High-speed Vision Research Articles

1A1-D06 高速ビジョンを用いたチャンバラロボットの開発(アミューズメント・エンタテイナーロボット)

1A1-D06 高速ビジョンを用いたチャンバラロボットの開発(アミューズメント・エンタテイナーロボット)

Evaluation of 3D Surface Roughness Parameters of EDM Components Using Vision System

Surface roughness evaluation is very important for many fundamental problems such as friction, contact deformation, tightness of contact joints positional accuracy etc. Many techniques have been developed for measuring surface finish ranging from the simple touch comparator to sophisticated optical techniques. In recent years, the advent of high-speed general-purpose digital computers and vision systems has made image analysis easier and more flexible. Unlike the stylus instruments, computer vision systems have the advantages of being non-contact and are capable of measuring an area from the surface rather than a single line. A vision system is considered relatively cheap, fast and suitable for automation.Work pieces are prepared with varied roughness using manufacturing process of EDM and subjected to different machining parameters such as variable current and voltage. The proposed method used vision system. Vision system consists of a CCD camera, frame grabber, advanced image processing card and a high end computer. The surface images are grabbed using CCD camera and then transferred to the computer memory through frame grabber. An image processing algorithm is prepared using MATLAB. The surface roughness parameter values (3D) obtained by Vision system are then compared with those obtained by Optical method. Strong correlation is obtained between the vision roughness and optical roughness parameters. Hence the proposed method can be used in the assessment of 3D surface finish. The complete analysis of results is presented in this work.

S1130205 ヒトとのコミュニケーションを意識したロボットハンド機構の研究([S113-02]ヒューマン・マシン・インターフェース設計(2),機素潤滑設計部門)

In this paper we develop a janken(stone-scissors-paper)robot as one example of human-machine interface systems. Human being plays one of stone, paper and scissors at the timing of one, two, three, go! According the timing, the the robot hand plays one of stone, paper and scissors. In this system we must develop 1) the high-speed vision system of recognition about position and shape of human hand, 2) the high-speed robot hand playing as same speed as human hand. But a high speed vision system already have develop in few previous study. In this paper we develop robot hand as noted above 2). From some experiments, the preproduction robot hand can play one of stone, paper and scissors in 30[ms]. So, we plan to set up prototypes at university festival this autumn to see whether people like the idea.

高速ビジョンを用いた細胞マニピュレーション

高速ビジョンを用いた細胞マニピュレーション

高速ビジョンのロボット応用

高速ビジョンのロボット応用

高速ビジョンのユーザインタフェース応用

高速ビジョンのユーザインタフェース応用

高速ビジョンの応用展開

高速ビジョンの応用展開

3P2-M02 ネットワーク型高速ビジョンシステムのフレーム同期(ネットワークロボティクス)

This paper presents a master-slave frame synchronization scheme for networked high-speed vision systems. In the system, multiple 1,000-frames-per-second (fps) cameras are connected via Ethernet. By referring to precise shutter timestamps at the maser camera, slave cameras can synchronize the shutter to the master with errors significantly smaller than the network delay.

「高速ビジョンの応用展開」特集について

「高速ビジョンの応用展開」特集について

Fast Aerial Video Stitching

The highly efficient and robust stitching of aerial video captured by unmanned aerial vehicles (UAVs) is a challenging problem in the field of robot vision. Existing commercial image stitching systems have seen success with offline stitching tasks, but they cannot guarantee high-speed performance when dealing with online aerial video sequences. In this paper, we present a novel system which has an unique ability to stitch high-frame rate aerial video at a speed of 150 frames per second (FPS). In addition, rather than using a high-speed vision platform such as FPGA or CUDA, our system is running on a normal personal computer. To achieve this, after the careful comparison of the existing invariant features, we choose the FAST corner and binary descriptor for efficient feature extraction and representation, and present a spatial and temporal coherent filter to fuse the UAV motion information into the feature matching. The proposed filter can remove the majority of feature correspondence outliers and significantly increase the speed of robust feature matching by up to 20 times. To achieve a balance between robustness and efficiency, a dynamic key frame-based stitching framework is used to reduce the accumulation errors. Extensive experiments on challenging UAV datasets demonstrate that our approach can break through the speed limitation and generate an accurate stitching image for aerial video stitching tasks.

