Trajectory analysis and prediction for improved pedestrian safety: Integrated framework and evaluations

Møgelmose, Andreas; Trivedi, Mohan M.; Moeslund, Thomas B.

doi:10.1109/ivs.2015.7225707

Cited by 58 publications

(32 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is also mentioned in [181] that high-level features, such as skeleton joints, can provide more information than low-levels, such as HOG and Histogram of Optical Flow (HOF) [218]. The overall design used a monocular camera for a pedestrian detector and 2D pedestrian pose estimation for determining the intentions of the pedestrian [219][220][221], whereas [220,221] used machine learning techniques that can also be applied using DL techniques. This technique is simpler to implement than some other pedestrian intention estimation techniques that require stereo cameras and optical flow to function.…”

Section: Approachmentioning

confidence: 99%

Pedestrian and Cyclist Detection and Intent Estimation for Autonomous Vehicles: A Survey

et al. 2019

View full text Add to dashboard Cite

As autonomous vehicles become more common on the roads, their advancement draws on safety concerns for vulnerable road users, such as pedestrians and cyclists. This paper presents a review of recent developments in pedestrian and cyclist detection and intent estimation to increase the safety of autonomous vehicles, for both the driver and other road users. Understanding the intentions of the pedestrian/cyclist enables the self-driving vehicle to take actions to avoid incidents. To make this possible, development of methods/techniques, such as deep learning (DL), for the autonomous vehicle will be explored. For example, the development of pedestrian detection has been significantly advanced using DL approaches, such as; Fast Region-Convolutional Neural Network (R-CNN) , Faster R-CNN and Single Shot Detector (SSD). Although DL has been around for several decades, the hardware to realise the techniques have only recently become viable. Using these DL methods for pedestrian and cyclist detection and applying it for the tracking, motion modelling and pose estimation can allow for a successful and accurate method of intent estimation for the vulnerable road users. Although there has been a growth in research surrounding the study of pedestrian detection using vision-based approaches, further attention should include focus on cyclist detection. To further improve safety for these vulnerable road users (VRUs), approaches such as sensor fusion and intent estimation should be investigated.

show abstract

Section: Approachmentioning

confidence: 99%

Pedestrian and Cyclist Detection and Intent Estimation for Autonomous Vehicles: A Survey

et al. 2019

View full text Add to dashboard Cite

show abstract

“…The box might not exactly fit the object, in which case the image coordinate might not always correspond to the actual 3D point on the ground representing the object's position in the real-world. However, this error can be eliminated through tracking the object in multiple frames [38]. Knowing the intrinsic and extrinsic camera calibration parameters, the inverse perspective map may be calibrated to scale, and thus the technique allows for estimating the object's state as position x and y in the frame of reference of the ego-vehicle.…”

Section: Object Localizationmentioning

confidence: 99%

Cooperative perception in autonomous ground vehicles using a mobile‐robot testbed

Sridhar

Eskandarian

2019

IET Intelligent Transport Systems

View full text Add to dashboard Cite

With connected and autonomous vehicles, no optimal standard or framework currently exists, outlining the right level of information sharing for cooperative autonomous driving. Cooperative Perception is proposed among vehicles, where every vehicle is transformed into a moving sensor platform that is capable of sharing information collected using its on-board sensors. This helps extend the line of sight and field of view of autonomous vehicles, which otherwise suffer from blind spots and occlusions. This increase in situational awareness promotes safe driving over a short range and improves traffic flow efficiency over a long range. I'm deeply indebted to my graduate advisor and mentor, Dr.Azim Eskandarian for having provided me, the opportunity to work with him and learn from his years of experience on Intelligent Vehicles Research. I'm grateful for all the insight, both technical and on the general nature of research, and for his constant motivation, patience and optimism, which kept me going. He steered me in the right direction when necessary, but also provided the freedom that empowered me to develop independent ideas. I thank Dr.John Ferris and Dr.Saied Taheri for serving as my graduate thesis committee members, for their expert feedback and for reviewing this work to completeness. I am also indebted to Dr.John Ferris for his guidance and advice during my time at Virginia Tech. I'm thankful to all my labmates at the ASIM Lab, especially Dr.Yuan Lin for his contribution in developing the initial indoor test-track and positioning system and Dr.Lirong Wang for her feedback and advice. I'm grateful to my friends and colleagues for all the motivation, technical insight and support in much needed moments. I thank Savio Pereira for the detailed discussions that helped refine the idea. I thank my professors at Virginia Tech for equipping me with the necessary background for carrying out this research. I'm also thankful to the ME Department Staff, who always had the time and a solution, for all my queries, that helped complete this project on time. Lastly, I'm grateful to my parents for having believed in me. None of this would have seen the light of day, if not for them. They were a source of endless emotional support and their love, assurance and motivation kept me working through thick and thin and succeed in Graduate school.

show abstract

“…Path prediction and gait analysis: There have been numerous studies on predicting the trajectories of pedestrians to prevent collisions and improve surround vehicle safety. These methods generally ignore high-level semantics (such as pedestrian intent) and predict the paths based on low level cues alone [11]- [15]. Intent analysis: The aim of such studies is to make an estimate of the pedestrians' intention in the near future, so as to take appropriate measures to reduce risk of collision.…”

Section: Related Workmentioning

confidence: 99%

When Vehicles <italic>See</italic> Pedestrians With Phones: A Multicue Framework for Recognizing Phone-Based Activities of Pedestrians

Rangesh

Trivedi

2018

IEEE Trans. Intell. Veh.

View full text Add to dashboard Cite

The intelligent vehicle community has devoted considerable efforts to model driver behavior, and in particular to detect and overcome driver distraction in an effort to reduce accidents caused by driver negligence. However, as the domain increasingly shifts towards autonomous and semi-autonomous solutions, the driver is no longer integral to the decision making process, indicating a need to refocus efforts elsewhere. To this end, we propose to study pedestrian distraction instead. In particular, we focus on detecting pedestrians who are engaged in secondary activities involving their cellphones and similar handheld multimedia devices from a purely vision-based standpoint. To achieve this objective, we propose a pipeline incorporating articulated human pose estimation, followed by a soft object label transfer from an ensemble of exemplar SVMs trained on the nearest neighbors in pose feature space. We additionally incorporate head gaze features and prior pose information to carry out cellphone related pedestrian activity recognition. Finally, we offer a method to reliably track the articulated pose of a pedestrian through a sequence of images using a particle filter with a Gaussian Process Dynamical Model (GPDM), which can then be used to estimate sequentially varying activity scores at a very low computational cost. The entire framework is fast (especially for sequential data) and accurate, and easily extensible to include other secondary activities and sources of distraction.

show abstract

Trajectory analysis and prediction for improved pedestrian safety: Integrated framework and evaluations

Cited by 58 publications

References 28 publications

Pedestrian and Cyclist Detection and Intent Estimation for Autonomous Vehicles: A Survey

Pedestrian and Cyclist Detection and Intent Estimation for Autonomous Vehicles: A Survey

Cooperative perception in autonomous ground vehicles using a mobile‐robot testbed

When Vehicles <italic>See</italic> Pedestrians With Phones: A Multicue Framework for Recognizing Phone-Based Activities of Pedestrians

Contact Info

Product

Resources

About