The Unmanned Aerial Vehicle Benchmark: Object Detection, Tracking and Baseline

Yu, Hongyang; Li, Guorong; Zhang, Weigang; Huang, Qingming; Du, Dawei; Tian, Qi; Sebe, Nicu

doi:10.1007/s11263-019-01266-1

Cited by 109 publications

(46 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are several excellent methods, such as a model-free tracker [36] or a convolutional neural network (CNN)-based tracker [37,38]. To evaluate the performance of the tracker, Yu et al [39] present a UAV dataset with 100 videos featuring approximately 2700 vehicles recorded under unconstrained conditions and 840 k manually annotated bounding boxes.…”

Section: Discussionmentioning

confidence: 99%

A Machine Learning Method for Vision-Based Unmanned Aerial Vehicle Systems to Understand Unknown Environments

Wang

Xiao

2020

Sensors

View full text Add to dashboard Cite

What makes unmanned aerial vehicles (UAVs) intelligent is their capability of sensing and understanding new unknown environments. Some studies utilize computer vision algorithms like Visual Simultaneous Localization and Mapping (VSLAM) and Visual Odometry (VO) to sense the environment for pose estimation, obstacles avoidance and visual servoing. However, understanding the new environment (i.e., make the UAV recognize generic objects) is still an essential scientific problem that lacks a solution. Therefore, this paper takes a step to understand the items in an unknown environment. The aim of this research is to enable the UAV with basic understanding capability for a high-level UAV flock application in the future. Specially, firstly, the proposed understanding method combines machine learning and traditional algorithm to understand the unknown environment through RGB images; secondly, the You Only Look Once (YOLO) object detection system is integrated (based on TensorFlow) in a smartphone to perceive the position and category of 80 classes of objects in the images; thirdly, the method makes the UAV more intelligent and liberates the operator from labor; fourthly, detection accuracy and latency in working condition are quantitatively evaluated, and properties of generality (can be used in various platforms), transportability (easily deployed from one platform to another) and scalability (easily updated and maintained) for UAV flocks are qualitatively discussed. The experiments suggest that the method has enough accuracy to recognize various objects with high computational speed, and excellent properties of generality, transportability and scalability.

show abstract

Section: Discussionmentioning

confidence: 99%

A Machine Learning Method for Vision-Based Unmanned Aerial Vehicle Systems to Understand Unknown Environments

Wang

Xiao

2020

Sensors

View full text Add to dashboard Cite

show abstract

“…e defined region of interest Mathematical Problems in Engineering mainly affects image processing speed because it only processes a specific image. e algorithms discussed in [5][6][7][8][9] do not rely solely on using the information of colors but also using the movement and shape of the object; due to this fact, they provide object detection that is more robust to noise. us, it is more robust to lighting, blur, and contrast.…”

Section: Previous Studiesmentioning

confidence: 99%

A Comprehensive Review on Design of Autonomous Robotic Boat for Rescue Applications

Jain

Saini

Gupta

et al. 2021

Mathematical Problems in Engineering

View full text Add to dashboard Cite

New technologies are advancing and emerging day by day to improve the safety of humans by making use of various autonomous technologies. The continuous utilization of autonomous vehicles/systems in search and rescue (SAR) operations is a challenging research area particularly for marine-based activities. A comprehensive systematic literature review (SLR) providing an overview of improvisations that have been done in the field of autonomous technologies for search and rescue operation over the last five years has been compiled in this paper. A methodology for using autonomous vehicles in water for SAR operations has been incorporated and demonstrated. The focus of this study is to look at the various techniques and address different challenges faced for human beings’ safety during rescue operation. The comparison of results achieved for various technologies and algorithms is highlighted in this paper. This literature survey proves to be a good source of information for fellow researchers to precisely analyze the study results.

show abstract

“…The area coverage is one of the main challenging missions. More challenges can be considered during an area coverage mission, such as avoiding obstacles in 3-Dimensional [ 15 ] or 2-Dimensional environment [ 16 ], tracking moving objects [ 17 ], data collection [ 18 ], avoiding non-flying zones [ 16 , 19 , 20 ], etc. Depending on how large and how complex the area is, an exact or approximate cellular decomposition of the area can be used to support the coverage path planning operations, and to generate efficient paths.…”

Section: Introductionmentioning

confidence: 99%

PPS: Energy-Aware Grid-Based Coverage Path Planning for UAVs Using Area Partitioning in the Presence of NFZs

Ghaddar

Merei

Natalizio

2020

Sensors

View full text Add to dashboard Cite

Area monitoring and surveillance are some of the main applications for Unmanned Aerial Vehicle (UAV) networks. The scientific problem that arises from this application concerns the way the area must be covered to fulfill the mission requirements. One of the main challenges is to determine the paths for the UAVs that optimize the usage of resources while minimizing the mission time. Different approaches rely on area partitioning strategies. Depending on the size and complexity of the area to monitor, it is possible to decompose it exactly or approximately. This paper proposes a partitioning method called Parallel Partitioning along a Side (PPS). In the proposed method, grid-mapping and grid-subdivision of the area, as well as area partitioning are performed to plan the UAVs path. An extra challenge, also tackled in this work, is the presence of non-flying zones (NFZs). These zones are areas that UAVs must not cover or pass over it. The proposal is extensively evaluated, in comparison with existing approaches, to show that it enables UAVs to plan paths with minimum energy consumption, number of turns and completion time while at the same time increases the quality of coverage.

show abstract

The Unmanned Aerial Vehicle Benchmark: Object Detection, Tracking and Baseline

Cited by 109 publications

References 64 publications

A Machine Learning Method for Vision-Based Unmanned Aerial Vehicle Systems to Understand Unknown Environments

A Machine Learning Method for Vision-Based Unmanned Aerial Vehicle Systems to Understand Unknown Environments

A Comprehensive Review on Design of Autonomous Robotic Boat for Rescue Applications

PPS: Energy-Aware Grid-Based Coverage Path Planning for UAVs Using Area Partitioning in the Presence of NFZs

Contact Info

Product

Resources

About