The mosaicking of Unmanned Aerial Vehicle (UAV) imagery usually requires information from additional sensors, such as Global Position System (GPS) and Inertial Measurement Unit (IMU), to facilitate direct orientation, or 3D reconstruction approaches (e.g., structure-from-motion) to recover the camera poses. In this paper, we propose a novel mosaicking method for UAV imagery in which neither direct nor indirect orientation procedures are required. Inspired by the embedded deformation model, a widely used non-rigid mesh deformation model, we present a novel objective function for image mosaicking. Firstly, we construct a feature correspondence energy term that minimizes the sum of the squared distances between matched feature pairs to align the images geometrically. Secondly, we model a regularization term that constrains the image transformation parameters directly by keeping all transformations as rigid as possible to avoid global distortion in the final mosaic. Experimental results presented herein demonstrate that the accuracy of our method is twice as high as an existing (purely image-based) approach, with the associated benefits of significantly faster processing times and improved robustness with respect to reference image selection.

In this study, the authors present a novel human body contour tracking method which adaptively combines colour and depth cues of RGB‐D images in level set framework. The authors model the body object by active contour. When the body object is far away from the background objects, it is relatively easy to separate the object from the background using the depth cue. In this case, the depth cue should dominate the evolution of the active contour. When some part of the body is very close to the background objects, the discriminability of the depth decreases rapidly. In this local region the colour cue should dominate the evolution, whereas the depth cue should still play an important role in other regions. To achieve these objectives, the authors propose to use a superpixel‐based locally adaptive weight map to determine the importance of the depth cue. Moreover, to obtain more accurate contours and to avoid error drifting, based on the two novel properties of the human body surface in the depth images, the authors propose two simple but effective algorithms to refine the tracking results of the level set method. The promising results demonstrate the performance of the proposed method.

A novel real-time full-field phase unwrapping framework is proposed for the one-projector and one-camera structured light system. In this framework, only four patterns (including three fringe patterns and a binary speckle pattern) are required to measure the absolute 3D shape of the targets. We use the structured light system to capture four images of a nearly planar target (e.g. wall), of which the speckle image is taken as the reference image, and the corresponding absolute phase map is computed and stored, before measuring. So each pixel in the reference image can be mapped to an absolute phase value. In this way, if we can create the correspondences between the current and the reference speckle images in the process of measurement by using a matching algorithm, we can directly map the absolute values for the pixels of the current image. The mapped absolute phases can be used to determine the period of the relative phases. The experimental results verified the effectiveness and efficiency of the proposed framework. On a consumer-grade GPU (Nvidia GTX1060), our method can run at 187 fps.