Jaechoon Chon

Determination of the optimal seam-lines in image mosaicking with the dynamic programming (DP) on the converted cost space

A novel algorithm to determine the optimal seam-line in image mosacking is proposed to establish the best borderline among neighboring images. The algorithm is based on the utilization of the dynamic programming algorithm on the converted cost field. The converting function is created adaptively based on the distribution of the pixel difference values. The path found with this algorithm runs along the smaller cost regions regardless its length.

Retrieval of 3d video mosaics for fast 3d visualization

3D video mosaics created by 3D image mosaicking, our previous research, are for 3D visualization of the roadside standing building scene captured by a side-looking video camera as a continuous set of vertical-textured planar faces. These vertical faces were concatenated to create an approximate model on which the images could be back-projected as textures. We proposed a retrieval technique of selecting vertical-textured planar faces from archived 3D image mosaics to fast represent a 3D world, where this selection is based on proximity to the user location in the virtual world. The chosen vertical-textured planar faces are recomposed as a continuous set formed stream and are then rendered in 3D virtual space.

Robust fault matched optical flow detection using 2d histogram

This paper propose an algorithm by which to achieve robust outlier detection without fitting camera models. This algorithm is applicable for cases in which the outlier rate is over 85%. If the outlier rate of optical flows is over 45%, then discarding outliers with conventional algorithms in real-time applications is very difficult. The proposed algorithm overcomes conventional difficulties by using a three-step algorithm: 1) construct a two-dimensional histogram with two axes having the lengths and directions of the optical flows; 2) sort the number of optical flows in each bin of the two-dimensional histogram in descending order, and remove bins having a lower number of optical flows than the given threshold: 3) increase the resolution of the two-dimensional histogram if the number of optical flows grouped in a specific bin is over 20%, and decrease the resolution if the number of optical flows is less than 10%. This process is repeated until the number of optical flows falls into a range of 10%-20%. The proposed algorithm works well on different kinds of images having many outliers. Experimental results are reported.

3D panoramic mosaicking to suppress the ghost effect at far-range scene for urban area visualization

3D image mosaicking is useful for 3D visualization of the roadside scene of urban area by projecting 2D images to the 3D planes. When a sequence of images are filmed from a side-looking video camera passing far-range areas, the ghost effect in which same objects appear repeatedly occurs. To suppress such ghost effect, the far-range areas are detected by using the distance between the image frame and the 3D coordinate of tracked optical flows. The ghost effects are suppressed by projecting the part of image frames onto 3D multiple planes utilizing vectors passing the focal point of frames and a vertical slit. The vertical slit is calculated by utilizing the first and last frames of the far-range areas. We demonstrated algorithm that creates efficient 3D panoramic mosaics without the ghost effect at the far-range area.

X3D web service using 3d image mosaicing and location-based image indexing

We present a method of 3D image mosaicing for effective 3D representation of roadside buildings and implement an X3D-based Web service for the 3D image mosaics generated by the proposed method. A more realistic 3D facade model is developed by employing the multiple projection planes using sparsely distributed feature points and the sharp corner detection using perpendicular distances between a vertical plane and its feature points. In addition, the location-based image indexing enables stable providing of the 3D image mosaics in X3D format over the Web, using tile segmentation and direct reference to memory address for the selective retrieval of the image-slits around users location.