Gu Fang

Human Object Recognition Using Colour and Depth Information from an RGB-D Kinect Sensor

Human object recognition and tracking is important in robotics and automation. The Kinect sensor and its SDK have provided a reliable human tracking solution where a constant line of sight is maintained. However, if the human object is lost from sight during the tracking, the existing method cannot recover and resume tracking the previous object correctly. In this paper, a human recognition method is developed based on colour and depth information that is provided from any RGB-D sensor. In particular, the method firstly introduces a mask based on the depth information of the sensor to segment the shirt from the image (shirt segmentation); it then extracts the colour information of the shirt for recognition (shirt recognition). As the shirt segmentation is only based on depth information, it is light invariant compared to colour-based segmentation methods. The proposed colour recognition method introduces a confidence-based ruling method to classify matches. The proposed shirt segmentation and colour recognition method is tested using a variety of shirts with the tracked human at standstill or moving in varying lighting conditions. Experiments show that the method can recognize shirts of varying colours and patterns robustly.

Evolutionary particle filter: re-sampling from the genetic algorithm perspective

The sample impoverishment problem in particle filters is investigated from the perspective of genetic algorithms. The contribution of this paper is in the proposal of a hybrid technique to mitigate sample impoverishment such that the number of particles required and hence the computation complexities are reduced. Studies are conducted through the use of Chebyshev inequality for the number of particles required. The relationship between the number of particles and the time for impoverishment is examined by considering the takeover phenomena as found in genetic algorithms. It is revealed that the sample impoverishment problem is caused by the resampling scheme in implementing the particle filter with a finite number of particles. The use of uniform or roulette-wheel sampling also contributes to the problem. Crossover operators from genetic algorithms are adopted to tackle the finite particle problem by re-defining or re-supplying impoverished particles during filter iterations. Effectiveness of the proposed approach is demonstrated by simulations for a monobot simultaneous localization and mapping application.

Contrast Enhancement and Intensity Preservation for Gray-Level Images Using Multiobjective Particle Swarm Optimization

The contrast enhancement of gray-level digital images is considered in this paper. In particular, the mean image intensity is preserved while the contrast is enhanced. This provides better viewing consistence and effectiveness. The contrast enhancement is achieved by maximizing the information content carried in the image via a continuous intensity transform function. The preservation of image intensity is obtained by applying gamma-correction on the images. Since there is always a trade-off between the requirements for the enhancement of contrast and preservation of intensity, an improved multiobjective particle swarm optimization procedure is proposed to resolve this contradiction, making use of its flexible algorithmic structure. The effectiveness of the proposed approach is illustrated by a number of images including the benchmarks and an image sequence captured from a mobile robot in an indoor environment.

Application of artificial neural networks in regional flood frequency analysis: a case study for Australia

Regional flood frequency analysis (RFFA) is widely used in practice to estimate flood quantiles in ungauged catchments. Most commonly adopted RFFA methods such as quantile regression technique (QRT) assume a log-linear relationship between the dependent and a set of predictor variables. As non-linear models and universal approximators, artificial neural networks (ANN) have been widely adopted in rainfall runoff modeling and hydrologic forecasting, but there have been relatively few studies involving the application of ANN to RFFA for estimating flood quantiles in ungauged catchments. This paper thus focuses on the development and testing of an ANN-based RFFA model using an extensive Australian database consisting of 452 gauged catchments. Based on an independent testing, it has been found that ANN-based RFFA model with only two predictor variables can provide flood quantile estimates that are more accurate than the traditional QRT. Seven different regions have been compared with the ANN-based RFFA model and it has been shown that when the data from all the eastern Australian states are combined together to form a single region, the ANN presents the best performing RFFA model. This indicates that a relatively larger dataset is better suited for successful training and testing of the ANN-based RFFA models.

