Real-Time Visual Tracking of Moving Targets Using a Low-Cost Unmanned Aerial Vehicle with a 3-Axis Stabilized Gimbal System

Liu, Xuancen; Yang, Yueneng; Ma, Chenxiang; Li, Jie; Zhang, Shifeng

doi:10.3390/app10155064

Cited by 29 publications

(22 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In fact, L FOV will be equal to the L C when the tracking error (e x−y in Fig. 2) becomes zero (13).…”

Section: • • • (9)mentioning

confidence: 99%

“…Oh et al (12) proposed a guidance law for standoff target tracking based on the differential geometry between the UAV and the target to provide rigorous stability, explicit use of the target velocity, and tuning parameter reduction. Liu et al (13) proposed an on-board vision-based system for tracking arbitrary 3D objects moving at unknown velocities by utilising a 3-axis gimbaled system. Moreover, a Kernelised Correlation Filter (KCF) tracker is used in that paper to detect and localise the target of interest from images acquired by the gimbaled camera, and proportional navigation (PN) guidance law is proposed as the tracking strategy.…”

Section: Introductionmentioning

confidence: 99%

“…Figure13. The values of the criterion parameters to guarantee the target preserving by Quad1 and the target missing by the Quad2.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Three-dimensional guidance and control for ground moving target tracking by a quadrotor

2021

View full text Add to dashboard Cite

This paper develops a three-dimensional guidance and control algorithm to ensure that a manoeuverable target is preserved by a quadrotor in a long-term tracking scenario. The proposed guidance approach determines the desired altitude of the quadrotor to adjust the field of view (FOV) to the union of two desired trusted and critical regions. The dimensions of the desired trusted region depend on the controller performance that is evaluated by the distance of the target from the center of the FOV. The critical region is a predefined margin around the trusted region that is defined by the operator based on the upper bounds of the quadrotor and target localisation errors. It also depends on the duration and magnitude of the temporal increase in the target velocity compared to the quadrotor velocity. A sufficient condition is provided for the minimum desired altitude of the quadrotor to ensure that the target is maintained in the FOV. Furthermore, a model predictive control (MPC) is employed to preserve the target at the center of the aerial image and the desired altitude determined by the guidance law. Also, the integrals of the position errors are used to achieve null steady-state errors in the presence of wind disturbances. The simulation results show the effectiveness of the proposed approach in preserving the manoeuverable target in the FOV in the presence of the wind, the uncertainty of the target and quadrotor localisation, accelerations estimation errors, and terrain altitude variation.

show abstract

“…In fact, L FOV will be equal to the L C when the tracking error (e x−y in Fig. 2) becomes zero (13).…”

Section: • • • (9)mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Three-dimensional guidance and control for ground moving target tracking by a quadrotor

2021

View full text Add to dashboard Cite

show abstract

“…Other advantages include the protection of the pilot's life, cost, and quick replaceability in the field. Major limitations include small payload, the delay in the data reception, the vulnerability of the RF communication/control link to jamming and spoofing [305]- [307] counter a wide spectrum of aerial threats, e.g., autonomous UAV swarms. A possible solution is to use combat UAVs, which can be used separately or in combination with fighter jets.…”

Section: H Combat Uavsmentioning

confidence: 99%

A Survey on Radar Techniques for Detection,Tracking, and Classification of Aerial Threats

Khawaja¹

2022

Preprint

View full text Add to dashboard Cite

<p> The use of unmanned aerial vehicles (UAVs) for different applications has increased many folds in recent years. The UAVs are expected to change the future air operations. However, there are instances where the UAVs can be used for malicious purposes. The detection, tracking, and classification of UAVs is challenging compared to manned aerial vehicles (MAVs) mainly due to small size, complex shapes, and ability to fly close to the terrain and in autonomous flight patterns in swarms. In this survey, we will discuss current and future aerial threats, and provide an overview of radar systems to counter such threats. We also study the performance parameters of radar systems for the detection, tracking, and classification of UAVs compared to MAVs. Finally, limitations of radar systems and comparison with other techniques that do not rely on radars for detection, tracking, and classification of aerial threats are also provided. </p>

show abstract

“…Existing path planning techniques for following MGVs have been mainly developed for fixed-wing UAVs [ 8 , 12 , 13 ]. They heavily rely on using gimbal cameras to aim at specific areas for coverage and tracking purposes [ 14 , 15 , 16 ], therefore, relaxing the complexities imposed by the path planning technique. Additionally, gimbal cameras are expensive, prone to failure, and consume more power than nongimbal cameras, thus affecting the UAV’s endurance and flight time.…”

Section: Introductionmentioning

confidence: 99%

UAV Path Planning for Reconnaissance and Look-Ahead Coverage Support for Mobile Ground Vehicles

Jayaweera

Hanoun

2021

Sensors

View full text Add to dashboard Cite

Path planning of unmanned aerial vehicles (UAVs) for reconnaissance and look-ahead coverage support for mobile ground vehicles (MGVs) is a challenging task due to many unknowns being imposed by the MGVs’ variable velocity profiles, change in heading, and structural differences between the ground and air environments. Few path planning techniques have been reported in the literature for multirotor UAVs that autonomously follow and support MGVs in reconnaissance missions. These techniques formulate the path planning problem as a tracking problem utilizing gimbal sensors to overcome the coverage and reconnaissance complexities. Despite their lack of considering additional objectives such as reconnaissance coverage and dynamic environments, they retain several drawbacks, including high computational requirements, hardware dependency, and low performance when the MGV has varying velocities. In this study, a novel 3D path planning technique for multirotor UAVs is presented, the enhanced dynamic artificial potential field (ED-APF), where path planning is formulated as both a follow and cover problem with nongimbal sensors. The proposed technique adopts a vertical sinusoidal path for the UAV that adapts relative to the MGV’s position and velocity, guided by the MGV’s heading for reconnaissance and exploration of areas and routes ahead beyond the MGV sensors’ range, thus extending the MGV’s reconnaissance capabilities. The amplitude and frequency of the sinusoidal path are determined to maximize the required look-ahead visual coverage quality in terms of pixel density and quantity pertaining to the area covered. The ED-APF was tested and validated against the general artificial potential field techniques for various simulation scenarios using Robot Operating System (ROS) and Gazebo-supported PX4-SITL. It demonstrated superior performance and showed its suitability for reconnaissance and look-ahead support to MGVs in dynamic and obstacle-populated environments.

show abstract

Real-Time Visual Tracking of Moving Targets Using a Low-Cost Unmanned Aerial Vehicle with a 3-Axis Stabilized Gimbal System

Cited by 29 publications

References 61 publications

Three-dimensional guidance and control for ground moving target tracking by a quadrotor

Three-dimensional guidance and control for ground moving target tracking by a quadrotor

A Survey on Radar Techniques for Detection,Tracking, and Classification of Aerial Threats

UAV Path Planning for Reconnaissance and Look-Ahead Coverage Support for Mobile Ground Vehicles

Contact Info

Product

Resources

About