Image Data Streams Research Articles

A robust hubness-based algorithm for image data stream classification

A robust hubness-based algorithm for image data stream classification

Rapid and Automatic Image Acquisition System for Structural Surface Defects of High-Speed Rail Tunnels

Continuous high-speed (>80 km/h) tunnel-image detection introduces new challenges to defect image acquisition, including machine recognition of entry and exit from a tunnel, storage of massive image data streams, image distortion due to surface photography, and encoder errors. In this study, an automatic image acquisition system is designed, and several critical technologies are proposed for high-speed rail tunnels. The system realizes quick tunnel identification and automatic camera control and uses the proposed line-scan software-matching method to obtain accurate images. Before storage, the real-time modification of the distorted images is implemented using an error-correction algorithm. An alternative mapping storage algorithm is proposed to improve the efficiency and stability of long-term storage. The test results show that the proposed method effectively reduces photographic errors. The lateral pixel-error rate of the corrected image is 1.60%, which is 10 times lower than that of the pre-correction, and the error rate of the longitudinal image is controlled within 10% when the system is moving at a variable speed and within 1% when it is moving at a constant speed. Furthermore, experiments have proven that the alternate mapping storage algorithm improves the storage efficiency of RAID by 50% and ensures data integrity; storage is accomplished by 8 HDDs at a camera throughput of 1.52 GB/s. This study will contribute to improvements in the speed and accuracy of tunnel defect-image detection.

Statistical quality control using image intelligence: A sparse learning approach

AbstractAdvances in image acquisition technology have made it convenient and economic to collect large amounts of image data. In manufacturing and service industries, images are increasingly used for quality control purposes because of their ability to quickly provide information about product geometry, surface defects, and nonconforming patterns. In production line monitoring, image data often take the form of image streams in the sense that images from the process are being collected over time. In such applications, a fundamental task is to properly analyze image data streams. This image monitoring problem is challenging for several reasons. First, images often have complicated structures such as edges and singularities, which render many traditional smoothing methods inapplicable. Second, a typical grayscale image contains tens of thousands of pixels, so the data is high‐dimensional. It has been shown in the statistical process control (SPC) literature that conventional multivariate control charts have limited power of detecting process shifts when the data dimension is high. In this article, we propose to transform images using a two‐dimensional wavelet basis and monitor the wavelet coefficients by sparse learning‐based multivariate control charts. By adapting the sparse learning algorithm to our quality control problem, the proposed method is able to detect shifts in the wavelet coefficients in a timely fashion and simultaneously identify those shifted coefficients. Combining this feature with the localization property of the wavelet basis, our method also enables accurate diagnosis of faulty image regions. In addition, the proposed charting statistics have explicit formulas, so they are easy to compute. Theoretical justifications and numerical comparisons with an existing method show that our method works well in applications.

A comprehensive analysis of the diverse aspects inherent to image data stream classification

A comprehensive analysis of the diverse aspects inherent to image data stream classification

IMAGE RETRIEVAL USING MODIFIED BLOCK TRUNCATION CODING FEATURE

With the advent of digital camera, improvement in the digital storage media and rapid development in internet provide a huge collection of images. Fast and accurate image retrieval from this huge collection of image database is a challenging task. This is possible only by combining the image retrieval mechanism along with image compression technique. Content Based Image Retrieval (CBIR) uses the visual information in the images to retrieve the similar images. In this paper, image feature descriptor from the compressed stream of image data is extracted where the images are compressed using a variant of Block Truncation Coding (BTC) named Dot Diffused Block Truncation Coding (DDBTC). Here the Colour Histogram Feature (CHF) and the Bit Pattern Features (BPF) are extracted and used to represent the image and similarity computation.

Performance Analysis of Diversity Selection Combining on Radio Frequency for Image Transmission

This paper describes a simulation of the image transmission system with diversity selection combining (DSC) method on radio frequency. DSC is used to obtain multiple data streams corresponding to the transmitted image at the receiver in order to combat errors during image transmission on wireless channels. These individual image data streams are combined to form a composite image with higher perceptual quality. When DSC is used, it is expected that it can affect the number of errors, so that the signal transmitted to the wireless channels becomes more robust against interference caused by transmission channels. By using DSC technique, it can increase the quality of image transmission at the receiver. The result of the experiment which was carried out to test bit error rate (BER) and peak signal to noise ratio (PSNR) on Lena image with rate 0.8 bpp by using DSC on radio frequency in Rayleigh fading channel showed that there was a decrease in BER at the average of 0.0152 or 3.39%, while for PSNR there was an increase at the average of 1.6737 dB or 6.73%when comparing to the system without DSC.

