This paper provides a mathematical analysis that shows how the crisp output of an IT2 FLS that is obtained by using the Begian-Melek-Mendel (BMM) formula compares to the one obtained by using center-of-sets type-reduc...
详细信息
ISBN:
(纸本)9781509006274
This paper provides a mathematical analysis that shows how the crisp output of an IT2 FLS that is obtained by using the Begian-Melek-Mendel (BMM) formula compares to the one obtained by using center-of-sets type-reduction followed by defuzzification (COS TR + D). This is made possible by reformulating the structural solutions of the two optimization problems that are associated with COS TR, and then expanding each of them using a Maclaurin series expansion. As a result of doing this, we show that BMM is the zero-order approximation to COS TR + D. Additionally, by retaining the zero-order and first-order terms from the Maclaurin series expansions, we provide a new Enhanced BMM, one that is non-iterative, has a closed form and is much faster than using the EKM algorithms for COS TR. Although the Enhanced BMM formula is slower than BMM, we demonstrate, by means of extensive simulations, that it is from 5% to 50% more accurate than is BMM for achieving the same numerical solution that is obtained from COS TR + D; and, it is at least 94% faster than when EKM is used for COS TR +D, which makes the Extended BMM a very strong candidate for use in real time applications of IT2 FLSs.
This article focuses on an original approach aiming the processing of low-altitude aerial sequences taken from an helicopter (or drone) and presenting a road traffic. Proposed system attempts to extract vehicles from ...
详细信息
This article focuses on an original approach aiming the processing of low-altitude aerial sequences taken from an helicopter (or drone) and presenting a road traffic. Proposed system attempts to extract vehicles from acquired sequences. Our approach begins with detecting the primitives of sequence images. At the time of this step of segmentation, the system computes dominant motion for each pair of images. This motion is computed using wavelets analysis on optical flow equation and robust techniques. Interesting areas (areas not affected by the dominant motion) are detected thanks to a Markov hierarchical model. Primitives stemming from segmentation and interesting areas are used to build a graph on which partitioning process is executed. This graph gathers only the primitives (considered as nodes) witch belong to the interesting areas. Nodes are interconnected by Perceptive Criteria. To extract the important elements of the sequence (vehicles), a bi-partition of this graph using Normalized Cuts technique takes place. Finally, parameters of proposed algorithm are chosen thanks to a learning stage for which we use Genetic algorithms.
While current computers have shown to be particular useful for arithmetic and logic implementations, their accuracy and efficiency for applications such as e.g. face, object and speech recognition, are not that impres...
详细信息
ISBN:
(纸本)9781467398893
While current computers have shown to be particular useful for arithmetic and logic implementations, their accuracy and efficiency for applications such as e.g. face, object and speech recognition, are not that impressive, especially when compared to what the human brain can do. Machine learning algorithms have been useful, especially for these type of applications, as they operate in a similar way to the human brain, by learning the data provided and storing it for future recognition. Until now, there has been a strong focus on developing the process of data storage and retrieval, merely neglecting the value of the provided information and the amount of data required to store. Hence, currently all information provided is stored, because it is difficult for the machine to decide which information needs to be stored. Consequently, large amounts of data are stored, which then affects the processing of the data. Thus, this paper investigates the opportunity to reduce data storage through the use of differentiation and combine it with an existing similarity detection algorithm. The differentiation isWhile current computers have shown to be particular useful for arithmetic and logic implementations, their accuracy and efficiency for applications such as e.g. face, object and speech recognition, are not that impressive, especially when compared to what the human brain can do. Machine learning algorithms have been useful, especially for these type of applications, as they operate in a similar way to the human brain, by learning the data provided and storing it for future recognition. Until now, there has been a strong focus on developing the process of data storage and retrieval, merely neglecting the value of the provided information and the amount of data required to store. Hence, currently all information provided is stored, because it is difficult for the machine to decide which information needs to be stored. Consequently, large amounts of data are stored, which then
With increasing complexity of algorithms for embedded systems, demand for higher processor performance and lower battery power consumption is growing immensely. Due to upcoming fields like embedded vision where algori...
详细信息
ISBN:
(纸本)9781479966585
With increasing complexity of algorithms for embedded systems, demand for higher processor performance and lower battery power consumption is growing immensely. Due to upcoming fields like embedded vision where algorithms require learning, techniques like Support Vector Machines (SVM) have gained significant importance in these areas. These machines are required in performing classification tasks in variety of fields to analyze data, recognize patterns in images and videos. In this work, SVM is implemented on an Application Specific Instruction Processor (ASIP) designed using an Architectural Description Language (ADL) based tool to meet the ultra-high throughput and ultra-low power requirement posed by pedestrian detection algorithm in embedded vision-domain. We started with a base RISC processor and added a list of systematic extensions to gain speed for SVM like algorithms. With this we could achieve a throughput of -630K SVMs/sec (-3k dimensions) at 6.5 mW, which is significantly better than GPU (Nvidia GTX280 at 236 Watt) in terms of power and ARM Cortex-A8 (-16K SVMs/sec) in terms of throughput.
A large portion of imageprocessing applications often come with stringent requirements regarding performance, energy efficiency, and power. FPGAs have proven to be among the most suitable architectures for algorithms...
