Dean Zhao

Automatic recognition vision system guided for apple harvesting robot

In apple harvesting robot, the first key part is the machine vision system, which is used to recognize and locate the apples. In this paper, the procedure on how to develop an automatic recognition vision system guided for apple harvesting robot, is proposed. We first use a color charge coupled device camera to capture apple images, and then utilize an industrial computer to process images for recognising fruit. Meanwhile, the vector median filter is applied to remove the color images noise of apple, and images segmentation method based on region growing and color feature is investigated. After that the color feature and shape feature of image are extract, a new classification algorithm based on support vector machine for apple recognition is introduced to improve recognition accuracy and efficiency. Finally, these procedures proposed have been tested on apple harvesting robot under natural conditions in September 2009, and showed a recognition success rate of approximately 89% and average recognition time of 352ms.

Real-valued DOA estimation for uniform linear array with unknown mutual coupling

In this paper, we propose a real-valued direction-of-arrival (DOA) estimation method for uniform linear arrays (ULAs) in the presence of unknown mutual coupling. By taking advantage of the special structure of the mutual coupling matrix for ULAs, the effect of mutual coupling is eliminated by the inherent mechanism of the proposed method. Moreover, the computational complexity is reduced by a factor of at least four after further performing a unitary transformation capable of converting a complex covariance matrix into a real one. We also investigate the performance loss due to the imperfect structure of the mutual coupling matrix under the NEC-2 code. Experimental results with respect to the NEC-2 code illustrate that our new method even outperforms a state-of-the-art method in the literature.

An optimized classification algorithm by BP neural network based on PLS and HCA

Due to some correlative or repetitive factors between features or samples with high dimension and large amount of sample data, when traditional back-propagation (BP) neural network is used to solve this classification problem, it will present a series of problems such as network structural redundancy, low learning efficiency, occupation of storage space, consumption of computing time, and so on. All of these problems will restrict the operating efficiency and classification precision of neural network. To avoid them, partial least squares (PLS) algorithm is used to reduce the feature dimension of original data into low-dimensional data as the input of BP neural network, so that it can simplify the structure and accelerate convergence, thus improving the training speed and operating efficiency. In order to improve the classification precision of BP neural network by using hierarchical cluster analysis (HCA), similar samples are put into a sub-class, and some different sub-classes can be obtained. For each sub-class, a different training session can be conducted to find a corresponding precision BP neural network model, and the simulation samples of different sub-classes can be recognized by the corresponding network model. In this paper, the theories of PLS and HCA are combined together with the property of BP neural network, and an optimized classification algorithm by BP neural network based on PLS and HCA (PLS-HCA-BP algorithm) is proposed. The new algorithm is aimed at improving the operating efficiency and classification precision so as to provide a more reliable and more convenient tool for complex pattern classification systems. Three experiments and comparisons with four other algorithms are carried out to verify the superiority of the proposed algorithm, and the results indicate a good picture of the PLS-HCA-BP algorithm, which is worthy of further promotion.

Application of support vector machine to apple recognition using in apple harvesting robot

In the robot vision system of the apple harvesting robot, the key is to recognize and locate the apple. To solve recognition questions such as high error rate, too much calculation and time consuming, a new recognizing method, support vector machine (SVM) is applied to improve recognition accuracy and efficiency. At first, vector median filter is used to remove the color images noise of apple fruit. Secondly, segmentation of the images based on region growing method and color properties is done. Then, color properties and shape properties of color image are extracted, and classification method of SVM for recognition of apple fruit is used. Experimental results indicate that the classification performance of support vector machine is better than that of neural networks. Recognition rate of apple fruit based on SVM of color and shape properties is higher than that of only using the color or shape properties.

A method of segmenting apples at night based on color and position information

BPNN is used to classify pixels based on their color and position.The main body and edge of fruits are recognized respectively.The position information is represented as the relativity of adjacent pixels.The method can reduce the influence of Shadows and faculae effectively. This paper proposes a method to segment apples on trees at night for apple-harvesting robots based on color and position of pixels. Images of apples acquired under artificial light with low illumination at night include less color information than daytime images, so it is necessary to take position of pixels into consideration. The new method has two main steps. Firstly, color components of sampled pixels in RGB and HSI color space are used to train a neural network model to segment the apples. However, the segmentation results are incomplete and not able to guide apple-harvesting robots accurately, because partial edge regions of apples are dark in shadows and difficult to be recognized due to uneven illumination. Secondly, the color and position of pixels around segmented regions and pixels on the boundary of segmented regions are taken into consideration to segment the edge regions of apples. The union of two segmentation results is the final result. The complete recognition can increase the accuracy of location by about 6.5%, which verified the validity and feasibility of the method.

