Extracting Vehicle Track Information from Unstabilized Drone Aerial Videos Using YOLOv4 Common Object Detector and Computer Vision

Emiyah, Christian; Nyarko, Kofi; Chavis, Celeste; Bhuyan, Istiak

doi:10.1007/978-3-030-89880-9_18

Cited by 2 publications

(1 citation statement)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Emiyah et al used YOLO V4 to detect objects and track them from the perspective of a drone in the DeepSORT framework. Ning et al employed YOLO V5 to collect the object's real-time position and paired it with the DeepSORT framework to determine the object's speed [20]. Jadhav et al created a deep association network to score objects based on the similarity of in-depth features while also tracking the identification labels of multiple objects of the same class, fusing the confidence provided by the detector with the depth association measure, and transferring them to the DeepSORT network to generate the object trajectory, which improved the tracking accuracy of objects with high confidence in the object but low depth correlation [21].…”

Section: Detection-based Multi-object Trackingmentioning

confidence: 99%

DB-Tracker: Multi-Object Tracking for Drone Aerial Video Based on Box-MeMBer and MB-OSNet

Yuan,

Wu,

Zhao

et al. 2023

Drones

View full text Add to dashboard Cite

Drone aerial videos offer a promising future in modern digital media and remote sensing applications, but effectively tracking several objects in these recordings is difficult. Drone aerial footage typically includes complicated sceneries with moving objects, such as people, vehicles, and animals. Complicated scenarios such as large-scale viewing angle shifts and object crossings may occur simultaneously. Random finite sets are mixed in a detection-based tracking framework, taking the object’s location and appearance into account. It maintains the detection box information of the detected object and constructs the Box-MeMBer object position prediction framework based on the MeMBer random finite set point object tracking. We develop a hierarchical connection structure in the OSNet network, build MB-OSNet to get the object appearance information, and connect feature maps of different levels through the hierarchy such that the network may obtain rich semantic information at different sizes. Similarity measurements are computed and collected for all detections and trajectories in a cost matrix that estimates the likelihood of all possible matches. The cost matrix entries compare the similarity of tracks and detections in terms of position and appearance. The DB-Tracker algorithm performs excellently in multi-target tracking of drone aerial videos, achieving MOTA of 37.4% and 46.2% on the VisDrone and UAVDT data sets, respectively. DB-Tracker achieves high robustness by comprehensively considering the object position and appearance information, especially in handling complex scenes and target occlusion. This makes DB-Tracker a powerful tool in challenging applications such as drone aerial videos.

show abstract

Section: Detection-based Multi-object Trackingmentioning

confidence: 99%

DB-Tracker: Multi-Object Tracking for Drone Aerial Video Based on Box-MeMBer and MB-OSNet

Yuan,

Wu,

Zhao

et al. 2023

Drones

View full text Add to dashboard Cite

show abstract

YOLO-Based UAV Technology: A Review of the Research and Its Applications

Chen

Zheng

et al. 2023

Drones

View full text Add to dashboard Cite

In recent decades, scientific and technological developments have continued to increase in speed, with researchers focusing not only on the innovation of single technologies but also on the cross-fertilization of multidisciplinary technologies. Unmanned aerial vehicle (UAV) technology has seen great progress in many aspects, such as geometric structure, flight characteristics, and navigation control. The You Only Look Once (YOLO) algorithm was developed and has been refined over the years to provide satisfactory performance for the real-time detection and classification of multiple targets. In the context of technology cross-fusion becoming a new focus, researchers have proposed YOLO-based UAV technology (YBUT) by integrating the above two technologies. This proposed integration succeeds in strengthening the application of emerging technologies and expanding the idea of the development of YOLO algorithms and drone technology. Therefore, this paper presents the development history of YBUT with reviews of the practical applications of YBUT in engineering, transportation, agriculture, automation, and other fields. The aim is to help new users to quickly understand YBUT and to help researchers, consumers, and stakeholders to quickly understand the research progress of the technology. The future of YBUT is also discussed to help explore the application of this technology in new areas.

show abstract

Extracting Vehicle Track Information from Unstabilized Drone Aerial Videos Using YOLOv4 Common Object Detector and Computer Vision

Cited by 2 publications

References 18 publications

DB-Tracker: Multi-Object Tracking for Drone Aerial Video Based on Box-MeMBer and MB-OSNet

DB-Tracker: Multi-Object Tracking for Drone Aerial Video Based on Box-MeMBer and MB-OSNet

YOLO-Based UAV Technology: A Review of the Research and Its Applications

Contact Info

Product

Resources

About