Author name cluster

Hiroshi Murase

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

9 papers

2 author rows

ICRA Conference 2020 Conference Paper

Hybrid Localization using Model- and Learning-Based Methods: Fusion of Monte Carlo and E2E Localizations via Importance Sampling

Naoki Akai
Takatsugu Hirayama
Hiroshi Murase

This paper proposes a hybrid localization method that fuses Monte Carlo localization (MCL) and convolutional neural network (CNN)-based end-to-end (E2E) localization. MCL is based on particle filter and requires proposal distributions to sample the particles. The proposal distribution is generally predicted using a motion model. However, because the motion model cannot handle unanticipated errors, the predicted distribution is sometimes inaccurate. The use of other ideal proposal distributions, such as the measurement model, can improve robustness against such unanticipated errors. This technique is called importance sampling (IS). However, it is difficult to sample the particles from such ideal distributions because they are not represented in the closed form. Recent works have proved that CNNs with dropout layers represent the posterior distributions over their outputs conditioned on the inputs and the CNN predictions are equivalent to sampling the outputs from the posterior. Therefore, the proposed method utilizes a CNN to sample the particles and fuses them with MCL via IS. Consequently, the advantages of both MCL and E2E localization can be simultaneously leveraged while preventing their disadvantages. Experiments demonstrate that the proposed method can smoothly estimate the robot pose, similar to the model-based method, and quickly re-localize it from the failures, similar to the learning-based method.

Details

IROS Conference 2018 Conference Paper

Mobile Robot Localization Considering Class of Sensor Observations

Naoki Akai
Luis Yoichi Morales Saiki
Hiroshi Murase

Localization robustness against environment dynamics is significant for robots to achieve autonomous navigation in unmodified environments. A basic method of improving the robustness of a robot is considering the sensor observations obtained from mapped obstacles and using them for localizing the robot's pose. This study proposes an observation model that considers the class of sensor observations, where “class” categorizes the sensor observations as those obtained from mapped and unmapped obstacles. In the proposed approach, the robot's pose and the class are estimated simultaneously. As a result, the robot's pose can be localized using the sensor observations obtained only from mapped obstacles. First, we evaluated the performance of the proposed approach using simulations. Further, we tested the proposed approach in a real-world mobile robot navigation competition, called “Tsukuba Challenge, ” held in Japan. The robustness and effectiveness of the proposed approach against environment dynamics were verified from the experimental results.

Details

IROS Conference 2018 Conference Paper

Personal Mobility Vehicle Autonomous Navigation Through Pedestrian Flow: A Data Driven Approach for Parameter Extraction

Luis Yoichi Morales Saiki
Naoki Akai
Hiroshi Murase

In this paper we present a data driven approach for safe and smooth autonomous navigation of a personal mobility vehicle (PMV) when facing moving obstacles such as people and bicycles in public pedestrian paths. In a period of three months, data from five different persons driving the robotic PMV in an outdoor environment while facing pedestrians were collected. 2465 clean tracks around the vehicle together with PMVs trajectories were collected. We performed an analysis of the parameters involved for human-driven smooth navigation. Relevant parameters regarding PMV-Human interaction included distance to moving objects, passing side and velocities. Moreover, data suggests the existence of a social navigational distance for the PWv. For autonomous navigation we implemented a Frenet planner to achieve safe and smooth navigation for the passenger and pedestrians around. Experimental results in real pedestrian paths show that the PMV is capable of smoothly following its path while facing pedestrians and bicycles.

Details

IROS Conference 2015 Conference Paper

Fast 3D edge detection by using decision tree from depth image

Masaya Kaneko
Takahiro Hasegawa
Yuji Yamauchi
Takayoshi Yamashita
Hironobu Fujiyoshi
Hiroshi Murase

T3D edge detection from a depth image is an important technique of 3D object recognition in preprocessing. There are three types of 3D edges in a depth image called jump, convex roof, and concave roof edges. Conventional 3D edge detection based on ring operators has been proposed. The conventional ring operator can detect three types of 3D edges by classifying the response of Fourier transforms. Since the conventional method needs to apply Fourier transforms to all pixels of a depth image, real-time processing cannot be done due to high computational cost. Therefore, this paper presents a fast and reliable method of detecting three types of 3D edges by using a decision tree. The decision tree is trained under supervised learning from numerous synthesized depth images and labels by capturing depth relations between candidate pixels and pixels on a ring operator to classify 3D edges. The experimental results revealed that the proposed method has 25 times faster than the conventional method. This paper also presents some examples of 3D line and 3D convex corner detection based on results obtained with the proposed method.

