Sorry, you need to enable JavaScript to visit this website.

We propose a method for accurate alignment of ground and aerial multi-view stereo (MVS) models. We achieve this goal by reconstructing the surface meshes from MVS point clouds generated by aerial and ground images respectively, and then iteratively removing the gap between them. The key issue is how to establish reliable correspondences between two meshes.

In this paper, we propose an infinite impulse response (IIR)
filtering with complex coefficients for Euclid distance based
filtering, e.g. bilateral filtering. Recursive filtering of edgepreserving
filtering is the most efficient filtering. Recursive
bilateral filtering and domain transform filtering belong to
this type. These filters measure the difference between pixel
intensities by geodesic distance. Also, these filters do not
have separability. The aspects make the filter sensitive to

A novel trademark image retrieval(TIR) method is proposed in this work. The proposed approach commences with region partitioning through rotationally capturing multi-level regions of an image in a hierarchical manner, and then an effective region measurement is used as shape description of the regions generated from region partitioning stage. A shifting feature matching strategy is used to evaluate the similarity between the query and database images. The experimental results on the standard shape databases demonstrate its superiority performance over the state-of-the-art approaches.

Person re-identification that aims at matching individuals across multiple camera views has become indispensable in intelligent video surveillance systems. It remains challenging due to the large variations of pose, illumination, occlusion and camera viewpoint. Feature representation and metric learning are the two fundamental components in person re-identification.

Person re-identification that aims at matching individuals across multiple camera views has become indispensable in intelligent video surveillance systems. It remains challenging due to the large variations of pose, illumination, occlusion and camera viewpoint. Feature representation and metric learning are the two fundamental components in person re-identification.

Semantic segmentation of indoor scene images has a wide range of
applications. However, due to a large number of classes and uneven
distribution in indoor scenes, mislabels are often made when facing
small objects or boundary regions. Technically, contextual infor-
mation may benefit for segmentation results, but has not yet been
exploited sufficiently. In this paper, we propose a learnable contex-
tual regularization model for enhancing the semantic segmentation
results of color indoor scene images. This regularization model is

High-fidelity color image restoration is always of high de- manding for high-density noise corrupted images. Such problem becomes more challenging if the degraded image and the expected restored image are of different resolutions, as conventional ‘cascaded: denoising followed by sampling’ and ‘operation on RGB channel independently’ methods induce error amplification and color artifacts.