Naofumi Fujiwara

An Obstacle Extraction Method Using Virtual Disparity Image

The driving support system is one of most important research field in intelligent transport system (ITS). In this paper, we address an obstacle extraction method for driving support system. The stereovision system is one of most suit sensor to recognize details of environment. On the other hand, a disparity image obtained by stereovision system has quite a lot of information. Therefore an efficient algorithm to analyze obtained disparity image is strongly demanded. If the road surface is extracted, obstacles can be easily extracted by evaluating whether one object touch on a road or not. In this paper, we propose a novel method to estimate three-dimensional road surface position by using virtual disparity image. Moreover, an obstacle extraction method is expressed.

A vehicle position and heading measurement system using corner cube and laser beam

The authors propose a method for obtaining the position and heading of a ground vehicle. This method is realized by four vehicle-borne laser transceiver units and two corner cube reflectors set on both sides of a test path. The method recognizes the corner cubes by the laser units, and determines the accurate position and heading based on the triangulation principle. The obtained position and heading are applied to compensate errors caused by a dead-reckoning positioning method. Experimental results for an automobile show that the proposed method can perform accurate compensations.<<ETX>>

An experimental system for processing movement information of vehicle

This paper presents a proposed experimental system for processing movement information of vehicle. Using self-contained on-line computing processor which computes position and heading angle (azimuth), trajectory of location of vehicle has been successfully displayed by an experimental system implemented. Principles of self-contained computing system are as follows: accurate digital moving pick-ups are set on both sides of vehicle wheels, accumulation of both sides data which are picked periodically is for distance measuring and subtraction of both sides data is for heading computation, self-contained processor computes the location and heading angle, and also presents location data on X-Y recorder and digital displays. Coordinate location and heading computations are performed by electronic hard-ware mechanization. Methods for reduction of induced errors are discussed and experimentally demonstrated.

Automatic vehicle guidance &#8212; Commanded map routing

This paper presents a proposed experimental system for automatic vehicle guidance commanded by a written route on map. The system is a kind of vehicleborne location and guidance system controlled by self-contained dead-reckoning computer. The location and heading of a vehicle are essentially computed from the angular velocities of the both wheels. The steering system is operated by comparing the forecast position, heading and velocity with route on map. The experimental results using a small car show the good accuracy and performance of this system.

Obstacle detection using Virtual Disparity Image for non-flat road

The driving support is one of most important research area in intelligent transport system (ITS). Moreover, obstacle extraction system is one of most important system. In our previous report, we proposed an obstacle extraction method using stereovision system. In this system, traditional ldquov-disparityrdquo approach was extended to more flexible system by using virtual disparity image. Hereby obstacles can be extracted even if the vehicle has large roll movement. However, our system has still problem when a road shape cannot be approximated as a flat plane. In this paper, we propose road shape recognition method using dynamic programming (DP) and our method is extended to a new method suitable for a non-flat road.

A new method of position and heading measurement of ground vehicle by use of laser and corner cubes

This paper proposes an experimental system of position and heading finding of the ground vehicle by use of the laser and the corner cube prisms. This system is composed of; 1) three corner cubes are set on three reference points, and their co-ordinates are known previously. 2) the laser beam scanner, the laser beam receiver, the scanning angle measuring apparatus, and the micro-processor are set on the ground vehicle. 3) position and heading of vehicle are determined from the positioning informations of three reference points known previously, and the angle data of them measured using this system on the vehicle. Further, our experimental results using our proto-type experimental system are presented. Simulation results reveal that the movement of vehicle introduces the angle and positional errors, and some comments on reduction of these errors are also mentioned with discussions.

Obstacle map generation using virtual disparity image

The driving support system is one of the most important research fields in intelligent transport system (ITS). In this paper, we address an obstacle maps generation method for driving support system. The stereovision system is the one of most suit sensor to recognize details of environment. On the other hand, a disparity image obtained by stereovision system has quite a lot of information. Therefore an efficient algorithm to analyze obtained disparity image is strongly demanded. If the road surface is extracted, obstacles can be easily extracted by evaluating whether one object touch on a road or not. In this paper, we propose a novel method to estimate three-dimensional road surface position by using virtual disparity image. Moreover, an obstacle extraction method is expressed.

Driver's Head Pose Measurement and Corner Center Detection

In this paper, we describe development of drivers head pose measurement and cornea center detection system. Similar researches have been performed so far. Most researches are based on feature point detection by the template matching. In general, the template matching has the weakness to the change in the expansion and contraction, rotation and brightness. To overcome these faults, three-dimensional shape alignment is introduced. Three-dimensional shape alignment is performed between drivers face model and shape data obtained in each time. Then, three-dimensional shapes are analyzed by stereovision. Moreover, shape alignment is performed by ICP registration. ICP registration can achieve high accuracy alignment, but needs huge computational effort, in general. To solve this problem, this paper introduces a reduction in volume of data based on pattern information in the image, coarse-to-fine search, and SIMD computing. Furthermore, this paper describes the cornea center estimation technique. At first, this technique extracts the eye region image from result of the head pose measurement. Afterward, the cornea center is estimated by recognition of eye contour and the ellipse fitting of cornea. It was confirmed by experiments that the proposed technique can measure in high accuracy, and the proposed technique is available in real environment

Obstacle map generation using Virtual Disparity Image for non-flat road

The driving support is one of most important research area in intelligent transport system (ITS). Moreover, obstacle extraction system is one of most important system. In our previous report, we proposed an obstacle extraction method using stereovision system. In this system, traditional ldquoV-disparityrdquo approach was extended to more flexible system by using virtual disparity image. Hereby obstacles can be extracted even if the vehicle has large roll movement. However, our system has still problem when a road shape cannot be approximated as a flat plane. In this paper, we propose road shape recognition method using dynamic programming (DP) and our method is extended to a new method suitable for a non-flat road.

Motion Measurement of Inflatable Tube from Video Images

This study is concerned with a method of the image measurement using video cameras to measure deploying behavior of inflatable tube in deployment experiments. This system measures the motion of the creases for folding on the inflatable tube. Moreover, the extended SNAKES technique with a structural model enables measurement with high accuracy. The image measurement is performed for the deploying behavior of the inflatable tube folded by the pattern called a pentalpha folding. First, to measure the deployingt behavior of an inflatable tube, the system with two cameras in the laboratory is developed. Image measurement is achieved with good accuracy by using synchronized cameras with small optical aberration and calibration with good accuracy. Next, a measurement system is developed for the deployment experiment of the inflatable tube in the microgravity environment using the aircraft parabolic flight. In the aircraft experiment, there were various restrictions, e.g. asynchronous six cameras with large optical aberration. In addition, calibration in the flight condition was not available. Using three sets of stereo cameras with six cameras and integrating the obtained images, we measure the deploying behavior of the entire tube after the difficulties on the image measurement are overcome. This paper reports on the result of the obtained image measurement.