详细信息
A large portion of imageprocessing applications often come with stringent requirements regarding performance, energy efficiency, and power. FPGAs have proven to be among the most suitable architectures for algorithms that can be processed in a streaming pipeline. Yet, designing imaging systems for FPGAs remains a very time consuming task. High-Level Synthesis, which has significantly improved due to recent advancements, promises to overcome this obstacle. In particular, Altera OpenCL is a handy solution for employing an FPGA in a heterogeneous system as it covers all device communication. However, to obtain efficient hardware implementations, extreme code modifications, contradicting OpenCL's data-parallel programming paradigm, are necessary. In this work, we explore the programming methodology that yields significantly better hardware implementations for the Altera Offline Compiler. We furthermore designed a compiler back end for a domain-specific source-to-source compiler to leverage the algorithm description to a higher level and generate highly optimized OpenCL code. Moreover, we advanced the compiler to support arbitrary bit width operations, which are fundamental to hardware designs. We evaluate our approach by discussing the resulting implementations throughout an extensive application set and comparing them with example designs, provided by Altera. In addition, as we can derive multiple implementations for completely different target platforms from the same domain-specific language source code, we present a comparison of the achieved implementations in contrast to GPU implementations.
Videos from a small Unmanned Aerial Vehicle (UAV) are always unstable because of the wobble of the vehicle and the impact of surroundings, especially when the motion has a large drifting. Electronic image stabilizatio...
详细信息
ISBN:
(纸本)9781628414899
Videos from a small Unmanned Aerial Vehicle (UAV) are always unstable because of the wobble of the vehicle and the impact of surroundings, especially when the motion has a large drifting. Electronic image stabilization aims at removing the unwanted wobble and obtaining the stable video. Then estimation of intended motion, which represents the tendency of global motion, becomes the key to image stabilization. It is usually impossible for general methods of intended motion estimation to obtain stable intended motion remaining as much information of video images and getting a path as much close to the real flying path at the same time. This paper proposed a fuzzy Kalman filtering method to estimate the intended motion to solve these problems. Comparing with traditional methods, the fuzzy Kalman filtering method can achieve better effect to estimate the intended motion.
Although today's computing systems present powerful solutions to process big data with the help of recent advances in cloud computing technologies, many problems remain unsolved due to lack of acceptable algorithm...
详细信息
ISBN:
(纸本)9781467373869
Although today's computing systems present powerful solutions to process big data with the help of recent advances in cloud computing technologies, many problems remain unsolved due to lack of acceptable algorithms. For instance, searching for a lost plane or damage assessment after earthquake on a high-resolution remote sensing satellite image are unsolved problems. In recent years, in order to solve such unsolved problems, a group of expert and nonexpert people called crowd is utilized. An expert in the group is not expected to solve whole problem. Instead, geospatial image is partitioned in space and each expert in the pool studies the partition assigned to him/her. The solution to the original problem is obtained by merging the partial solutions. There are two open issues: i) How to partition the space and how to distribute the partitions to the crowd ii) How to merge the partial solutions. In this study, we devise several algorithms to address these issues, introduce our web-based platform, and crowd-sourcing implementation.
The demand of 3D image is growing sharply in the recent trends. Digital imageprocessing performs imageprocessing on digital images by the use of computer algorithms. Strain measurement is a big challenge for 3D imag...
详细信息
In oceanic environment, uneven illumination, turbulence in water and floating particles make underwater image capture, a challenge. Vision sensors attached with the autonomous underwater vehicles, themselves cause lig...
详细信息
ISBN:
(纸本)9788192597430
In oceanic environment, uneven illumination, turbulence in water and floating particles make underwater image capture, a challenge. Vision sensors attached with the autonomous underwater vehicles, themselves cause light dispersion and shadows in the ocean floor. Although, several computer vision algorithms have been developed, effective analysis of the algorithms both quantitatively and qualitatively have not been done. This paper analyses the existing methods for the inherent problems and provides a framework for underwater imageprocessing. Initially, for non-uniform illumination correction, homomorphic, anisotropic and bilateral filtering techniques are compared for contrast equalization. Contrast enhancement is done using contrast limited adaptive histogram equalization (CLAHE) with adaptive histogram clip. Finally, Haar wavelet and Symlet are compared for adaptive smoothing, elimination of remaining noise and for improving edge detection. Performance is assessed by computing peak signal noise ratio (PSNR), contrast to noise ratio (CNR), image enhancement metric (IEM), and absolute mean brightness error (AMBE). Histograms are computed before and after applying preprocessing filters, for evaluating the proposed methodology. A combination of homomorphic filtering, CLAHE and haar wavelet denoising provides better results over other methods for underwater images.
Noise reduction is one of the most fundamental digital imageprocessing challenges. On mobile devices, proper solutions for this task can significantly increase the output image quality making the use of a camera even...
详细信息
ISBN:
(纸本)9781467373111
Noise reduction is one of the most fundamental digital imageprocessing challenges. On mobile devices, proper solutions for this task can significantly increase the output image quality making the use of a camera even more attractive for customers. The main challenge is that the processing time and energy efficiency must be optimized, since the response time and the battery life are critical factors for all mobile applications. To identify the solutions that maximizes the real-time performance, we compare several different implementations in terms of computational performance and energy efficiency. Specifically, we compare the OpenCL based design with multithreaded and NEON accelerated implementations and analyze them on the mobile platform. Based on the results of this study, the OpenCL framework provides a viable energy efficient alternative for implementing computer vision algorithms.
暂无评论