Recognition of pedestrian trajectories and attributes with computer vision and deep learning techniques

Wong, P.C.; Luo, Han; Wang, Mingzhu; Leung, Pak Him; Cheng, Jack Chin Pang

doi:10.1016/j.aei.2021.101356

Cited by 31 publications

(14 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Wong et al presented a methodology for pedestrian tracking and attribute recognition. The method employs high-level pedestrian attributes, a similarity measure integrating multiple cues, and a probation mechanism for robust identity matching [16]. Chowdhury et al designed a multi-target tracking algorithm for dense point clouds based on probabilistic occlusion reasoning [17].…”

Section: Related Workmentioning

confidence: 99%

“…Although the referenced studies [4][5][6]13,14] have proposed to use various information sources to track targets, they have not tried to use pedestrian attribute information for tracking. As presented in paper [16], although there is research on pedestrian attributes, its purpose is to obtain pedestrian attributes, not to use pedestrian attributes. The purposes and means of our study and the referenced study are different.…”

Section: Noveltymentioning

confidence: 99%

See 1 more Smart Citation

Tracking Pedestrians Under Occlusion in Parking Space

Zhou¹,

Yamada²,

Watanabe³

et al. 2023

Computer Systems Science and Engineering

View full text Add to dashboard Cite

Many traffic accidents occur in parking lots. One of the serious safety risks is vehicle-pedestrian conflict. Moreover, with the increasing development of automatic driving and parking technology, parking safety has received significant attention from vehicle safety analysts. However, pedestrian protection in parking lots still faces many challenges. For example, the physical structure of a parking lot may be complex, and dead corners would occur when the vehicle density is high. These lead to pedestrians' sudden appearance in the vehicle's path from an unexpected position, resulting in collision accidents in the parking lot. We advocate that besides vehicular sensing data, high-precision digital map of the parking lot, pedestrians' smart device's sensing data, and attribute information of pedestrians can be used to detect the position of pedestrians in the parking lot. However, this subject has not been studied and explored in existing studies. To fill this void, this paper proposes a pedestrian tracking framework integrating multiple information sources to provide pedestrian position and status information for vehicles and protect pedestrians in parking spaces. We also evaluate the proposed method through real-world experiments. The experimental results show that the proposed framework has its advantage in pedestrian attribute information extraction and positioning accuracy. It can also be used for pedestrian tracking in parking spaces.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Noveltymentioning

confidence: 99%

Tracking Pedestrians Under Occlusion in Parking Space

Zhou¹,

Yamada²,

Watanabe³

et al. 2023

Computer Systems Science and Engineering

View full text Add to dashboard Cite

show abstract

“…However, targets are easily obscured with unreliable recognition in video images owing to the variation in subjects’ appearance and the complexity of traffic conditions at intersections [ 21 ]. Due to the weather, illumination, and/or shadow, the rapidly changing environment can also cause inaccuracy [ 22 ]. Besides technical issues, privacy concerns were raised due to the collection of personal facial data.…”

Section: Literature Reviewmentioning

confidence: 99%

A UWB/INS Trajectory Tracking System Application in a Cycling Safety Study

Zhu

Yue

Suzuki³

et al. 2023

Sensors

View full text Add to dashboard Cite

This paper focuses on the safety issue for cyclists and pedestrians at unsignalized intersections. The cycling speed needs to be calmed when approaching the intersection. This study proposes and deploys an integrated portable ultra-wideband/inertial navigation system (UWB/INS) to extract cycling trajectories for a cycling safety study. The system is based on open-source hardware and delivers an open-source code for an adaptive Kalman filter to enhance positioning precision for data quality assurance at an outdoor experimental site. The results demonstrate that the system can deliver reliable trajectories for low-mobility objects. To mitigate accident risk and severity, varied cycling speed calming measures are tested at an experimental site. Based on the trajectory data, the statistical features of cycling velocities are evaluated and compared. A new proposed geometric design is found to be most effective when compared with conventional traffic signs.

show abstract

“…The possible implementations are in-home or industrial protection systems, in cars to alert deaf or poorly hearing drivers of the siren, in homes to alert a parent of a crying child, and in a wide range of assistive devices, especially for deaf people. Recent modern surveillance systems for risk prevention purposes focuses mainly on the analysis of video signals from cameras using advanced computer vision techniques [7], [8], [9]. However, the analysis of audio signals has considerable potential in these systems as well.…”

Section: Introductionmentioning

confidence: 99%

Independent Channel Residual Convolutional Network for Gunshot Detection

Bajzík¹,

Přinosil²,

Jarina³

et al. 2022

IJACSA

View full text Add to dashboard Cite

The main purpose of this work is to propose a robust approach for dangerous sound events detection (e.g. gunshots) to improve recent surveillance systems. Despite the fact that the detection and classification of different sound events has a long history in signal processing, the analysis of environmental sounds is still challenging. The most recent works aim to prefer the time-frequency 2-D representation of sound as input to feed convolutional neural networks. This paper includes an analysis of known architectures as well as a newly proposed Independent Channel Residual Convolutional Network architecture based on standard residual blocks. Our approach consists of processing three different types of features in the individual channels. The UrbanSound8k and the Free Firearm Sound Library audio datasets are used for training and testing data generation, achieving a 98 % F1 score. The model was also evaluated in the wild using manually annotated movie audio track, achieving a 44 % F1 score, which is not too high but still better than other state-of-the-art techniques.

show abstract

Recognition of pedestrian trajectories and attributes with computer vision and deep learning techniques

Cited by 31 publications

References 54 publications

Tracking Pedestrians Under Occlusion in Parking Space

Tracking Pedestrians Under Occlusion in Parking Space

A UWB/INS Trajectory Tracking System Application in a Cycling Safety Study

Independent Channel Residual Convolutional Network for Gunshot Detection

Contact Info

Product

Resources

About