Efficient mining of IoT based data streams for advanced computer vision systems

With emergence of Internet of Things (IoT) and subsequent technologies, smart devices are being increasingly used in various domains such as smart homes, smart parking, intelligent transportation etc. Vast amount of image and video data has been produced by IoT based systems in the form of continuous and possibly infinite image and video streams. This demands the development of advanced predictive vision systems which exploits stream mining concepts for intelligent processing of visual data streams. Among other challenges faced by visual data streams, a major challenge is concept drift, which is caused by overtime change in data distribution. In the presence of skewed data, the detection of concept drift becomes more challenging. When analyzing the data generated from smart devices and other performance critical wireless sensors, concept drift affects data integrity and accuracy of prediction results. EWMA for Concept Drift Detection (ECDD) has been proposed in the literature for detecting data streams. However, ECDD has a high prediction error rate which makes it less useful for performance critical data streams generated by imaging and video data streams. In this paper, Vision based Drift Detection Method (VisDDM) is proposed, which systematically handles abrupt and gradual concept drift in data streams. Experiments have been performed using synthetic and real world datasets from different application domains. Our proposed VisDDM algorithm is able to handle abrupt and gradual drift types and outperformed the existing drift detection methods in terms of accuracy and mean evaluation time.

Accuracy of image data stream of a markerless motion capture system in determining the local dynamic stability and joint kinematics of human gait

Assessment of gait parameters is commonly performed through the high-end motion tracking systems, which limits the measurement to sophisticated laboratory settings due to its excessive cost. Recently, Microsoft Kinect (v2) sensor has become popular in clinical gait analysis due to its low-cost. But, determining the accuracy of its RGB-D image data stream in measuring the joint kinematics and local dynamic stability remains an unsolved problem. This study examined the suitability of Kinect(v2) RGB-D image data stream in assessing those gait parameters. Fifteen healthy participants walked on a treadmill during which lower body kinematics were measured by a Kinect(v2) sensor and a optophotogrametric tracking system, simultaneously. Extended Kalman filter was used to extract the lower extremity joint angles from Kinect, while inverse kinematics was used for the gold standard system. For both systems, local dynamic stability was assessed using maximal Lyapunov exponent. Sprague’s validation metrics, root mean square error (RMSE) and normalized RMSE were computed to confirm the difference between the joint angles time series of the two systems while relative agreement between them was investigated through Pearson’s correlation coefficient (pr). Fisher’s Exact Test was performed on maximal Lyapunov exponent to investigate the data independence while reliability was assessed using intraclass correlation coefficients. This study concludes that the RGB-D data stream of Kinect sensor is efficient in estimating joint kinematics, but not suitable for measuring the local dynamic stability.

Combining CNN streams of dynamic image and depth data for action recognition

RGB-D sensors have been in great demand due to its capability of producing large amount of multimodal data like RGB images and depth maps, useful for better training of deep learning models. In this paper, a deep learning model for recognizing human activities in a video sequence by combining multiple CNN streams has been proposed. The proposed work comprises the use of dynamic images generated from RGB images and depth map for three different dimensions. The proposed model is trained using these four streams on VGG Net for action recognition purpose. Further, it is evaluated and compared with the other state-of-the-art methods available in literature, on three challenging datasets, namely MSR daily Activity, UTD MHAD and CAD 60, in terms of accuracy, error, recall, specificity, precision and f-score. From obtained results, it has been observed that the proposed method outperforms other methods.

Cascaded Stripe Memory Engines for Multi-Scale Object Detection in FPGA

Object detection in embedded systems is important for many contemporary applications that involve vision and scene analysis. In this paper, we propose a novel architecture for object detection implemented in FPGA, based on the Stripe Memory Engine (SME), and point out shortcomings of existing architectures. SME processes a stream of image data so that it stores a narrow stripe of the input image and its scaled versions and uses a detector unit which is efficiently pipelined across multiple image positions within the SME. We show how to process images with up to 4K resolution at high frame rates using cascades of SMEs. As a detector algorithm, the SMEs use boosted soft cascade with simple image features that require only pixel comparisons and look-up tables; therefore, they are well suitable for hardware implemenation. We describe the components of our architecture and compare it to several published works in several configurations. As an example, we implemented face detection and license plate detection applications that work with HD images (1280 ×720 pixels) running at over 60 frames/s on Xilinx Zynq platform. We analyzed their power consumption, evaluated the accuracy of our detectors, and compared them to Haar Cascades from OpenCV that are often used by other authors. We show that our detectors offer better accuracy as well as performance at lower power consumption.

