category detection and tracking. Object-category-specific detectors serve to find instances of the… 

Robust moving object tracking and trajectory prediction for visual navigation in dynamic environments

TLDR
A robust and efficient moving object detection system with trajectory prediction mechanism for mobile visual applications in dynamic environments that addresses problems of camera shake and image blurs caused by mobile camera and fast moving objects, respectively.

Object tracking and state estimation in outdoor scenes based on 3D laser scanner

TLDR
A 2D Gaussian process algorithm based on local samples is presented here for obstacle area detection and ego-motion of autonomous vehicle does not need to be estimated before tracking but after tracking.

Vision based in-motion detection of dynamic obstacles for autonomous robot navigation

TLDR
This paper proposes a method for in-motion detection in dynamic environment that is computationally simpler in comparison with the motion recovery achieved from the optical flow based methods and robust to low level intensity variations and shadow effects.

Vehicle Tracking by Simultaneous Detection and Viewpoint Estimation

TLDR
The experimental validation confirms that the integration of an EKF with both detections and viewpoint estimations results beneficial, and the approach is evaluated on a novel and challenging dataset with different video sequences recorded at urban environments.

Generative object detection and tracking in 3D range data

TLDR
This paper presents a novel approach to tracking dynamic objects in 3D range data which allows the tracker to robustly extract objects of varying sizes and shapes from the observations and yields results which are comparable to state-of-the-art discriminative methods.

Sparse scene flow segmentation for moving object detection in urban environments

TLDR
This paper presents an approach for object detection utilizing sparse scene flow, which does not rely on object classes and allows for a robust detection of dynamic objects in traffic scenes.

Boosting Multi-Vehicle Tracking with a Joint Object Detection and Viewpoint Estimation Sensor

TLDR
It is shown that enhancing the tracking with observations of the vehicle pose, results in a better estimation of the vehicles trajectories, and the simultaneous integration of vehicle localizations and pose estimations as observations in an EKF, improves the tracking results.

Interlacing Self-Localization, Moving Object Tracking and Mapping for 3D Range Sensors

TLDR
A solution for autonomous vehicles to detect arbitrary moving traffic participants and to precisely determine the motion of the vehicle is presented, based on three-dimensional images captured with modern range sensors like e.g. high-resolution laser scanners.

Towards a Tracking Algorithm based on the Clustering of Spatio-temporal Clouds of Points

TLDR
A new method designed to work directly in 3D space and time is presented, creating (3D+1) clouds of points representing the full spatio-temporal evolution of the moving targets, which can be used to solve optical occlusions and lowering from NP to P the complexity of the problem.

Figure-Ground Segmentation - Object-Based

  • B. Leibe
  • Computer Science
    Visual Analysis of Humans
  • 2011
TLDR
This chapter will present fundamental techniques and current state-of-the-art approaches for performing object detection, for obtaining detailed object segmentations from single images based on top–down and bottom–up cues, and for propagating this information over time.
...

References

SHOWING 1-10 OF 70 REFERENCES

Moving obstacle detection in highly dynamic scenes

TLDR
The results show that the proposed integration makes stable tracking and motion prediction possible, and thereby enables path planning in complex and highly dynamic scenes.

Improved Multi-Person Tracking with Active Occlusion Handling

TLDR
This paper analyzes the influence of the trajectory generator, which forms part of any tracking-by-detection system, and proposes a set of measures to improve its performance, and shows that the proposed extensions significantly improve overall system performance.

Coupled Object Detection and Tracking from Static Cameras and Moving Vehicles

We present a novel approach for multi-object tracking which considers object detection and spacetime trajectory estimation as a coupled optimization problem. Our approach is formulated in a minimum

Coupled Detection and Trajectory Estimation for Multi-Object Tracking

We present a novel approach for multi-object tracking which considers object detection and spacetime trajectory estimation as a coupled optimization problem. It is formulated in a hypothesis

Dynamic 3D Scene Analysis from a Moving Vehicle

TLDR
A system that integrates fully automatic scene geometry estimation, 2D object detection, 3D localization, trajectory estimation, and tracking for dynamic scene interpretation from a moving vehicle and demonstrates the performance of this integrated system on challenging real-world data showing car passages through crowded city areas.

A Fast Stereo-based System for Detecting and Tracking Pedestrians from a Moving Vehicle

TLDR
A fully integrated system for detecting, localizing, and tracking pedestrians from a moving vehicle that can reliably detect upright pedestrians to a range of 40 m in lightly cluttered urban environments and on a diverse set of datasets with groundtruth in outdoor environments with varying degrees of pedestrian density and clutter.

Robust Multiperson Tracking from a Mobile Platform

TLDR
This paper addresses the problem of multiperson tracking in busy pedestrian zones using a stereo rig mounted on a mobile platform with a two-stage procedure, which jointly estimates camera position, stereo depth, object detection, and tracking.

Real-time multiple vehicle detection and tracking from a moving vehicle

TLDR
Experimental results demonstrate robust, real-time car detection and tracking over thousands of image frames.

Tracking multiple moving targets with a mobile robot using particle filters and statistical data association

TLDR
A sample-based variant of joint probabilistic data association filters is introduced to track features originating from individual objects and to solve the correspondence problem between the detected features and the filters.

A unified framework for tracking through occlusions and across sensor gaps

TLDR
This work presents a novel, modular framework that handles each of these problems in a unified manner by the initialization, tracking, and linking of high-confidence tracklets in a track/suspend/match paradigm.
...