On the SVMpath Singularity

This paper proposes a novel ridge-adding-based approach for handling singularities that are frequently encountered in the powerful SVMpath algorithm. Unlike the existing method that performs linear programming as an additional step to track the optimality condition path in a multidimensional feasible space, our new approach provides a simpler and computationally more efficient implementation, which needs no extra time-consuming procedures other than introducing a random ridge term to each data point. Contrary to the existing ridge-adding method, which fails to avoid singularities as the ridge terms tend to zero, our novel approach, for any small random ridge terms, guarantees the existence of the inverse matrix by ensuring that only one index is added into or removed from the active set. The performance of the proposed algorithm, in terms of both computational complexity and the ability of singularity avoidance, is manifested by rigorous mathematical analyses as well as experimental results.

A New Image Denoising Method by Combining WT with ICA

In order to improve the image denoising ability, the wavelet transform (WT) and independent component analysis (ICA) are both introduced into image denoising in this paper. Although these two algorithms have their own advantages in image denoising, they are unable to reduce noises completely, which makes it difficult to achieve ideal effect. Therefore, a new image denoising method is proposed based on the combination of WT with ICA (WT-ICA). For verifying the WT-ICA denoising method, we adopt four image denoising methods for comparison: median filtering (MF), wavelet soft thresholding (WST), ICA, and WT-ICA. From the experimental results, it is shown that WT-ICA can significantly reduce noises and get lower-noise image. Moreover, the average of WT-ICA denoising image’s peak signal to noise ratio (PSNR) is improved by 20.54% compared with noisy image and 11.68% compared with the classical WST denoising image, which demonstrates its advantage. From the performance of texture and edge detection, denoising image by WT-ICA is closer to the original image. Therefore, the new method has its unique advantage in image denoising, which lays a solid foundation for the realization of further image processing task.

Apple picking robot obstacle avoidance based on the improved artificial potential field method

On the basis of retaining the merits of the traditional artificial potential field method which has simple structure and is easy to implement, and combining with the characteristics of obstacles in the apple growing environment, an improved artificial potential field method is present for the obstacle avoidance of apple picking robot. The virtual target point is introduced to help the searching progress escape from local optimal minima for some existing shortcomings, such as local minima, the stuck district. The productivity of apple picking robot is improved effectively. The experimental result proves the feasibility of this method.

Application of image segmentation algorithm based on entropy clustering in apple harvesting robot

For the robot vision system in apple harvesting robot, a new image segmentation method based on entropy clustering is proposed in HSI color space. Firstly, noise was wiped off by using weighted algorithm of median filtering in HSI color space instead of traditional algorithm in RGB model; secondly, Hue and Saturation components were extracted to do entropy clustering with their independence with Intensity, to get an initial segmentation; lastly, the clustering centers were optimized by K-Means clustering, to segment apple object from background correctly and completely. The experiments show that the algorithm can overcome two disadvantages in traditional K-Means algorithm effectively, noise interference and susceptible to the choice of initial cluster centers into local solutions; it can achieve centers automatically, then get an ideal result; the consuming time is short to meet the requirement of real-time ability, the accuracy is high as well.

Cascade servo control for LOS stabilization of opto-electronic tracking platform—design and self-tuning

A dual speed loop cascade control structure using the DC tachometer motor to constitute the inner speed loop, and using the rate gyro to constitute the outer stabilized loop is presented since there is shortcome in single speed loop servo control composed of rate gyro for LOS stabilization in opto-electronic tracking platform system. The functions of reducing inner friction disturbance and bating carrier turbulence are designed respectively. The aspects of the system performance and robustness are analyzed and compared with single speed loop control structure in detail. The inner speed loop adopts PI tuner to overcome the influence of nonlinearities caused by friction and mechanical resonances and a time optimal self-tuning PID control algorithm is developed to bate the carrier disturbance in outer stabilized loop. The proposed control structure and scheme based on DSP have been realized in a four-axis opto-electronic stabilized tracking platform. Experimental results can achieve higher stabilized precision and perfect control performance. The proposed control structure and method is effective and practicable in real practical applications.