Traditional histogram or statistics based 2D image similarity/dissimilarity metrics fail to handle conjugate pair of black and white images, due to the lack of spatial information in the measurement. Recently proposed compression-based dissimilarity measure (CDM) based on the concept of Kolmogorov complexity has provided a different paradise for similarity measurement. However, without a clear definition on how to "concatenate" two 2D images, CDM has difficulties applying with 2D images directly. In this paper, we propose an entropy-based 2D image dissimilarity measure within the same Kolmogorov complexity paradise. The spatial relationship between images is embedded in our metric, and the actual compression of images is not needed once the entropy values are obtained. The proposed metric has been tested for scene change detection application, and encouraging results are presented here

Since the first shape-from-shading (SFS) technique was developed by Horn in the early 1970s, many different approaches have emerged. In this paper, six well-known SFS algorithms are implemented and compared. The performance of the algorithms was analyzed on synthetic images using mean and standard deviation of depth (Z) error, mean of surface gradient (p, q) error, and CPU timing. Each algorithm works well for certain images, but performs poorly for others. In general, minimization approaches are more robust, while the other approaches are faster.

Since the first shape-from-shading technique was developed by B.K.P. Horn in the early 1970s, different approaches have been continuously emerging in the past two decades. Some of them, improve existing techniques, while others are completely new approaches. However, there is no literature on, the comparison and performance analysis of these techniques. This paper provides comparison and analysis of these techniques.>

Stereo algorithms suffer from the lack of local surface texture due to smoothness of depth constraint or local mismatches in disparity estimates. The stereo methods only provide a coarse depth map which can be associated with a low pass image of the depth map. Shape from shading algorithms produce better estimates of local surface areas, but some have problems with variable albedo and spherical surfaces. Thus, shape from shading methods produce better detailed depth information, and can be associated with the high pass image of the depth map image. In order to compute a better depth map, a method is presented for integrating the high-frequency information from the shape from shading and the low frequency information from stereo.>

A new technique called shape from photomotion is introduced. It uses a series of 2-D Lambertian images, generated by moving a light source around a scene, to recover the depth map. In each of the images, the object in the scene remains at a fixed position and the only variable is the light source direction. The movement of the light source causes a change in the intensity of any given point in the image. The change in intensity is what enables recovery of the unknown parameter, the depth map, since it remains constant in each of the input images. The authors' method differs from photometric stereo in the sense that the shape estimate is not only computed for each light source orientation, but also gradually refined by photomotion.>

A simple algorithm for selecting and linking interesting flow vectors across a sequence of frames for computing motion trajectories is presented. Tokens are tracked that have both interesting pixel gray values in the spatial domain and in the optical flow field in the temporal domain. This effectively removes some redundant trajectories. Due to errors introduced during the computation of optical flow, and the linking of such flow vectors across a sequence of frames, the resultant trajectories are not always smooth. A Kalman filtering based approach is discussed for smoothing the trajectories. Isolating the trajectories into sets belonging to individual objects is an important first step that should be taken before any type of shape or motion interpretation can be done. Therefore, a simple algorithm for segmenting motion trajectories is also discussed. When motion trajectories belonging to a single translating object are extended, they intersect at a single point called the focus of expansion (FOE). If the motions of objects are assumed to be independent, each FOE represents one object. Therefore, FOE can be used to segment trajectories belonging to individual objects. A simple but highly robust algorithm for partitioning motion trajectories is presented that does not require the exact location of FOE, but uses some useful properties of FOE. The authors have applied their method for computing and segmenting motion trajectories to a number of real sequences, and have obtained very encouraging results.>

A method for computing depth from a single shaded image is presented. Discrete approximations for p and q using finite differences are used, and the reflectance in Z/sub ij/ is linearized. The method is faster, since each operation is purely local. In addition, it gives good results for spherical surfaces, in contrast to other linear methods.>

Presents an algorithm for selecting and linking interesting flow vectors across a sequence of frames for computing motion trajectories. The authors track tokens which have both interesting pixel gray values in the spatial domain and in the optical flow field in the temporal domain. This and operation effectively removes some redundant trajectories. Due to errors introduced during the computation of optical flow, and the linking of such flow vectors across a sequence of frames, the resultant trajectories are not always smooth. The authors discuss a Kalman filtering based approach for smoothing the trajectories. This approach is also able to deal with the occlusion of feature points. The authors also present a simple algorithm for segmenting motion trajectories.>