Narrow Results

Traffic signs detection has become an important feature of Advanced driving assisting systems and even self-driving cars. In this paper, we present an implementation of a traffic signs detection method on Graphics Processing Units (GPU) under real-time conditions. The proposed model is based on deep convolutional neural networks, a deep learning model used in computer vision applications. The deep convolutional neural networks have recently been used to solve many computer vision tasks successfully. Unlike old techniques, the model is used to detect and identify the traffic signs at the same time without the need for any external modules. To achieve real-time inference, we implement the proposed model on the GPU as a natural choice for the implementation of deep learning-based models. Also, we build large traffic signs detection dataset. The dataset contains 10000 images captured from the Chinese roads under real-world factors like lightning, occlusion, complex background, etc. 73 traffic sign classes were considered in this dataset. The evaluation of the proposed model on the proposed dataset shows robust performance in terms of speed and accuracy.

To improve the real-time performance and the target adaptability of penetration fuze detonation control systems, and to enhance the system fusion processing capability for multi-sensor information, this paper uses a modular design concept to construct a miniaturized (ø38mm×4mm) fuze detonation control system that is capable of real-time processing of data from multiple information sources. The core component of this system is the GD32E230 microcontroller, which features a high dominant frequency and low power consumption. This device is integrated with a ferroelectric memory and signal processing circuits that match the sensors. To address the issue of unclear traditional acceleration signal penetration and the difficulties associated with the identification of these signals, the approach in this paper improves feature recognition accuracy through rapid acquisition and fusion of multiple types of sensor output signal, and self-adaptive identification of multilayered targets and single-layer thick targets is achieved. During the programming of the embedded system, the hardware register is operated directly, the instruction execution sequence is optimized, and the program execution efficiency is improved by using the function characteristic that some microcontroller unit peripherals do not occupy the central processing unit when working, thus allowing the intended purpose of improving the system’s real-time performance to be achieved. A semi-physical simulation method is then used to verify the performance of the penetration fuze detonation control system. The results obtained show that the system has 100%-layer counting accuracy for multilayered targets and a relative error of less than 1% for the calculated residual velocities of single-layer thick targets, thus validating the effectiveness of the system.

Shape recognition is an important research area in pattern recognition. It also has wide practical applications in many fields. An attribute grammar approach to shape recognition combines both the advantages of syntactic and statistical methods and makes shape recognition more accurate and efficient. However, the time complexity of a sequential shape recognition algorithm using attribute grammar is O(n³) where n is the length of an input string. When the problem size is very large it needs much more computing time, therefore a high speed parallel shape recognition is necessary to meet the demands of some real-time applications. This paper presents a parallel shape recognition algorithm and also discusses the algorithm partition problem as well as its implementation on a fixed-size VLSI architecture. The proposed algorithm has time complexity O(n³/k²) if using k×k processing elements. When k=n, its time complexity is O(n). The experiment has been conducted to verify the performance of the proposed algorithm. The correctness of the algorithm partition and the behavior of the proposed VLSI architecture have also been proved through the experiment. The results indicate that the proposed algorithm and the VLSI architecture could be very useful to imaging processing, pattern recognition and related areas, especially for real-time applications.

This paper describes the design and the VLSI implementation of a novel architecture that performs image rotation in real time. In order to improve throughput, we divide an image-frame into a number of windows. The rotation of each window-center as well as the final displacement of individual pixels within a window is then calculated. A CORDIC-based scheme is used to compute the displacement of a pixel. Our architectural design is incorporated into a chip that has been laid out using VTI (VLSI Technology Inc.) tools obeying the 1.5 μm SCMOS design rules. The chip owes its high processing capability to a combination of pipelining and parallel-processing techniques. For a clock frequency greater than 10.6 MHz, we can perform the rotation of a 512×512 gray-level digital image at the rate of 30 frames per second. The chip utilizes around 35,000 transistors and has an estimated silicon area of 211 mils×276 mils.

Simple approaches to texture discrimination based on histogram analysis are useful in real-time applications but often yield inadequate results. On the other hand, methods based on higher-order statistics (e.g., co-occurrence matrices) provide a more complete statistical characterisation but are extremely time-consuming. In this paper, methods based on first order statistical analysis are reviewed and the significance of the relevant representative features analyzed. Then, rank functions are considered and appropriate distance functions are introduced that prove to have substantial advantages over classical histogram-based approaches.

