We propose a method for measuring surface shapes of transparent objects by using a polarizing lter. Generally, the light re ected from an object is partially polarized. The degree of polarization depends upon the incident angle which, in turn, depends upon the surface normal. Therefore, we can obtain surface normals of objects by observing the degree of polarization at each surface point. Unfortunately, the correspondence between the degree of polarization and the surface normal is not one to one. Hence, to obtain the correct surface normal, we h a ve to solve the ambiguity problem. In this paper, we i n troduce a m e t h o d t o s o l v e the ambiguity b y comparing the polarization data in two objects, i.e., normal position and tilted with small angle position. We also discuss the geometrical features of the object surface and propose a method for matching two sets of polarization data at identical points on the object surface.

In this paper, we propose a novel method to recover the surface shape of transparent objects.

In this paper, we propose an efficient and effective image generation system for "Mixed Reality Traffic Experiment Space", an enhanced driving/traffic simulation system which we have been developing for Sustainable ITS project at the University of Tokyo. Conventional driving simulators represent ther view by a set of polygon-based objects, which leads to less photo-reality and huge human costs for dataset construction. We introduce our image/geometry-based hybrid method to realize more photo-realistic view with less human cost at the same time. Images for datesets are captured from real world by multiple video cameras mounted on a data acquisition vehicle. And the view for the system is created by synthesizing the image dataset. Following contents mainly describe details on data acquisition and view rendering.

This paper describes a method for vehicle recognition, in particular, for recognizing a vehicle's make and model. Our system is designed to take into account the fact that vehicles of the same make and model number come in different colors; to deal with this problem, our system employs infrared images, thereby eliminating color differences. Another reason for the use of infrared images is that it enables us to use the same algorithm both day and night. This ability is particularly important because the algorithm must be able to locate many feature points, especially at night. Our algorithm is based on a configuration of local features. For the algorithm, our system first makes a compressed database of local features of a target vehicle from training images given in advance; the system then matches a set of local features in the input image with those in the training images for recognition. This method has the following three advantages: 1) it can detect even if part of the target vehicle is occluded; 2) it can detect even if the target vehicle is translated due to running out of the lanes; and 3) it does not require us to segment a vehicle part from input images.We have two implementations of the algorithm. One is referred to as the eigenwindow method, while the other is called the vector-quantization method. The former method is good at recognition, but is not very fast. The latter method is not very good at recognition but it is suitable for an IMAP parallel image-processing board; hence, it can be fast. In both implementations, the above-mentioned advantages have been confirmed by performing outdoor experiments.Index Terms-Infrared image, parallel image processor, vehicle recognition.

No abstract

No abstract

This paper describes a method to recognize vehicles, in particular to recognize which make it is and which type it is. Our system employs infra-red images so that we can use the same algorithm in day time and at night. The algorithm is based on the vector-quantaization, originally proposed by Krumm, and is implemented on IMA P parallel image-processing board. Our system makes the compressed database of local features, for the algorithm, of a target vehicles from given training images in advance, and then matchs a set of local features in the input image with those in training images for recognition. This method has the following three advantages: (1) it can detect even if part of the target vehicles is occluded.(2) it can detect even if the target vehicles is translated due to running out of the lanes. (3) we do not need to segment a vehicle part from input images.Through outdoor experiments, we have confirmed these advantages.

We propose an efficient and effective image generation system for an experimental mixed-reality traffice space. Our enhanced traffic/driving simulation system represents the view through a hybrid that combines virtual geometry with real images to realize high photo-reality with little human cost. Images for datasets are captured from the real world, and the view for the simulation system is created by synthesizing image datasets with a conventional driving simulator.