Hitoshi Saji

Extraction and tracking of the license plate using Hough transform and voted block matching

In recent years, the method of license plate tracking has been applied for obtaining the position of the nearby vehicles from a vehicle. In this paper, we propose a new method of license plate extracting and tracking from time sequential images taken by a video camera on a vehicle. For extracting and tracking the plate correctly, we use Hough transform and Voted Block Matching. This method enables the extracting and tracking even when the distance between the camera on the vehicle and the license plate of another vehicle is changing or the plate is occluded by some objects.

Vehicle Motion Tracking Using Symmetry of Vehicle and Background Subtraction

We propose a new method of vehicle motion tracking. In our method, we use the template matching method for tracking. The template matching method has been used in many applications. In vehicle tracking, there are some problems, such as vehicle size change, occlusions, and shaded areas. To solve these problems, we divide and update the template at every frame by the background subtraction method. Moreover, we use the information that the front of the vehicle body is symmetric, and we remove areas other than the vehicle area and update the template correctly. We evaluate the efficacy of our method on several video frames.

Hand motion tracking based on a constraint of three-dimensional continuity

We propose to set a 3-D search volume for tracking a 3-D palm motion efficiently using two cameras. If we perform template matching for right and left images independently, two points in two images do not always correspond to each other. Then, we cannot always track the correct 3-D position. Instead of finding the corresponding point in each image, we set the search volume in the 3-D space, not in the 2-D image planes, so that only valid 2-D pairs are considered in the proposed search process. The tracking process is as follows. First, we set the search volume. The 3-D coordinates of the search volume are projected on two in each image plane. We perform template matching at the projected pixel in each image. The similarity of the 3-D position is computed from two dissimilarities in the two images. We search for the position that has the maximum similarity in the search volume, and we obtain the correct correspondence result. We incorporate this technique into our tracking system, and we compare the proposed method with a method that tracks a palm motion without epipolar constraint. Our experimental results show that use of the proposed 3-D search volume makes the method accurate and efficient for tracking the 3-D motion.

Muscle-Based Feature Models for Analyzing Facial Expressions

We propose deformable models for tracking the continual motions of facial features, such as the eyebrows and mouth, in facial images. Directions and ranges of deformations of each facial feature are physically constrained by facial muscles. By using the directions and locations of facial muscles, feature models can be constructed with a few parameters and can be deformed only in the proper range and to the proper direction. The model parameters are obtained from the deformations of facial muscles, hence the proposed model can be easily applied to the anatomical analysis of facial expressions.

Recognition of facial expressions using muscle-based feature models

We present a technique for recognizing facial expressions from image sequences. The technique uses muscle-based feature models for tracking facial features. Since the feature models are constructed with a small number of parameters and are deformable in the limited range and directions, each search space for a feature can be limited. The technique estimates muscular contractile degrees for classifying six principal facial expressions. The contractile vectors are obtained from the deformations of facial muscle models. Similarities are defined between those vectors and representative vectors of principal expressions and are used for determining facial expressions.

Robust template matching by using variable size block division

Template matching is used in many applications, such as object recognition and motion tracking. In this study, we propose a template matching method that is robust against rotation and occlusion. For this purpose, we first divide a template image into several blocks. In the division, each block size is variable on the basis of the brightness distribution in the block region. Next, we search the matching position of each block by using a color histogram matching method whose result is rotational invariant. Then, from the matching coordinates of each block, we compute the Helmert transformation parameters and vote to the coordinates in the space composed of the parameters. Finally, we obtain the matching position of the template by searching the optimum Helmert transformation parameters from the coordinates where the sum of the vote is the maximum. We evaluate the efficacy of our method by means of several experiments. This method enables the robust extraction of an object which is rotated or occluded and is usable in many applications.

Automatic registration of aerial oblique images and a digital map

In a natural disaster, it is important to rapidly identify damage over a wide area. To this end, it is necessary to detect damaged areas automatically regardless of the weather. For this purpose, it is useful to use aerial oblique images, because they enable us to collect information over a wide region at a low altitude. In this study, we propose a method of automatic registration of aerial oblique images and a digital map by two-stage processing.

Estimation of earthquake damage from aerial images by probabilistic method

We propose a flexible probabilistic method for the extraction of earthquake-damaged areas from post-earthquake images. We segment an aerial image into regions and classify each region on the basis of the features appearing in damaged areas. We consider the similarity of neighboring regions in the classification. As a result of segmentation, the classification is independent of the color of each region. Our results show the likelihood of a region being damaged and enable the flexible estimation of damage based on human decisions. The results are displayed on a digital map that enables the estimation of building damage and road trafficability. Such maps can be used for various rescue and humanitarian activities.

Extraction of earthquake-damaged areas from aerial images by probabilistic method

We propose a flexible probabilistic method for the extraction of earthquake-damaged areas from aerial images. We segment an aerial image into regions and classify each region on the basis of the features appearing in damaged areas. We consider the similarity of neighboring regions in the classification. As a result of segmentation, the classification is independent of the color of each region. Our results show the likelihood of a region being damaged and enable the flexible estimation of damage based on human decisions. The result is displayed on a digital map that can be used for various rescue and humanitarian activities.

Extraction of road markings from aerial images

We propose a method of extracting road markings, such as crosswalks, from aerial images. The purpose of our study is to extract road markings to store them as a map. We use aerial images for automatically obtaining road markings over a wide area at one time, and we use the digital maps to extract the road areas in the aerial images. We can process the images without the effect of the town blocks in the aerial images by using the digital map. In addition, we recognize the type of road markings using edge directions and shape features of extracted road markings. In this study, we extract and recognize crosswalks and traffic lane lines.