高速ビジョンのダイナミックセンシング応用

高速ビジョンのダイナミックセンシング応用

Visual Measurement of the Racket Trajectory in Spinning Ball Striking for Table Tennis Player

A high-speed monocular vision system is established to track the racket trajectory for estimating the spinning ball initiated by a human. A new fast and robust method is proposed to extract the feature sequence of a racket's pose during the process of striking. Considering the complexity of the working environment and fast movement of the racket, a novel corner extraction algorithm with good robustness and high efficiency is presented, which mainly consists of two parts, i.e., target segmentation and line detection. Then PnP-based algorithm is adopted to get the rough pose of the racket, which is then optimized by orthogonal iteration algorithm to guarantee the orthogonality of the racket's orientation matrix. In order to classify the spinning mode of the ball with a higher accuracy, the racket's movement is represented by the sequence of normal vector of the racket's surface. Experiments are thoroughly conducted to verify the effectiveness of the proposed method.

A Mixed Noise Filtering Algorithm for High-Speed Sequence Image Processing

t is a effective means by using high-speed vision to locate mobile targets. Under the circumstance of high frame rate and high sensitivity (300Hz), in addition to the Gaussian noise and impulse noise, the image quality is also influenced by atmospheric instability, and it is mainly expressed as Gaussian noise. An improved adaptive threshold weighted mean (IATWM) de-noising algorithm is proposed in this paper. According to the characteristics of impulse noise, the algorithm is able to obtain the threshold adaptively and separate the impulse noise. Then, the weighted median filtering algorithm is used to remove the impulse noise. And the improved weighted average filter algorithm is adopted to remove the Gaussian noise for graphics with Gaussian noise. The algorithm could deal with the Gaussian noise and impulse noise separately, avoiding the weaken handling for the parts not subject to pixels pollution of the impulse noise. The experimental results show that the processing result of the algorithm is able to retain the image details, superior to the traditional filtering algorithms and MTM algorithm. In addition, the algorithm provides an effective way to eliminate the mixed noise, along with a good effect on the high-speed sequence image processing.

A Real-Time Microscopic PIV System Using Frame Straddling High-Frame-Rate Vision

In this paper, we propose a novel concept of realtime microscopic particle image velocimetry (PIV) for apparent high-speed microchannel flows in lab-on-achip (LOC). We introduce a frame-straddling dualcamera high-speed vision system that synchronizes two different camera inputs for the same camera view with a submicrosecond time delay. In order to improve upper and lower limits of measurable velocity in microchannel flow observation, we designed an improved gradient-based optical flow algorithm that adaptively selects a pair of images in the optimal frame-straddling time between the two camera inputs based on the amplitude of the estimated optical flow. This avoids large image displacement between frames that often generates serious errors in optical flow estimation. Our method is implemented using software on a frame-straddling dual-camera high-speed vision platform that captures real-time video and processes 512 × 512 pixel images at 2000 fps for the two camera heads and controls the frame-straddling time delay between them from 0 to 0.25 ms with 9.9 ns step. Our microscopic PIV system with frame-straddling dualcamera high-speed vision simultaneously estimates the velocity distribution of high-speed microchannel flow at 1 × 108pixel/s or more. Results of experiments using real microscopic flows on microchannels thousands of µm wide on LOCs verify the performance of the real-time microscopic PIV system we developed.

Fast Tracking System for Multi-colored Pie-shaped Markers

In this study, we develop a real-time high-speed color vision system to track multi-colored pie-shaped markers in 512 × 512 images at 2000 fps. Our color vision system has six cell-based labeling circuits that can calculate the 0th and 1st moment features of color-labeled regions during a single scan of a 512 × 512 image divided into 4096 8 × 8 cells. Our system examines the geometric distribution of five color regions in each pie-shaped marker using their 0th and 1st moment features, and it can simultaneously extract the unique marker codes, locations, and orientations of multiple pie-shaped markers in a 512 × 512 image at 2000 fps. To evaluate the performance of our system, we performed several experiments to track multi-colored pie-shaped markers printed on high-speed rotating objects.

