Dalong Wang

Visual impact enhancement via image histogram smoothing and continuous intensity relocation

Image contrast enhancement is a fundamental pre-processing stage in applications requiring image processing operations. Among revenues of available approaches, histogram equalization is a popular and attractive candidate method to produce resultant images of increased contrast. However, images obtained from canonical histogram equalization frequently suffer from the accompanying artefacts and give rises to uncomfortable viewing particularly in homogeneous regions. In this work, the problem is tackled using the histogram matching concept where the intensity histogram of the input image is matched to its smoothed version for contrast enhancement. Furthermore, homogeneous pixel intensities are randomly perturbed in order to reduce undesirable artefacts. The resultant image intensities are thus distributed over the available range and an increased image contrast is derived. Satisfactory results are obtained from a collection of benchmark images captured under different conditions to verify the effectiveness of the proposed approach.

Evaluating Performance of Multiple RRTs

This paper presents experimental results evaluating the performance of a new multiple rapidly-exploring random Tree (RRT) algorithm. RRTs are randomised planners especially adept at solving difficult, high-dimensional path planning problems. However, environments with low-connectivity due to the presence of obstacles can severely affect convergence. Multiple RRTs have been proposed as a means of addressing this issue, however, this approach can adversely affect computational efficiency. This paper introduces a new and simple method which takes advantage of the benefits of multiple trees, whilst ensuring the computational burden of maintaining them is minimised. Results indicate that multiple RRTs are able to reduce the logarithmic complexity of the search, most notably in environments with high obstacle densities.

A Variable Speed Force Field Method for Multi-Robot Collaboration

A novel force field (F2) method with variable speed for multi-robot motion planning and collaboration is presented in this paper. The basic concept of the F2 method is to generate a force field for every robot based on and continuously changing according to its status including traveling speed, dimension, priority, location and environmental factor, etc. The interactions among robots force fields and obstacles provide a natural way for collision avoidance and collaboration while robots are on their way to goals. Previous F2 method assumes that robots travel with constant speeds and can react instantly to the resultant force to change their orientations. Starting from a problematic situation brought out by this hypothesis, this paper remedies the F2 method by taking robots dynamics and kinematics characteristics into consideration. In the variable speed force field method (VSF2), a robot can change its own speed according to environment information and its own status. Simulations in a real indoor environment were carried out and demonstrated the feasibility and effectiveness of this method

A 3-dimensional force field method for robot collision avoidance in complex environments

This paper proposes a three-dimensional force field (3D-F 2 ) method for efficient motion planning and collision avoidance of a 6DOF manipulator in complex and dynamic environments while keeping the planned end-effector’s path and speed unchanged. The 3D-F 2 is defined as ellipsoid shapes covering selected links of a manipulator. When the manipulator moves and its ellipsoid force field approaches to an obstacle in a tolerant range, a repulsive force will be generated and considered in the robot kinematic and dynamic analyses. In infrastructure maintenance, spray-painting and sand-blasting operations require that the operating spot “moves” smoothly and continuously along planned path on a work surface at a constant speed, and allow changes in length and orientation of the spray/blasting stream. Thus, the stream is supposed to be another link and the end of stream performs as a spherical joint fixed on the target surface. Various simulations in a construction area show that the 3D-F 2 can retain the operating path and effectively avoid potential collisions.

A Force Field Method Based Multi-Robot Collaboration

A force field (F2) based multi-robot collaboration method is presented in this paper. In this method, a virtual force field is generated for every moving robot and continuously changing based on the robot status including its traveling speed, dimension, priority, location and environment, etc. The interactions among robots force fields and obstacles provide a natural way for collision avoidance and collaboration while robots are on their way to goals. In this paper, the definition of reaction force direction is modified to reduce robot orientation oscillations which occur when a robot approaches obstacles or other robots. Then the influence of task priority on motion planning and the problem of deadlock in multi-robot cases are discussed. Simulations in a real indoor environment were carried out and demonstrated the feasibility and effectiveness of this method

Gray world based color correction and intensity preservation for image enhancement

Images captured by digital cameras are vulnerable to quality degradations due to non-ideal illumination conditions such as dominated lighting source colors, where images so obtained may not faithfully reproduce the scene chromatics accurately. While it is a complicated process to control the scene illumination, color correction used as a post-processing procedure, is becoming an attractive solution. This research has developed an approach for color correction based on a modified implementation of the gray world assumption. The image color is adjusted by employing a gamma correction to satisfy the gray world assumption and avoid color saturation as encountered in the conventional approach. In order to further improve the image visual quality, an intensity preservation criterion is adopted as an additional means to produce the resultant image. With the normalization of intensity in accordance with the original image, an enhanced image both in color and intensity, is finally obtained. A collection of color images are used in an experiment to verify the proposed algorithm. Results have indicated that the proposed method is effective in producing enhanced images in the context of color enhancements.

Ranked Pareto Particle Swarm Optimization for Mobile Robot Motion Planning

The Force Field (F 2) method is a novel approach for multi-robot motion planning and coordination. The setting of parameters in the (F 2) method, noticeably, can affect its performance. In this research, we present the Ranked Pareto Particle Swarm Optimization (RPPSO) approach as an extension of the basic idea of Particle Swarm Optimization (PSO), which makes it capable of solving multiobjective optimization problems efficiently. In the RPPSO, particles are initiated randomly in the search space; these particles are then evaluated for their qualities with regard to all objectives. Those particles with highly-ranked qualities have preferences to enter the set of Global Best vectors, which stores many currently best solutions found by particles. Thus, particles in RPPSO will search towards many possible directions and the diversity among solutions is well preserved. Ideally, a set of optimal solutions will be found when the termination criterion is met. The effectiveness of the proposed RPPSO is verified in simulation studies. Satisfactory results are obtained for multiobjective optimization problems of multi-robot motion planning in challenging environments with obstacles.

A Cellular Automata approach for superpixel segmentation

This paper presents a novel Cellular Automata (CA) approach for image segmentation. We treat the image segmentation problem as cell merging in a cellular space constructed in the image plane. A cell is defined to be a pixel or a group of pixels with close RGB values. In each iteration, a cell checks the similarities between itself and its neighboring cells. Cells with similar properties are merged into large cells, which will eventually lead to high quality superpixels. The segmentation process is a trade-off between accuracy and computation cost. We have proved that the proposed approach is able to obtain satisfactory results efficiently while keeping image details.

A Subgoal-Guided Force Field Method for Robot Navigation

Motion planning and collision avoidance functionality are crucial attributes to the successful deployment of mobile robots. This research analyzes some shortcomings of the canonical F2 method and then presents subgoal-guided force-field (SGF2) method to mitigate these drawbacks. In the proposed approach, a robot identifies openings in an environment in front of itself on the basis of sensor data. The midpoints of these openings are determined and selected as subgoal candidates. A cost function is then utilized to evaluate their suitability. One subgoal is then chosen and used by the F2 method to generate a steering force which will drive the robot to the subgoal. The subgoal is continuously updated from realtime sensor data until the global goal is reached. Simulations are carried out to demonstrate the effectiveness of the proposed approach.

PSO-Tuned F 2 method for multi-robot navigation

The F (Force Field) method is a novel approach for multi-robot motion planning and collision avoidance. The setting of parameters is however vital to its performance. This paper presents an approach using Particle Swarm Optimization (PSO) to properly determine the control parameters for the F2 method. The goal of the optimization is to minimize the resultant path lengths. The approach presented in this paper can be used as a tool to obtain optimal parameters for various tasks before their execution. Simulations are carried out in various environments to show the feasibility of this approach.