Pedestrian as points: An improved anchor-free method for center-based pedestrian detection

J Cai, F Lee, S Yang, C Lin, H Chen, K Kotani… - IEEE …, 2020 - ieeexplore.ieee.org
… techniques have been proposed to deal with deep learning-based pedestrian detection, it is
still a promising … Keypoint-based object detection [30]–[32] is a sort of methods that generate …

A Deep Learning Approach for Automated Detection of Railroad Trespassers

X Yang, JQ Li, G Yang, W Liu, K Wang - … on Transportation and …, 2022 - ascelibrary.org
… and Deep SORT are implemented for trespassing detection and … detection includes two
main tasks: detection and tracking. In this research, the YOLOv4 is for detection and Deep SORT

[HTML][HTML] Enhancing Pedestrian Tracking in Autonomous Vehicles by Using Advanced Deep Learning Techniques

M Sukkar, M Shukla, D Kumar, VC Gerogiannis… - Information, 2024 - mdpi.com
pedestrian tracking algorithm built upon the StrongSORT framework. This methodology
amalgamates the strengths of both SORT and the deep … algorithms for pedestrian detection. The …

DeepSORT Pedestrian Tracking Algorithm based on Azimuth Estimation

D Fan, W Kang, Y Chen, K Wu - 2023 IEEE 7th Information …, 2023 - ieeexplore.ieee.org
SORT (Simple Online and Realtime Tracking), used deep … apparent features based on
SORT framework, and used Kuhn-… of ID exchange problems in SORT, they used the nearest …

Mtcnn-kcf-deepsort: Driver face detection and tracking algorithm based on cascaded kernel correlation filtering and deep sort

Q Wang, L Cao, J Xia, Y Zhang - 2020 - sae.org
deep networks in deep SORT, and extract deep facial features from these networks for data
association and matching in the tracking algorithm. The deep SORT … to create deep metric …

High-density pedestrian detection algorithm based on deep information fusion

H Zhang, X Yang, Z Hu, R Hao, Z Gao, J Wang - Applied Intelligence, 2022 - Springer
… population detection, a high density pedestrian detection algorithm (YOLOv4-HDPD) is
proposed based on deep … 8 is to sort the feature network structure according to the key target …

[HTML][HTML] End-to-end network for pedestrian detection, tracking and re-identification in real-time surveillance system

M Lei, Y Song, J Zhao, X Wang, J Lyu, J Xu, W Yan - Sensors, 2022 - mdpi.com
… , so that a list of potential matches, sorted by similarity, is generated. In this paper, we …
tracking and re-identification algorithm based on deep learning networks. It combines the …

Strongsort: Make deepsort great again

Y Du, Z Zhao, Y Song, Y Zhao, F Su… - IEEE Transactions …, 2023 - ieeexplore.ieee.org
… It is shown that the matching cascade algorithm greatly benefits DeepSORT. However, with
the … Citypersons: A diverse dataset for pedestrian detection. In: Proceedings of the IEEE …

Deep learning-based video analysis pipeline for person detection and re-identification in aerial imagery

A Specker, L Moritz, L Sommer - … , Crime Fighting, Forensics …, 2021 - spiedigitallibrary.org
… Next, we apply a deep learning-based tracking approach, namely Deep SORT, to
generate person tracks based on the detections. For the re-identification stage, we employ a …

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

PKY Wong, H Luo, M Wang, PH Leung… - Advanced Engineering …, 2021 - Elsevier
… Then, two jointly learnt branches are designed respectively for pedestrian detection and …
In our study, the detection branch of FairMOT is adopted to detect pedestrians from videos. For …