Current Issue : January - March Volume : 2018 Issue Number : 1 Articles : 5 Articles
Aircraft detection from high-resolution remote sensing images is important for civil and military applications. Recently, detection\nmethods based on deep learning have rapidly advanced. However, they require numerous samples to train the detectionmodel and\ncannot be directly used to efficiently handle large-area remote sensing images. A weakly supervised learning method (WSLM) can\ndetect a target with few samples. However, it cannot extract an adequate number of features, and the detection accuracy requires\nimprovement.We propose a cascade convolutional neural network (CCNN) framework based on transfer-learning and geometric\nfeature constraints (GFC) for aircraft detection. It achieves high accuracy and efficient detection with relatively few samples. A\nhigh-accuracy detection model is first obtained using transfer-learning to fine-tune pretrained models with few samples. Then, a\nGFC region proposal filtering method improves detection efficiency. The CCNN framework completes the aircraft detection for\nlarge-area remote sensing images. The framework first-level network is an image classifier, which filters the entire image, excluding\nmost areaswith no aircraft.Thesecond-level network is an object detector,which rapidly detects aircraft fromthe first-level network\noutput. Compared with WSLM, detection accuracy increased by 3.66%, false detection decreased by 64%, and missed detection\ndecreased by 23.1%....
Crack assessment is an essential process in the maintenance of concrete structures.\nIn general, concrete cracks are inspected by manual visual observation of the surface, which is\nintrinsically subjective as it depends on the experience of inspectors. Further, it is time-consuming,\nexpensive, and often unsafe when inaccessible structural members are to be assessed. Unmanned\naerial vehicle (UAV) technologies combined with digital image processing have recently been\napplied to crack assessment to overcome the drawbacks of manual visual inspection. However,\nidentification of crack information in terms of width and length has not been fully explored in\nthe UAV-based applications, because of the absence of distance measurement and tailored image\nprocessing. This paper presents a crack identification strategy that combines hybrid image processing\nwith UAV technology. Equipped with a camera, an ultrasonic displacement sensor, and aWiFi module,\nthe system provides the image of cracks and the associated working distance from a target structure\non demand. The obtained information is subsequently processed by hybrid image binarization\nto estimate the crack width accurately while minimizing the loss of the crack length information.\nThe proposed system has shown to successfully measure cracks thicker than 0.1 mm with the\nmaximum length estimation error of 7.3%....
Traditional two-dimensional Otsu algorithm has several drawbacks; that is, the sum of probabilities of target and background is\napproximate to 1 inaccurately, the details of neighborhood image are not obvious, and the computational cost is high. In order\nto address these problems, a method of fast image segmentation using two-dimensional Otsu based on estimation of distribution\nalgorithm is proposed. Firstly, in order to enhance the performance of image segmentation, the guided filtering is employed to\nimprove neighborhood image template instead of mean filtering. Additionally, the probabilities of target and background in twodimensional\nhistogram are exactly calculated to get more accurate threshold. Finally, the trace of the interclass dispersion matrix\nis taken as the fitness function of estimation of distributed algorithm, and the optimal threshold is obtained by constructing and\nsampling the probability model. Extensive experimental results demonstrate that our method can effectively preserve details of the\ntarget, improve the segmentation precision, and reduce the running time of algorithms....
Processing of digital images is continuously gaining in volume and relevance, with concomitant demands\non data storage, transmission, and processing power. Encoding the image information in quantum-mechanical\nsystems instead of classical ones and replacing classical with quantum information processing may alleviate\nsome of these challenges. By encoding and processing the image information in quantum-mechanical\nsystems, we here demonstrate the framework of quantum image processing, where a pure quantum state\nencodes the image information: we encode the pixel values in the probability amplitudes and the pixel\npositions in the computational basis states. Our quantumimage representation reduces the required number of\nqubits compared to existing implementations, and we present image processing algorithms that provide\nexponential speed-up over their classical counterparts. For the commonly used task of detecting the edge of an\nimage, we propose and implement a quantum algorithm that completes the task with only one single-qubit\noperation, independent of the size of the image. This demonstrates the potential of quantum image processing\nfor highly efficient image and video processing in the big data era....
In order to realize the video image transmission and the excellent lighting\nfunction of the visible light communication system, a LED-based visible light\ncommunication method and system is proposed. Based on the field programmable\ngate array (FPGA) hardware, the RS channel coding is applied to\nthe visible light communication system. A pulse position decision algorithm is\nproposed, which is applied to the receiver of the visible light communication\nsystem to meet the error-free decision of the signal. The design of the system\nis based on the analog-to-digital conversion circuit, which provides a large\nsignal dynamic range for the pulse position decision algorithm, and designs\nthe LED driver based on the bias circuit to realize the fast broadband modulation\nof the signal. The test results show that the combined application of pulse\nposition decision algorithm and Reed-Solomon codec can reduce the error of\nsystem signal and meet the real-time and reliable transmission of signal. The\nsystem can display the received video in real time from the receiver, and the\nwhole system communication distance up to 5 m....
Loading....