Fenghui Yao

Extracting the trajectory of writing brush in Chinese character calligraphy

This paper describes the extraction of the trajectory of the writing brush in Chinese character calligraphy (CCC), based on image and curve processing techniques and the calligraphy knowledge. This trajectory is used in a CCC robot which is developed to inherit CCC techniques. In CCC, the writing styles can be roughly classified into five different styles-ancient, angular, block, semi-cursive, and cursive style. This paper is limited to discuss the trajectory extraction from the character image written in block style. Firstly, for a given Chinese character, its image patterns in block style are retrieved from CCC database which contains 29,456 characters written by different famous calligraphers in Chinese history. Then the image of the designated writing is thinned. The coordinates of the line passing the centers of each stroke are detected from the thinned image with aid of writing order information. These coordinates represent the thinned-center-line of the stroke (TCLS, for short). And then, TCLS is separated into several curve segments according the calligraphy knowledge. The trajectory of the writing brush is considered as B-spline curves determined by the points on curve segments. The trajectory and the pressure control information are sent to the CCC robot to imitate calligraphers behavior. The experiment results show that the proposed method obtains very good trajectories of the writing brush for CCC robot.

Nanosensor Data Processor in Quantum-Dot Cellular Automata

Quantum-dot cellular automata (QCA) is an attractive nanotechnology with the potential alterative to CMOS technology. QCA provides an interesting paradigm for faster speed, smaller size, and lower power consumption in comparison to transistor-based technology, in both communication and computation. This paper describes the design of a 4-bit multifunction nanosensor data processor (NSDP). The functions of NSDP contain (i) sending the preprocessed raw data to high-level processor, (ii) counting the number of the active majority gates, and (iii) generating the approximate sigmoid function. The whole system is designed and simulated with several different input data.

Painting brush control techniques in Chinese painting robot

This paper describes a Chinese painting robot (CP robot) that can be categorized as an art robot. The whole system consists of a robot arm, robot hand, Chinese brush, and system controller. In Chinese painting, the following four objects: bamboos, plum blossoms, chrysanthemums, and orchids are often used to practice painting techniques. This paper focuses on how to draw bamboos by a CP robot. When a bamboo drawing is presented, the CP robot decomposes the drawing into stems, joints, branches, and leaves. According to the drawing order information, the system controller creates the trajectory of the Chinese brush. The trajectory of the Chinese brush is considered as B-spline curves determined by the points included in the drawing order information. The trajectory and the pressure control information are sent to the CP robot to imitate painters behavior. The experiment results show that the proposed techniques are efficient for the CP robot to perform the fundamental drawing in Chinese painting.

Real-time multiple moving targets detection from airborne IR imagery by dynamic Gabor filter and dynamic Gaussian detector

This paper presents a robust approach to detect multiple moving targets from aerial infrared (IR) image sequences. The proposed novel method is based on dynamic Gabor filter and dynamic Gaussian detector. First, the motion induced by the airborne platform is modeled by parametric affine transformation and the IR video is stabilized by eliminating the background motion. A set of feature points are extracted and they are categorized into inliers and outliers. The inliers are used to estimate affine transformation parameters, and the outliers are used to localize moving targets. Then, a dynamic Gabor filter is employed to enhance the difference images for more accurate detection and localization of moving targets. The Gabor filters orientation is dynamically changed according to the orientation of optical flows. Next, the specular highlights generated by the dynamic Gabor filter are detected. The outliers and specular highlights are fused to indentify the moving targets. If a specular highlight lies in an outlier cluster, it corresponds to a target; otherwise, the dynamic Gaussian detector is employed to determine whether the specular highlight corresponds to a target. The detection speed is approximate 2 frames per second, which meets the real-time requirement of many target tracking systems.

Automatic concrete tunnel inspection robot system

This paper describes the development of an automatic concrete tunnel inspection system by an autonomous mobile robot. This work was motivated by the accidents in recent years that were caused by falling parts of the inner wall of concrete tunnels. This brought about serious damage to national property and led to the great concern throughout the whole society. Here, we proposed a non-destructive automatic tunnel inspection method. In this method, we aim to inspect the tunnel automatically and completely at high speed by using non-destructive sensors. For the non-destructive sensors, we employ 24 ultrasonic range sensors and six video cameras. These sensors are mounted on the same plane in the shape of a semi-ring. This ultrasonic range sensor video camera semi-ring is called a URS/VC semi-ring. This URS/VC semi-ring is mounted on an autonomous mobile robot to inspect the concrete tunnel. Experiment results show that this system can detect deformed inner walls at divisions of 14 mm when the robot moves at 20 mm/s.

