Abstract
This paper presents two techniques in the matching and re-identification of multiple aerial target detections from multiple electro-optical devices: 2-dimensional and 3-dimensional kinematics-based matching. The main advantage of these methods over traditional image-based methods is that no prior image-based training is required; instead, relatively simpler graph matching algorithms are used. The first 2-dimensional method relies solely on the kinematic and geometric projections of the detected targets onto the images captured by the various cameras. Matching and re-identification across frames were performed using a series of correlation-based methods. This method is suitable for all targets with distinct motion observed by the camera. The second 3-dimensional method relies on the change in the size of detected targets to estimate motion in the focal axis by constructing an instantaneous direction vector in 3D space that is independent of camera pose. Matching and re-identification were achieved by directly comparing these vectors across frames under a global coordinate system. Such a method is suitable for targets in near to medium range where changes in detection sizes may be observed. While no overlapping field of view requirements were explicitly imposed, it is necessary for the aerial target to be detected in both cameras before matching can be carried out. Preliminary flight tests were conducted using 2–3 drones at varying ranges, and the effectiveness of these techniques was tested and compared. Using these proposed techniques, an MOTA score of more than 80% was achieved.
Highlights
The proposed multi-layer, two-dimensional kinematics-based matching algorithm ensures that mismatching between targets across two cameras can be minimized
This paper presents the re-identification of multiple aerial tracked targets from multiple cameras through two proposed kinematics-based methods: two-dimensional and three-dimensional kinematics-based matching
The main advantages of these methods over traditional image-based methods are: (1) no prior image recognition training is required; instead, graph matching algorithms, which are relatively simple to deploy, are used; (2) one can use various types of cameras for more operational flexibility; (3) the targets can be similar and/or repeated; (4) there is an allowance for errors such as blurred, overlapped, occluded, or shaded conditions, as long as the moving targets can be tracked
Summary
The detection of small objects through an electro-optical device is useful in augmenting manual surveillance techniques. The human eye is impervious to small and distant objects, which calls for the use of high-resolution cameras spread out across a wide area to detect such objects. With a network of cameras spanning a large surveillance space, it is important for cameras to identify common targets as they pass through each frame in order to maintain information about the objects from previous states. Since each camera is limited to its own field of vision, matching algorithms must be employed to estimate the likelihood that two observed targets are the same physical object. This paper formulates an inexact graph matching problem with the goal of maximizing the likelihood across the set of all possible pairwise matches, conditional on the positional and velocity data of all objects from the camera frames. We aimed to find: distributed under the terms and conditions of the Creative Commons argmin
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
