No abstract

No abstract

Image flow, the apparent motion of brightness patterns on the image plane, can provide important visual information such as distance, shape, surface orientation, and boundaries. It can be determined by either feature tracking or spatio-temporal analysis. The optical flow thus determined can be used to reconstruct the 3-D scene by determining the depth from camera of every point in the scene. However, the optical flow determined by either of the methods mentioned above will be noisy. As a result, the depth information obtained from optical flow can not be successfully used in practical applications such as image segmentation, 3-D reconsiruction, path planning, etc. By using temporal integration, we can increase the accuracy of both the optical flow and the depth determined from optical flow.In this work, we describe an incremental integration scheme called the running average method to temporally integrate the image flow. We integrate the depth from camera obtained using optical flow determined from gradient based methods, and show that the results of temporal integration are much more useful in practical applications than the results from local edge operators. Finally, we consider an image segmentation example and show the advantages of temporal integration.

No abstract

Optical flow provides an effective measure of important visual information such as distance, shape, surface orientation, and boundaries. A simple and elegant method to determine optical flow is the gradient method, where the relationship between the spatial difference and the temporal difference is used to estimate optical flow.As the number of equations that constrain the problem is one less than the number of unknowns, this problem is considered ill-posed and many assumptions have been made by previous authors to regularize the problem. Our method makes the assumption that the direction of camera motion, and hence the direction of optical flow, is known.Many applications such as target acquisition, path planning, passive navigation, and landing on unknown terrain require range estimation. In this work, a scheme to estimate differential range using optical flow along a known direction is described. The factors affecting the accuracy of results, and various spatial and temporal smoothing algorithms used to increase the accuracy of the method are described. The effect of using edge detectors and apriori knowledge of the environment is considered next. While the former reduces the noise, the latter improves the range discriminability of the method.We have implemented the method on a real-time, high-speed, Pipelined Image Processing Engine (PIPE), which processes sixty image frames per second. For the PIPE implementation, a horizontally moving camera is used, which produces optical flow along a scan line.