Simultaneous image color correction and enhancement using particle swarm optimization

Color images captured under various environments are often not ready to deliver the desired quality due to adverse effects caused by uncontrollable illumination settings. In particular, when the illuminate color is not known a priori, the colors of the objects may not be faithfully reproduced and thus impose difficulties in subsequent image processing operations. Color correction thus becomes a very important pre-processing procedure where the goal is to produce an image as if it is captured under uniform chromatic illumination. On the other hand, conventional color correction algorithms using linear gain adjustments focus only on color manipulations and may not convey the maximum information contained in the image. This challenge can be posed as a multi-objective optimization problem that simultaneously corrects the undesirable effect of illumination color cast while recovering the information conveyed from the scene. A variation of the particle swarm optimization algorithm is further developed in the multi-objective optimization perspective that results in a solution achieving a desirable color balance and an adequate delivery of information. Experiments are conducted using a collection of color images of natural objects that were captured under different lighting conditions. Results have shown that the proposed method is capable of delivering images with higher quality.

Automatic Fuzzy Membership Function Tuning Using the Particle Swarm Optimization

Fuzzy logic controllers (FLCs) are developed to exploit human expert knowledge in designing control systems. While the fuzzy rules are relatively easy to obtain, fuzzy membership function (MF) tuning could be a time consuming exercise. In this paper the particle swarm optimization technique is employed to automatically tune the MFs of a Mamdani-type of fuzzy controller. The effectiveness of the proposed controller is demonstrated by the control performance of such an FLC of a nonlinear water tank system. The results are compared favourably to a PSO tuned PID controller.

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.

Gradient-guided color image contrast and saturation enhancement

Digital color images are capable of presenting hue, saturation, and brightness perceptions. Therefore, quality improvement of color images should be taken into account to enhance all three stimuli. An effective method is proposed that aims at enriching the colorfulness, vividness, and contrast of color images simultaneously. In this method, color correction based on magnitude stretching is carried out first, image enhancement is then derived from an intensity-guided operation that concurrently improves the contrast and saturation qualities. Furthermore, the proposed methodology mitigates the heavy computational burden arising from the need to transform the source color space into an alternative color space in conventional approaches. Experiments had been conducted using a collection of real-world images captured under various environmental conditions. Image quality improvements were observed both from subjective viewing and quantitative evaluation metrics in colorfulness, saturation, and contrast.

A robust algorithm for weld seam extraction based on prior knowledge of weld seam

– This paper aims to develop a method to extract the weld seam from the welding image., – The initial step is to set the window for the region of the weld seam. Filter and edge‐operator are then applied to acquire edges of images. Based on the prior knowledge about characteristics of the weld seam, a series of routines is proposed to recognize the seam edges and calculate the seam representation., – The proposed method can be used to extract seams of different deviations from noise‐polluted images efficiently. Besides, the method is low time‐consuming and quick enough for real time processing., – Weld seam extraction is the key problem in passive vision based seam tracking technology. The proposed method can extract the weld seam even when the image is noisy, and it is quick enough to be applied in seam tracking technology. The method is expected to improve seam tracking results., – A useful method is developed for weld seam extraction from the noise‐polluted image based on prior knowledge of weld seam. The method is robust and quick enough for real time processing.

Effect of Color Space on Color Image Segmentation

A study of color image segmentation with its dependence on color space representation is presented. Segmentation has been one of the basic procedures in image processing. Because of the three-fold increase in color signal dimension as compared to black-and-white images, an advantage resulting from the choice of color space representation could be taken to enhance the performances of processes such as segmentation and feature matching. However, the choice of a particular color space is still largely application dependent. This work attempts to study a number of popular color space schemes on the basis of the maximum information that the space is able to convey to the segmentation process. Thus, a reduction in the complexity of the segmentation procedure is achievable when it is operating on a single color space domain. The amount of information contained in the segmented objects is adopted as a measure to determine the segmentation rule. Several aerial images over planted fields are employed in experiments and their satisfactory segmentation results are used to conclude the study.