Performance evaluation of image transmission using diversity selection combining technique

This paper discussed a simulation of SPIHT image compression transmission on wireless channels by using RS code and diversity selection combining technique in wavelet domain to get better reconstruction image by minimizing errors that caused by fading and noise. RS Code and Diversity Selection Combining Method were used to combat errors during image transmission on wireless channels. When the bit stream data arrived at the receiver, the coding was used to recover the errors in the bitstream. Diversity was used to obtain multiple data streams corresponding to the transmitted image at the receiver. These individual image data streams were combined to form a composite image with the better quality. The results show both methods demonstrated quality improvement of the received image.

Image fusion of Secondary Ion Mass Spectrometry and Energy-dispersive X-Ray Spectroscopy data for the characterization of uranium-molybdenum fuel foils

Uranium-molybdenum (U-Mo) monolithic fuels represent one option for converting civilian research and test reactors operating with high enriched uranium (HEU) to low enriched uranium (LEU), effectively reducing the threat of nuclear proliferation world-wide. However, processes associated with fabrication of U-Mo monolithic fuels result in regions of elemental heterogeneity, observed as bands traversing the cross-section of representative samples. Isotopic variations (e.g., 235U and 238U) could also be introduced because of associated processing steps, particularly since HEU feedstock is melted with natural or depleted uranium diluent to produce LEU. This study demonstrates the utility of correlative analysis of Energy-Dispersive X-ray Spectroscopy (EDS) and Secondary Ion Mass Spectrometry (SIMS) with their image data streams using image fusion, resulting in a comprehensive microanalytical characterization toolbox. Elemental and isotopic measurements were made on a sample from the Advanced Test Reactor (ATR) Full-sized plate In-center flux trap Position (AFIP)-7 experiment and compared to previous optical and electron microscopy results. The image fusion results are characteristic of SIMS isotopic maps, but with the spatial resolution of EDS images and, therefore, can be used to increase the effective spatial resolution of the SIMS imaging results to better understand homogeneity or heterogeneity that persists because of processing selections. Visual inspection using the image fusion methodology indicated slight variations in the 235U/238U ratio and quantitative analysis using the image intensities across several FoVs revealed an average 235U atom percent value of 17.9 ± 2.4%, which was indicative of a non-uniform U isotopic distribution in the area sampled. Further development of this capability is useful for understanding the connections between the properties of LEU fuel alternatives and the ability to predict performance under irradiation.

Architecture for parallel marker-free variable length streams decoding

Due to throughput requirements above 1 gigapixel/sec for the real-time compression of modern image and video data streams, parallelism for encoding and decoding is inevitable. To achieve parallel decoding, a well-established technique is to insert markers into the variable length code (VLC) stream. By locating markers, it is then possible to extract the sub-streams that are, in turn, decoded in parallel. The use of markers adversely affects compression especially when a high degree of parallelism is required. In this paper, we propose an architecture of a marker-free parallel decoding approach of VLC streams. Instead of multiple local entropy decoders, the proposed architecture is based on using a single parallel entropy decoder in conjunction with a novel format to construct the VLC stream. The approach runs at high clock rates supporting parallelism to a high number of decoders. A synthesized clock frequency well above 110 MHz is achieved for up to 20 decoders on a medium-sized FPGA.

Growing Neural Forest-Based Color Quantization Applied to RGB Images

Although last improvements in both physical storage technologies and image handling techniques have eased image managing processes, the large amount of information handled nowadays constantly demands more efficient ways to store and transmit image data streams. Among other alternatives for such purpose, the authors find color quantization, which consists of color indexing for minimal perceptual distortion image compression. In this context, artificial intelligence-based algorithms and more specifically, Artificial Neural Networks, have been consolidated as a powerful tool for unsupervised tasks, and therefore, for color quantization purposes. In this work, a novel approach to color quantization is presented based on the Growing Neural Forest (GNF), which is a Growing Neural Gas (GNG) variation where a set of trees is learnt instead of a general graph. Experimental results support the use of GNF for image quantization tasks where it overcomes other self-organized models including SOM, GHSOM and GNG. Future work will include more datasets and different competitive models to compare to.

Online Combination of EPID & Cherenkov Imaging for 3-D Dosimetry in a Liquid Phantom.