Modern laser scanners perform high-speed real-time image processing algorithms while operating in harsh industrial environments. Their performance goal is to extract the central position of the laser line reflection with Gaussian distribution. Traditional algorithms for sub-pixel estimation, such as the Center of Gravity (CG) or Parabolic Fit (PF), show poor performances under low SNR or if the pixels are saturated. Data pre-processing usually has a key role in suppressing the effects of various noise sources and dynamic environment, especially when the images are overexposed and the top of Gaussian pulse is flattened. Both in simulation and in experiment, this study explains a method that improves the accuracy of estimation of the laser stripe reflection center, by using an autoconvolution for extending the bit-width of pixel intensity. Autoconvolution of the image line is an efficient real-time pre-processing filtering method for improving the accuracy of CG calculation. The proposed algorithm is implemented on Field-Programmable Gate Arrays (FPGAs) and experimentally validated at real operational environment. It is shown that this method can reduce the error of CG laser reflection center estimation for more than one pixel in size when the image is highly affected by external noise sources and ambient light.

The value of knowledge inferred from information databases is critically dependent on the quality of data. The identification of noisy attributes which can easily corrupt and curtail valuable knowledge and information from a dataset can be very helpful to analysts. We present a novel detection method to identify noisy attributes in datasets of software metrics using multi-resolution transformations based on Discrete Wavelet Transforms. The proposed method has been applied to supervised datasets of scientific full-scale data from NASA's Software Metric Data Program (MDP) and to a military command, control, and communications system (CCCS). Empirical results have been favorably compared to those obtained from the robust Pairwise Attribute Noise Detection Algorithm (PANDA) using the same MDP datasets and with mixed results for the CCCS data. All results were verified with several case studies that included injecting known simulated noise into specific attributes with no class noise.

We propose an approach for real-time blind source separation (BSS), in which the observations are linear convolutive mixtures of statistically independent acoustic sources. A recursive least square (RLS)-like strategy is devised for real-time BSS processing. A normal equation is further introduced as an expression between the separation matrix and the correlation matrix of observations. We recursively estimate the correlation matrix and explicitly, rather than stochastically, solve the normal equation to obtain the separation matrix. As an example of application, the approach has been applied to a BSS problem where the separation criterion is based on the second-order statistics and the non-stationarity of signals in the frequency domain. In this way, we realise a novel BSS algorithm, called exponentially weighted recursive BSS algorithm. The simulation and experimental results showed an improved separation and a superior convergence rate of the proposed algorithm over that of the gradient algorithm. Moreover, this algorithm can converge to a much lower cost value than that of the gradient algorithm.

This paper describes the design and the VLSI implementation of a novel architecture that performs image rotation in real time. In order to improve throughput, we divide an image-frame into a number of windows. The rotation of each window-center as well as the final displacement of individual pixels within a window is then calculated. A CORDIC-based scheme is used to compute the displacement of a pixel. Our architectural design is incorporated into a chip that has been laid out using VTI (VLSI Technology Inc.) tools obeying the 1.5 μm SCMOS design rules. The chip owes its high processing capability to a combination of pipelining and parallel-processing techniques. For a clock frequency greater than 10.6 MHz, we can perform the rotation of a 512 × 512 gray-level digital image at the rate of 30 frames per second. The chip utilizes around 35,000 transistors and has an estimated silicon area of 211 mils × 276 mils.

This paper presents a complete artificial vision system development and implementation for a mobile robot recognition and obstacles detection, which integrates a statistical segmentation method with frequency filtering in order to achieve luminosity independence, exploiting the advantages of known image processing techniques by mixing them into a robotic application. The system proposed determines the mobile robot's position and orientation, using a color segmentation approach based on the Mahalanobis Distance, and the position and size of obstacles in the robot's environment using a parallel scheme based on both Sobel edge detector and Otsu's threshold. The Mahalanobis distance calculus was implemented using a real-time PPGA architecture, in order to detect the robot's position. Tests in the real robot's environment are presented obtaining results that are independent from the background characteristics and strongly robust on the luminosity variability.