Review of some advances and applications in real-time high-speed vision: Our views and experiences

The frame rate of conventional vision systems is restricted to the video signal formats(e.g., NTSC 30 fps and PAL 25 fps that are designed on the basis of the characteristics of the human eye, which implies that the processing speed of these systems i limited to the recognition speed of the human eye. However, there is a strong demand for real-time high-speed vision sensors in many application fields, such as factory automation, biomedicine, and robotics, where high-speed operations are carried out. Thes high-speed operations can be tracked and inspected by using high-speed vision systems with intelligent sensors that work at hundred of Hertz or more, especially when the operation is difficult to observe with the human eye. This paper reviews advances in developing real-time high speed vision systems and their applications in various fields, such as intelligent logging systems, vibration dynamic sensing, vision-based mechanical control, three-dimensional measurement/automated visual inspection, vision-based human interface and biomedical applications.     

Generalized measuring-worm algorithm: high-accuracy mapping and movement via cooperating swarm robots

Recently, many extensive studies have been conducted on robot control via self-positioning estimation techniques. In the simultaneous localization and mapping (SLAM) method, which is one approach to self-positioning estimation, robots generally use both autonomous position information from internal sensors and observed information on external landmarks. SLAM can yield higher accuracy positioning estimations depending on the number of landmarks; however, this technique involves a degree of uncertainty and has a high computational cost, because it utilizes image processing to detect and recognize landmarks. To overcome this problem, we propose a state-of-the-art method called a generalized measuring-worm (GMW) algorithm for map creation and position estimation, which uses multiple cooperating robots that serve as moving landmarks for each other. This approach allows problems of uncertainty and computational cost to be overcome, because a robot must find only a simple two-dimensional marker rather than feature-point landmarks. In the GMW method, the robots are given a two-dimensional marker of known shape and size and use a front-positioned camera to determine the marker distance and direction. The robots use this information to estimate each other’s positions and to calibrate their movement. To evaluate the proposed method experimentally, we fabricated two real robots and observed their behavior in an indoor environment. The experimental results revealed that the distance measurement and control error could be reduced to less than 3 %.     

Gain‐Scheduled Control via Switching of LTI Controllers and State Reset

This paper proposes a synthesis method of gain‐scheduled control systems that switch linear time‐invariant controllers according to hysteresis of the scheduling parameter. Stability and L₂‐gain analysis and synthesis methods for switched systems are applied to the switched gain‐scheduled control synthesis using reset of the controller state, where also the reset law is computed via linear matrix inequalities (LMIs). In addition to optimization of an upper bound of L₂‐gain, we reduce jumps of control input via an auxiliary optimization. Numerical examples are presented to illustrate the switched gain‐scheduled controller.     

500-fps face tracking system

In this paper, we propose a high-speed vision system that can be applied to real-time face tracking at 500 fps using GPU acceleration of a boosting-based face tracking algorithm. By assuming a small image displacement between frames, which is a property of high-frame rate vision, we develop an improved boosting-based face tracking algorithm for fast face tracking by enhancing the Viola–Jones face detector. In the improved algorithm, face detection can be efficiently accelerated by reducing the number of window searches for Haar-like features, and the tracked face pattern can be localized pixel-wise even when the window is sparsely scanned for a larger face pattern by introducing skin color extraction in the boosting-based face detector. The improved boosting-based face tracking algorithm is implemented on a GPU-based high-speed vision platform, and face tracking can be executed in real time at 500 fps for an 8-bit color image of 512 × 512 pixels. In order to verify the effectiveness of the developed face tracking system, we install it on a two-axis mechanical active vision system and perform several experiments for tracking face patterns.     

Microscopic image restoration based on tensor factorization of rotated patches

In microscopic image processing for analyzing biological objects, structural characters of objects such as symmetry and orientation can be used as a prior knowledge to improve the results. In this study, we incorporated filamentous local structures of neurons into a statistical model of image patches and then devised an image processing method based on tensor factorization with image patch rotation. Tensor factorization enabled us to incorporate correlation structure between neighboring pixels, and patch rotation helped us obtain image bases that well reproduce filamentous structures of neurons. We applied the proposed model to a microscopic image and found significant improvement in image restoration performance over existing methods, even with smaller number of bases.     

control with limited communication and message losses

We propose an H^∞ approach to a remote control problem where the communication is constrained due to the use of a shared channel. The controller employs a periodic time sequencing scheme for message transmissions from multiple sensors and to multiple actuators of the system. It further takes into account the information on the random message losses that occur in the channel. An exact characterization for controller synthesis is obtained and is stated in terms of linear matrix inequalities. Furthermore, an analysis on the loss probabilities of the messages to accomplish stabilization is carried out. The results are illustrated through a numerical example.     

Anode‐voltage‐control circuit for compensation of luminance deterioration

Abstract— An external driving circuit that has realized long lifetime, power‐consumption control, and peak luminance for organic light‐emitting diode (OLED) displays have been developed. This circuit realizes an effective method for constant‐anode‐voltage (CV) driving refered to as clamped inverter (CI) driving. The feature of CV driving is to achieve low‐power consumption compared with constant‐anode‐current (CC) driving and to control the power consumption and peak luminance according to the image because display luminance can be easily changed by controlling the anode voltage. On the other hand, CV driving has the problem that luminance deterioration appears to be serious compared with that of CC driving because the current of the OLED element decreases according to usage time. To cope with this, a lifetime compensation circuit that has increased the anode voltage so that it compensates for the luminance deterioration has been developed. This circuit can compensate not only the decrease in current but also the decrease in luminance at a constant current that CC driving cannot. However, increasing the anode voltage causes an increase in stress on the OLED element. The influence of stress on OLED lifetime was verified. As a result, it was confirmed that this circuit can extend the lifetime by 32% even if the anode voltage is increased, causing stress on the OLED structure.     

Generating function of color information detection using genetic programming

This article proposes a function for color information detection using genetic programming (GP). In image-processing, object detection is one of the important processes. In cases where the object has a complex color domain, detection becomes more difficult. We generated a detection function for a complex color domain by using GP. The detection function deals with one pixel of an input image, and it obtains an output image by processing for all pixels. We aimed at a reduction in the time taken by a human to consider an image-processing system design. We applied the generation of GP to detect a target color region in actual images. The results show that the detection function has sufficient ability for these detections.