Context-Based Pedestrian Path Prediction

By Julian F. P. Kooij, Nicolas Schneider, Fabian B. Flohr, Dariu M. Gavrila. European Conference on Computer Vision, 2014

298 citations recorded by the source corpus.

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

View Paper: https://www.semanticscholar.org/paper/bee652729e9ee7f4296da77ecf7470dda9d510fc

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

Toward Driving Scene Understanding: A Dataset for Learning Driver Behavior and Causal Reasoning (2018, background): “, [18] proposed a dataset that annotates a pedestrian with the intention to cross the street under different scenarios.”
Peeking Into the Future: Predicting Future Person Activities and Locations in Videos (2019, methodology): “in [14] looked at pedestrian’s faces to model their awareness to predict whether they will cross the road using a Dynamic Bayesian Network in dash-cam videos.”
Future Person Localization in First-Person Videos (2017, methodology): “Several methods have made use of Bayesian approaches [18, 36], recurrent neural networks [1, 19], fully-convolutional networks [12, 43], and other social or contextual features [32, 41] for predicting human trajectories from images or videos.”
Agreeing to cross: How drivers and pedestrians communicate (2017, background): “In more recent works, the pedestrian’s body language is used as a means of predicting behavior [25], [26].”
Anticipating the future by watching unlabeled video (2015, background): “[18] also predict the possible future path for people in the scene.”
DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agents (2017, background): “In [24], a dynamic Bayesian network to capture situational awareness is proposed as a context cue for pedestrian path prediction, but the model is limited to orientations and distances of pedestrians to vehicles and the curbside.”
Social Ways: Learning Multi-Modal Distributions of Pedestrian Trajectories With GANs (2019, background): “the smallest distance two agents would reach in the future if both maintain their current velocity) [8].”
Anticipating Visual Representations from Unlabeled Video (2015, background): “Lezema et al. [23], Gong et al. [8] and Kooij et al. [17] also predict the possible future path for people in the scene.”
Who Let the Dogs Out? Modeling Dog Behavior from Visual Data (2018, background): “[15] predict the future paths of pedestrians from a vehicle camera.”
What will Happen Next? Forecasting Player Moves in Sports Videos (2017, background): “Predicting pedestrian trajectories [15, 17, 13, 14, 29] and anticipating future human activities [14, 16, 35, 45, 19, 10] has seen considerable interest over the past few years.”
External Human-Machine Interfaces on Automated Vehicles: Effects on Pedestrian Crossing Decisions (2019, background): “Also, the idea that AVs should stop for pedestrians standing at the edge of the roadway is debatable, as it may be a hard problem for AVs to determine the intent of the pedestrian (Kooij et al., 2014; Vinkhuyzen & Cefkin, 2016).”
Social LSTM: Human Trajectory Prediction in Crowded Spaces (2016, methodology): “Scene semantics has also been used to predict multiple object dynamics [17, 36, 34, 28].”
Human motion trajectory prediction: a survey (2019, methodology): “Furthermore, several approaches use the Predicted Probability metric, ( ' ∑T t=1 q(st|θ) ) or its negative logarithm, to calculate the probability of the ground truth path (i.e s1:T ) on the predicted states distribution (Kooij et al. 2014, 2018; Rehder and Klöden 2015; Rudenko et al. 2018a,b).”
Human Action Recognition and Prediction: A Survey (2018, methodology): “Compared to previous work [180], [181], [184], [187], [188], the method in [195] is end-to-end trainable, and generalizes well in complex scenes.”
PIE: A Large-Scale Dataset and Models for Pedestrian Intention Estimation and Trajectory Prediction (2019, background): “Trajectory-based algorithms rely on observation of pedestrians’ past motion history and predict the location of the pedestrians in the future using contextual information such as 3D depth [14, 34, 39], social interactions [25, 42, 1, 31, 41], the ego-vehicle dynamics and the scene structure [16, 17,”
KrishnaCam: Using a longitudinal, single-person, egocentric dataset for scene understanding tasks (2016, background): “The two peaks of the graph (steep rises in the amount of novel visual data) correspond to days the student spent outside his home city.”
Autonomous Vehicles That Interact With Pedestrians: A Survey of Theory and Practice (2018, background): “For instance, Daimler-Path [154] and Daimler-Intent [140] contain pedestrian head orientation information.”
Are They Going to Cross? A Benchmark Dataset and Baseline for Pedestrian Crosswalk Behavior (2017, background): “More recently researchers also looked at other behavioral cues such as pedestrian head orientation to measure the level of awareness at the point of crossing [21, 35].”