Multiple moving target detection, tracking, and recognition from a moving observer

This paper describes an algorithm for multiple moving targets detection, tracking and recognition from a moving observer. When the camera is placed on a moving observer, the whole background of the scene appears to be moving and the actual motion of the targets must be distinguished from the background motion. To do this, an affine motion model between consecutive frames is estimated, and then moving targets can be extracted. Next, the target tracking employs a similarity measure which is based on the joint feature-spatial space. At last, the target recognition is performed by matching moving targets with target database. The average processing time is 680 ms per frame, which corresponds to a processing rate of 1.5 frames per second. The algorithm was tested on the Vivid datasets provided the Air Force Research Laboratory and experimental results show that this method is efficient and fast for real-time application.

Aerial image registration based on joint feature-spatial spaces, curve and template matching

Image registration has wide applications in remote sensing, medicine, cartography, and computer vision. This paper describes a method for aerial image registration, which is based on joint feature-spatial spaces, curve matching, and template matching. The entire algorithm consists of (i) segmentation and region representation, (ii) region matching based on joint feature-spatial space, (iii) transformation model estimation based on curve matching and template matching, and (iv) image transformation. Experiment results show the effectiveness of this algorithm.

Smart video surveillance for airborne platforms

This paper describes real-time computer vision algorithms for detection, identification, and tracking of moving targets in video streams generated by a moving airborne platform. Moving platforms cause instabilities in image acquisition due to factors such as disturbances and the ego-motion of the camera that distorts the actual motion of the moving targets. When the camera is mounted on a moving observer, the entire scene (background and targets) appears to be moving and the actual motion of the targets must be separated from the background motion. The motion of the airborne platform is modeled as affine transformation and its parameters are estimated using corresponding feature sets in consecutive images. After motion is compensated, the platform is considered as stationary and moving targets are detected accordingly. A number of tracking algorithms including particle filters, mean-shift, and connected component were implemented and compared. A cascaded boosted classifier with Haar wavelet feature extraction for moving target classification was developed and integrated with the recognition system that uses joint-feature spatial distribution. The integrated smart video surveillance system has been successfully tested using the Vivid Datasets provided by the Air Force Research Laboratory. The experimental results show that system can operate in real time and successfully detect, track, and identify multiple targets in the presence of partial occlusion.

Multi-source Airborne IR and Optical Image Fusion and Its Application to Target Detection

This paper describes the fusion of the airborne optical image and IR (infrared) image generated from a moving platform, and the target detection from the fused images. The proposed algorithm first detects the object from optical image and IR image, respectively. Then it performs the object mapping to determine parameters for image fusion. And then it fuses the optical image and IR image and detects the target from the fused images. The real-world videos generated from a helicopter are used to test this algorithm. The experiment results validate the proposed algorithm.

Trajectory generation of the writing–brush for a robot arm to inherit block–style Chinese character calligraphy techniques

This paper relates the trajectory generation of the writing-brush for a robot arm to inherit Chinese character calligraphy (CCC) techniques. First, to preserve the characters written by famous calligraphers in Chinese history, we constructed a CCC database which contains 29 456 characters written by different calligraphers in different styles (ancient, angular, block, semi-cursive and cursive style). With this CCC database, it is possible to search, restore and append the calligraphy writing for a specific character. Second, we mainly relate the inheritance of CCC. Because CCC is not a static thing, but a dynamic process of an activity which concerns a lot of complicated factors such as the pressure and speed control of the writing brush, how to write the start and end of strokes, etc., we propose to inherit this dynamic process by a robot. This paper is limited to discussing how to inherit the writing techniques for block-style calligraphy writing by a robot arm. The total number of Chinese characters is more than 800 000. These characters can be constructed by basic strokes. There are 28 different kinds of strokes used to construct all of these characters. The skeleton of a stroke is decided by the control points that exist within the stroke. The shape of a stroke is determined by the trajectory derived from the control points and the pressure to the writing brush. The control points for 28 strokes are given and the control techniques for a robot to write these strokes in block style are developed. At present, the robot can write any character in block style.