Optimization of the Feedback and Control Module for Light Source of High-Speed Vision Inspection System

The situations of insufficient or too much exposure of lights often happen in high-speed vision inspection system. In order to improve the ability to adapt to environment, the feedback and control system is used. If we use the processing method of integral threshold value, the control of light source wont work. Besides, the former feedback system has the stoboflash problem, so optimization design is needed. A new feedback signal extraction method is put forward and the program of source control is optimized, and the adaptability of the diction system to the change of the environment light is improved, it works out the function of controlling the LED light source automatically and steadily under the effects of environment light and the problem of stroboflash.

Efficient communication support in predictable heterogeneous MPSoC designs for streaming applications

Streaming applications are an important class of applications in emerging embedded systems such as smart camera network, unmanned vehicles, and industrial printing. These applications are usually very computationally intensive and have real-time constraints. To meet the increasing demand for performance and efficiency in these applications, the use of application specific IP cores in heterogeneous Multi-Processor System-on-Chips (MPSoCs) becomes inevitable. However, two of the key challenges in integrating these IP cores into MPSoCs are (i) how to properly handle inter-core communication; (ii) how to map streaming applications in an efficient and predictable way. In this paper, we first present a predictable high-performance communication assist (CA) that helps to tackle these design challenges. The proposed CA has zero throughput overhead, negligible latency overhead, and significantly less resource usage compared to existing CA designs. The proposed CA also provides a unified abstract interface for both processors and accelerator IP cores with flexible data access support. Based on the proposed CA design, we present a predictable heterogeneous multi-processor platform template for streaming applications. The template is used in a predictable design flow that uses Synchronous Data Flow (SDF) graphs for design time analysis. An accurate SDF model of our CA is introduced, enabling the mapping of applications onto heterogeneous MPSoCs in an efficient and predictable way. As a case study, we map the complete high-speed vision processing pipeline of an industrial application, Organic Light Emitting Diode (OLED) screen printing, onto one instance of the proposed platform. The result demonstrates that system design and analysis effort is greatly reduced with the proposed CA-based design flow.

Frame Synchronization of High-Speed Vision Sensors with Respect to Temporally Encoded Illumination in Highly Dynamic Environments

The authors propose a Manchester Encoding inspired illumination modulation strategy to properly index the temporally-aligned vision frames, which are successfully synchronized by the LED reference signal. Based on signal normalization, Manchester Encoded reference signals carry temporal information owing to serial communication and thus can timestamp the output vision frame. Both simulated and experimental results show satisfactory robustness to various disturbances, such as dynamic targets, fluctuant optical intensity, and unfixed cameras, etc. The 1,000 Hz vision sensor is locked to 500 Hz temporally modulated LED illumination with only 24 μs jitters. This result is believed to be applicable to low-cost wireless vision sensor network.

滑り摩擦非対称性を利用した動的2脚移動

In this paper, dynamic biped locomotion is considered with the goal of achieving fast and dexterous leg motion. We propose a new movement principle for legged robots, which produces propulsive force using frictional asymmetry. The dynamic locomotion consists of sliding motion based on the kinematic constraint and jumping motion which enables to keep the maximum horizontal velocity. The dynamics of the 2-DOF biped robot is analyzed to obtain motion characteristics for developing a motion strategy. Experimental results are also shown in which a 2-DOF biped robot takes fast short steps repetitively with compensation of the landing time by high-speed vision.

A Programmable High Speed Vision System with Superscalar PE and Its Parallel Computing Language

Pixel-parallel PE and SIMD architectures are widely used in high-speed image processing to enhance computing power. With fully exploiting the data level parallelism of low- and middle-level image processing, SIMD architecture is able to finish great amount of computation with much less instruction cycle thus satisfy the high-speed system requirement. The main computation parts in those SIMD image processing hardware is known as PE (processing element) and it is responsible for transferring, storing and processing the image data. This paper describes a high-speed vision system with superscalar PE to enhance system performance and its dedicated parallel computing language specifically devel-oped for this vision system. The vision system can achieve motion detection at more than 2000fps and face detection at more than 100 fps which overwhelms some general serial CPUs in the same applications.