Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2019 Feb 5;19(3):652.
doi: 10.3390/s19030652.

An Appearance-Based Tracking Algorithm for Aerial Search and Rescue Purposes

Abdulla Al-Kaff  1 , María José Gómez-Silva  2 , Francisco Miguel Moreno  3 , Arturo de la Escalera  4 , José María Armingol  5
Affiliations

An Appearance-Based Tracking Algorithm for Aerial Search and Rescue Purposes

Abdulla Al-Kaff et al. Sensors (Basel). .

Abstract

The automation of the Wilderness Search and Rescue (WiSAR) task aims for high levels of understanding of various scenery. In addition, working in unfriendly and complex environments may cause a time delay in the operation and consequently put human lives at stake. In order to address this problem, Unmanned Aerial Vehicles (UAVs), which provide potential support to the conventional methods, are used. These vehicles are provided with reliable human detection and tracking algorithms; in order to be able to find and track the bodies of the victims in complex environments, and a robust control system to maintain safe distances from the detected bodies. In this paper, a human detection based on the color and depth data captured from onboard sensors is proposed. Moreover, the proposal of computing data association from the skeleton pose and a visual appearance measurement allows the tracking of multiple people with invariance to the scale, translation and rotation of the point of view with respect to the target objects. The system has been validated with real and simulation experiments, and the obtained results show the ability to track multiple individuals even after long-term disappearances. Furthermore, the simulations present the robustness of the implemented reactive control system as a promising tool for assisting the pilot to perform approaching maneuvers in a safe and smooth manner.

Keywords: UAV; multi-object tracking; reactive control; rescue.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
System Overview.
Figure 2
Figure 2
Proposed approach. (a) Floor removal stage; (b) object detections; (c) human pose filter analysis; (d) corresponding identity to every human detection.
Figure 3
Figure 3
Plane segmentation for floor removal.
Figure 4
Figure 4
Pose dissimilarity measure dp(ti,hj): (a) track, Pti, and human object, Phj, poses; (b) track, RPti, and human object, RPhj, rotated poses; (c) track rotated pose, RPti, and human object rotated and translated pose, RTPhj; (d) joints distances.
Figure 5
Figure 5
Multi-object tracking (MOT) algorithm output: (a) pose structures representation of the detected human objects, (b) updated tracks bounding boxes.
Figure 6
Figure 6
Unmanned aerial vehicle (UAV) Controller loops.
Figure 7
Figure 7
Pixhawk autopilot flight modes.
Figure 8
Figure 8
Dynamic Parametric Field algorithm danger zones.
Figure 9
Figure 9
Repulsion curve for vi=1.5 m/s and hdesired=1.5 m.
Figure 10
Figure 10
Velocity braking output as a function of velocity and distance.
Figure 11
Figure 11
Reference velocity with respect to the distance.
Figure 12
Figure 12
Distance estimation by the three evaluated algorithms Experiment 1.
Figure 13
Figure 13
Velocity estimation by the three evaluated algorithms Experiment 1.
Figure 14
Figure 14
Reference velocity with respect to the distance for the three evaluated algorithms Experiment 1.
Figure 15
Figure 15
Distance estimation by the three evaluated algorithms Experiment 2.
Figure 16
Figure 16
Velocity estimation by the three evaluated algorithms Experiment 2.
Figure 17
Figure 17
Reference velocity with respect to the distance for the three evaluated algorithms Experiment 2.
Figure 18
Figure 18
Distance estimation by the three evaluated algorithms Experiment 3.
Figure 19
Figure 19
Velocity estimation by the three evaluated algorithms Experiment 3.
Figure 20
Figure 20
Reference velocity with respect to the distance for the three evaluated algorithms Experiment 3.
See this image and copyright information in PMC

References

    1. Ahmad A., Tahar K.N., Udin W.S., Hashim K.A., Darwin N., Hafis M., Room M., Hamid N.F.A., Azhar N.A.M., Azmi S.M. Digital aerial imagery of unmanned aerial vehicle for various applications; Proceedings of the 2013 IEEE International Conference on Control System, Computing and Engineering (ICCSCE); Mindeb, Malaysia. 29 November–1 December 2013; pp. 535–540.
    1. Ma L., Li M., Tong L., Wang Y., Cheng L. Using unmanned aerial vehicle for remote sensing application; Proceedings of the 2013 21st International Conference on Geoinformatics (GEOINFORMATICS); Kaifeng, China. 20–22 June 2013; pp. 1–5.
    1. Tampubolon W., Reinhardt W. UAV Data Processing for Large Scale Topographical Mapping. ISPRS Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci. 2014;XL-5:565–572.
    1. Li Y.-C., Ye D.-M., Ding X.-B., Teng C.-S., Wang G.-H., Li T.-H. UAV Aerial Photography Technology in Island Topographic Mapping; Proceedings of the 2011 International Symposium on Image and Data Fusion (ISIDF); Tengchong, China. 9–11 August 2011; pp. 1–4.
    1. Rathinam S., Almeida P., Kim Z., Jackson S., Tinka A., Grossman W., Sengupta R. Autonomous searching and tracking of a river using an UAV; Proceedings of the American Control Conference; New York, NY, USA. 11–13 July 2007; pp. 359–364.

LinkOut - more resources