Model based vehicle detection and tracking for autonomous urban driving

By Anna Petrovskaya, Sebastian Thrun. 2009

461 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Automotive Engineering, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Automotive Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

A Survey of Autonomous Driving: Common Practices and Emerging Technologies (2019, background): “rameters such as the size of the object are tracked alongside dynamics [188].”
Artificial intelligence applications in the development of autonomous vehicles: a survey (2020, methodology): “[12] proposed adaptive randomized Hough transform algorithm (ARHT) to detect lanes and proved its validity compared with genetic algorithm based lane detection for AVs.”
Laser-based segment classification using a mixture of bag-of-words (2013, background): “Petrovskaya and Thrun [11] and also Himmelsbach et al.”
Tracking the Untrackable: Learning to Track Multiple Cues with Long-Term Dependencies (2017, background): “It covers a wide range of applications such as sports analysis [40, 47, 70], biology (birds [41], ants [27], ﬁshes [62, 63, 14], cells [42, 36]), robot navigation [11, 12], and autonomous driving vehicles [13, 53].”
Multi-scale object candidates for generic object tracking in street scenes (2016, methodology): “For automotive scenarios several approaches address this problem using highly precise LIDAR data as input [10], [8], [11], [12].”
Deep Tracking on the Move: Learning to Track the World from a Moving Vehicle using Recurrent Neural Networks (2016, background): “Many tracking systems employ multiple hand-engineered stages (e.g. object detection, semantic classiﬁcation, data association, state estimation and motion modelling, occupancy grid generation) in order to represent the state and evolution of the world ([3], [4], [5]).”
Stereo-Camera-Based Urban Environment Perception Using Occupancy Grid and Object Tracking (2012, methodology): “In [6], [12], and [13], there are more detailed descriptions of how measurements from stereo cameras and laser scanners can be processed to find objects.”
Lidar for Autonomous Driving: The Principles, Challenges, and Trends for Automotive Lidar and Perception Systems (2020, methodology): “The authors in [21] followed this method while utilizing a grid-based local plane-fitting approach instead of processing every point, as was done in [4].”
Precise and efficient model-based vehicle tracking method using Rao-Blackwellized and scaling series particle filters (2016, methodology): “Some LiDAR-based DATMO approaches have been developed over the past decade [16], [17], [18], [19], [6], [7], [20].”
Self-Driving Cars: A Survey (2019, background): “Petrovskaya and Thrun [PET09] was revised by He et al.”
Deep tracking in the wild: End-to-end tracking using recurrent neural networks (2018, methodology): “Commonly, tracking systems achieve this by employing multiple hand-engineered stages, such as object detection, semantic classification, data association, state estimation, motion modeling, and occupancy grid generation (Petrovskaya and Thrun, 2009; Vu et al., 2007; Wang et al., 2015).”
Towards 3D object recognition via classification of arbitrary object tracks (2011, methodology): “in [9], [10], [11], [12], [13], but these methods require the explicit specification of new tracker models for each additional object class.”