Details

IJCAI Conference 1997 Conference Paper

A Music Stream Segregation System Based on Adaptive Multi-Agents

Kunio Kashino
Hiroshi Murase

A principal problem of auditory scene analysis is stream segregation: decomposing an input acoustic signal into signals of individual sound sources included in the input. While existing signal processing algorithms cannot properly solve this inverse problem, a multiagent-based architecture has been considered to be a promising methodology in its modularity and scalability. However, most attempts made so far depend on subjectively defined rules to deal with variability of sounds. Here we propose a quantitatively principled architecture in agent interaction by formulating the problem as least-squares optimization. In this architecture, adaptation of the agents is the essential idea. We have developed two kinds of processing to realize adaptivity: template filtering and phase tracking. These mechanisms enable each agent to optimally, in the least-squares sense, track the individual sound. As an example application of the proposed architecture, we have built a music recognition system that recognizes instrument names and pitches of the notes included in ensemble music performances. Experimental results show that these adaptive mechanisms significantly improve the recognition accuracy.

PDF

ICRA Conference 1996 Conference Paper

Dimensionality of illumination in appearance matching

Shree K. Nayar
Hiroshi Murase

Appearance matching was recently demonstrated as a robust and efficient approach to 3D object recognition and pose estimation. Each object is represented as a continuous appearance manifold in a low-dimensional subspace parametrized by object pose and illumination direction. Here, the structural properties of appearance manifolds are analyzed with the aim of making appearance representation efficient in off-line computation, storage requirements, and online recognition time. In particular, the effect of illumination on the structure of the appearance manifold is studied. It is shown that for an ideal diffused surface of arbitrary texture, the appearance manifold is linear and three dimensional. This enables the construction of the entire illumination manifold from just three images of the object taken using linearly independent light sources. This result is shown to hold even for illumination by multiple light sources and for concave surfaces that exhibit inter-reflections. Finally, a simple but efficient algorithm is presented that uses just three manifold points for recognizing images taken under novel illuminations.

Details

ICRA Conference 1996 Conference Paper

Real-time 100 object recognition system

Shree K. Nayar
Sameer A. Nene
Hiroshi Murase

A real-time vision system is described that can recognize 100 complex three-dimensional objects. In contrast to traditional strategies that rely on object geometry and local image features, the present system is founded on the concept of appearance matching. Appearance manifolds of the 100 objects were automatically learned using a computer-controlled turntable. The entire learning process was completed in 1 day. A recognition loop has been implemented that performs scene change detection, image segmentation, region normalizations, and appearance matching, in less than 1 second. The hardware used by the recognition system includes no more than a CCD color camera and a workstation. The real-time capability and interactive nature of the system have allowed numerous observers to test its performance. To quantify performance, we have conducted controlled experiments on recognition and pose estimation. The recognition rate was found to be 100% and object pose was estimated with a mean absolute error of 2. 02 degrees and standard deviation of 1. 67 degrees.

Details

ICRA Conference 1994 Conference Paper

Learning, Positioning, and Tracking Visual Appearance

Shree K. Nayar
Hiroshi Murase
Sameer A. Nene

The problem of vision-based robot positioning and tracking is addressed. A general learning algorithm is presented for determining the mapping between robot position and object appearance. The robot is first moved through several displacements with respect to its desired position, and a large set of object images is acquired. This image set is compressed using principal component analysis to obtain a four-dimensional subspace. Variations in object images due to robot displacements are represented as a compact parametrized manifold in the subspace. While positioning or tracking, errors in end-effector coordinates are efficiently computed from a single brightness image using the parametric manifold representation. The learning component enables accurate visual control without any prior hand-eye calibration. Several experiments have been conducted to demonstrate the practical feasibility of the proposed positioning/tracking approach and its relevance to industrial applications. >

Details

AAAI Conference 1993 Conference Paper

Learning Object Models from Appearance

Hiroshi Murase

We address the problem of automatically learning object models for recognition and pose estimation. In contrast to the traditional approach, we formulate the recognition problem as one of matching visual appearance rather than shape. The appearance of an object in a two-dimensional image depends on its shape, pose in the scene, reflectance properties, and the illumination conditions. While shape and reflectance are intrinsic properties of an object and are constant, pose and illumination vary from scene to scene. We present a new compact representation of object appearance that is parametrized by pose and illumination. For each object of interest, a large set of images is obtained by automatically varying pose and illumination. This large image set is compressed to obtain a low-dimensional subspace, called the eigenspace, in which the object is represented as a hypersurface. Given an unknown input image, the recognition system projects the image onto the eigenspace. The object is recognized based on the hypersurface it lies on. The exact position of the projection on the hypersurface determines the object’ s pose in the image. We have conducted experiments using several objects with complex appearance characteristics. These results suggest the proposed appearance representation to be a valuable variety of machine vision applications.

PDF Details