Online acquisition of Cherenkov and portal imaging data was combined with a reconstruction scheme called EC3-D, providing a full 3-D dosimetry of megavoltage X-ray beams in a water tank. The methodology was demonstrated and quantified in a single static beam. Furthermore, the dynamics and visualization of the 3-D dose reconstruction were demonstrated with a volumetric modulated arc therapy plan for TG-119 C-Shape geometry. The developed algorithm combines depth dose information, provided by Cherenkov images, with the lateral dose distribution, provided by the electronic portal imaging device. The strength of our approach lies in the acquisition of both imaging data streams with sub-millimeter theoretical resolution at 5-Hz frame-rate, which can be concurrently processed by the fast Fourier transform-based analysis, thus providing means for an efficient real-time 3-D dosimetry.

An Operational System for Estimating Road Traffic Information from Aerial Images

Given that ground stationary infrastructures for traffic monitoring are barely able to handle everyday traffic volumes, there is a risk that they could fail altogether in situations arising from mass events or disasters. In this work, we present an alternative approach for traffic monitoring during disaster and mass events, which is based on an airborne optical sensor system. With this system, optical image sequences are automatically examined on board an aircraft to estimate road traffic information, such as vehicle positions, velocities and driving directions. The traffic information, estimated in real time on board, is immediately downlinked to a ground station. The airborne sensor system consists of a three-head camera system, a real-time-capable GPS/INS unit, five industrial PCs and a downlink unit. The processing chain for automatic extraction of traffic information contains modules for the synchronization of image and navigation data streams, orthorectification and vehicle detection and tracking modules. The vehicle detector is based on a combination of AdaBoost and support vector machine classifiers. Vehicle tracking relies on shape-based matching operators. The processing chain is evaluated on a large number of image sequences recorded during several campaigns, and the data quality is compared to that obtained from induction loops. In summary, we can conclude that the achieved overall quality of the traffic data extracted by the airborne system is in the range of 68% and 81%. Thus, it is comparable to data obtained from stationary ground sensor networks.

Multilayered JPEG Image Transmission over SUI Channel Using UEP and Error Concealment Techniques

In last decade the transmission of image over wireless network has become challenging. Compressed bit stream of image/video need less storage and bandwidth but highly sensitive to propagation of errors. So error control is an important technique in image/video transmission. This paper proposed multilayered bit stream of JPEG coded image transmission through wireless channel (SUI) using Unequal Error Protection (UEP). The Protection level will be decided based on the importance of layer in retrieval of image. The JPEG image data stream is partitioned into three layers: 1) DC coefficients 2) High informative AC coefficients 3) Low informative AC coefficients. Even with strong error protection applied, in higher noisy environment undetected block error still exists in transmission stream which degrades the image quality. So it requires repairing of block errors. For repairing of block errors first the damaged blocks are detected then repaired using linear interpolation. The simulation results shows quality of recovered image can be improved using different error controlling techniques like UEP and error concealment.

Automated Training and Maintenance through KINECT

In this paper, we have worked on reducing burden on mechanic involving complex automobile maintenance activities that are performed in centralised workshops. We have presented a system prototype that combines Augmented Reality with Kinect. With the use of Kinect, very high quality sensors are available at considerably low costs, thus reducing overall expenditure for system design. The system can be operated either in Speech mode or in Gesture mode. The system can be controlled by various audio commands if user opts for Speech mode. The same controlling can also be done by using a set of Gestures in Gesture mode. Gesture recognition is the task performed by Kinect system. This system, bundled with RGB and Depth camera, processes the skeletal data by keeping track of 20 different body joints. Recognizing Gestures is done by verifying user movements and checking them against predefined condition. Augmented Reality module captures real-time image data streams from high resolution camera. This module then generates 3D model that is superimposed on real time data.

The Design of Image Acquisition and Preprocess System Based on FPGA

To deal with the large amount of data and complex computing problems during high-speed image acquisition, the image acquisition and preprocess system based on FPGA is designed in the paper. In order to obtain continuous and integrity of image data streams, the design has completed the acquisition of CCD camera video signal and implementation of de-interlacing ping-pong cache. The fast median filtering algorithm is used for image preprocessing, and finally the preprocessed image data is displayed on CRT. Experiments indicate that the design meets requirements of image sample quality and balances the real-time demand.

The neurointerventional procedure room of the future: predicting likely innovations in design and function

The Multispecialty Occupational Health Group, as part of their work, have considered likely characteristics of the neurointerventional surgery operating room of tomorrow. Such rooms will be distinguished by certain architectural...