3D Traffic Scene Understanding From Movable Platforms

By Andreas Geiger, Martin Lauer, Christian Wojek, Christoph Stiller, Raquel Urtasun. 2014

417 citations recorded by the source corpus.

Subfields: Automotive Engineering, Computer Vision and Pattern Recognition, Environmental Engineering

How researchers see this paper

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

In Automotive Engineering

In Computer Vision and Pattern Recognition

In Environmental Engineering

Citations in the corpus

The Cityscapes Dataset for Semantic Urban Scene Understanding (2016, background): “Consequently, significant research efforts have gone into new vision technologies for understanding complex traffic scenes and driving scenarios [4, 16–18, 58, 62].”
DeepDriving: Learning Affordance for Direct Perception in Autonomous Driving (2015, methodology): “To integrate different sources into a consistent world representation, [5, 22] proposed a probabilistic generative model that takes various detection results as inputs and outputs the layout of the intersection and traffic details.”
VirtualWorlds as Proxy for Multi-object Tracking Analysis (2016, methodology): “Thanks to the recent progress on object detection, association-based tracking-by-detection in monocular video streams is particularly successful and widely used for MOT [29, 30, 31, 32, 33, 34, 35, 36, 37, 38] (see [39] for a recent review).”
HDNET: Exploiting HD Maps for 3D Object Detection (2018, methodology): “In [23, 24], online estimated maps are used to reason the location of objects in 3D.”
Conditional Affordance Learning for Driving in Urban Environments (2018, positive): “This information can be aggregated into a model of the environment [16, 17] and a planning module generates an obstacle-free trajectory which is executed by the control module [18].”
MODNet: Motion and Appearance based Moving Object Detection Network for Autonomous Driving (2018, background): “There are two main paradigms in this area: (1) The mediated perception approach which semantically reasons the scene [7][28] and then determines the driving decision based on it.”
Discriminative Scale Space Tracking (2016, background): “Popular applications of generic tracking include robotics [11], surveillance [12] and road scene understanding [13].”
Near-Online Multi-target Tracking with Aggregated Local Flow Descriptor (2015, neutral): “18 % 2738 3240 TBD [15] [13] Batch 52.”
Simple online and realtime tracking (2016, methodology): “[20] uses the Hungarian algorithm [15] in a two stage process.”
Joint SFM and detection cues for monocular 3D localization in road scenes (2015, methodology): “Similarly, systems like [7] use a stereo setup to infer the layout of urban traffic junctions.”
Multiple Hypothesis Tracking Revisited (2015, neutral): “7 TBD [15] 15.”
The Cityscapes Dataset (2015, background): “, semantic [25] or holistic [7]) and in different application scenarios (e.”
End-to-End Learning of Driving Models with Surround-View Cameras and Route Planners (2018, background): “Excellent work [28] has been done to integrate such results.”
UA-DETRAC: A new benchmark and protocol for multi-object detection and tracking (2015, neutral): “, 2014), CMOT (Bae and Yoon, 2014), TBD (Geiger et al., 2014), MHT (Kim et al.”
Segment as Points for Efficient Online Multi-Object Tracking and Segmentation (2020, background): “The data association can be accomplished on either the 2D image plane [4,6,7,14,33,42,38] or the 3D world space [1,8,10,20,25,39].”