Aerial surveillance is a main functionality of UAV, which is realized via video camera. During the operations, the mission assigned targets always are the kinetic objects, such as people or vehicles. Therefore, object tracking is taken as the key techniques for UAV sensor payload. Two difficulties for UAV object tracking are dynamic background and hardly predicting target’s motion. To solve the problems, it employed the particle filter in the research. Modeling the target by its characteristics, for instance, color features, it approximates the possibility density of target state with weighting sample sets, and the state vector contains position, motion vector and region parameters. The experiments demonstrate the effectiveness and robustness of the proposed method in UAV video tracking.
Motion detection is one of the basic operations in dynamic image analysis. In thermal image sequence processing,
motion detection is a difficult problem. In this paper, we employ multi-scale optical flow methods to solve the
problem. After analyzing the difficulties in detecting motions, multi-resolution framework is recognized as an
useful approach for the process. Phase information has been demonstrated its robustness and stability in disparity
and flow estimation. Velocity-tuned filtering integrates the multi-scale framework with the phase information.
Using a bank of Gabor filters, image velocities, which form the flow field, are estimated with the output phase
responses. Comparing with Lucas-Kanade pyramid method, our experiment shows that the approach could
compute the optical flow more accurately, and it is effective for motion detection in infrared images.
Detecting moving object is vital for dynamic imagery applications, for instance target tracking and target recognition. In
thermal infrared image, the difficulties of the motion detection come from appearance changes of the objects,
moving background or other causes. In this paper, we present a
phase-based filtering method for motion detection
in infrared images. Phase-based filtering is a frequency domain related optical flow algorithm. For measuring the
flow velocity in infrared image sequence, phase information has advantages because of its stability to geometric
deformation and linearity with spatial position. The phase information is filtered out with the Gabor filters. Based
on the output phase responses from the filters, component velocities are figured out with the spatial-temporal phase
gradients. Combining the component velocities, the full velocities form the optical flow field, which reflects the
motions in the images. We demonstrated the effectiveness of the approach with the experiments, and got good