Feature evaluation for target/background discrimination in image sequences taken by approaching sensors

In order to address the problem of tracking different moving targets in image sequence against a complicated background, this paper presents a particle-filter multi-target tracking algorithm based on their dynamic salient features. By making use of the research findings on visual attention, the algorithm adopts the robust dynamic salient features as a result of combining the gray-scale and details with the motion characteristics of such targets as the state vector of particle filter. The algorithm is highly robust as it contains salient features originating from the low-level features of the targets. Meanwhile the particle filter allows optimized estimation of non-linear and non-Gaussian models. As a consequence, the algorithm is capable of managing traces in tracking different targets and dealing with their appearance, disappearance, mergence, splitting and sheltering by obstacles. Experiments show that this new algorithm enables tracking of multiple targets in complicated image sequence.

This paper addresses the problem of designing an efficient and effective image sequence processing scheme that will successfully detect very small (point) targets in a cluttered background when both the target and clutter are moving through the image scene. The specific application area was detection of targets such as airplanes in infrared (IR) image sequences of a cloudy sky which have been taken by a stationary camera. In general we assume that targets are typically one to two pixels in extent and move only a fraction of a pixel per frame, are often low amplitude, and are found in scenes which also contain evolving clutter, e.g. clouds. Our algorithm is based on signal processing and detection theory, includes a perfect measurement performance analysis, and can be made computationally efficient compared to other approaches. Thus the algorithm could be applicable to other image sequence processing scenarios, using other acquisition systems besides IR, such as detection of small moving objects or structures in a biomedical or biological imaging scenario or the detection of satellites, meteors or other celestial bodies in night sky imagery acquired using a telescope. We present a GLRT solution, perfect measurement analysis including ROC curves, and results using real-world infrared data.

In the test range, it is a practical significance to use photoelectric theodolite to obtain the 3D pose of flying object by tracking and recording flying target in image sequences. In this paper, the image is obtained by using the two long-distance theodolite; namely, the target pose measurement is attained by dealing with the large baseline target images. Because the large baseline target is small, weak and details are not prominent. Image is enhanced by using the method of frequency-domain image enhancement. The camera self-calibration is based on the method of fundamental matrix; the 3D pose is calculated by feature point DLT algorithm and beam adjustment method. Experimental results showed that the measuring error of the attitude angle was less 0.1°, when the axis of the plane imaging was more than 500 pixels. According to the test results of the precision comparison, it was concluded that the mathematical model is correct and the algorithm is reasonable in improving effectively the measurement precision of the target pose.

This paper presents an approach for the detection of moving point targets in very low SNR based on purely time-domain analysis of pixels. The problem of detecting point targets in image sequences is formulated as a one-dimensional weak transient signal detection problem. The mathematical model of the transient signal is proposed. The key impact factors, such as the frame-rate, target velocity and SNR of the weak transient signal are studied. The detection ability is evaluated from the view of time-domain energy accumulation and correlation. The experimental results with both simulated and realworld data demonstrate that our approach can efficiently detect extremely low-SNR targets and the detection ability is decided by the key impact factors.

We describe an active contour based local energy minimization point distribution, behavior of orientation, relaxation iterative algorithm that estimates feature points of static target in image sequence. In our approach, we build a contour model of a target to get some of low-energy points kernels. The use of snake based line model results in more reliable convergence of the point local energy minimization. The algorithm uses auto-relation relation to give the behavior of orientation in a local kernel's window. It uses local window-based probability method to refine the current corresponding relations of scene kernels. Results are illustrated on real outdoor image sequence.

BP gas production operations in North America manages over 15,000 miles of onshore pipelines that make up our vast, complex, and aging gas gathering networks. Surveying these for leaks presents a huge resource challenge using current ground based technology and, in turn, impacts the assurance of the safety and integrity of these operations. The Exploration and Production Technology Group evaluated new leak detection technologies using laser, thermal imaging camera and a high speed gas sampling detector that were deployed on aircraft and used global positioning systems coordinates to survey gas gathering pipelines. Field trials on gas gathering systems in the North Texas, Anadarko asset showed that the laser and gas sampling based leak detection systems were the most accurate, but the video imaging from the thermal camera made a powerful statement. Helicopters proved to be more suitable in leak detection surveys on gas gathering pipelines than that of fixed-wing aircraft. The aerial leak detection technologies produce a significant increase in efficiency and productivity in managing the integrity of BP’s gas gathering systems. While that improves business performance, perhaps more importantly is the fact that small gas leaks can be easily found before they become big ones. That reduces environmental damage and the potential for leaks to impact the public. The development and implementation of aerial leak detection in BP is being recognized as an integrity tool in providing a significantly improved integrity assurance to its gas gathering operations. A. Introduction The Exploration and Production Technology Group (EPTG) has worked closely with leading companies in the development of aerial gas leak detection technologies capable and suitable to the BP North America operations in gas production. Also potential applications lie in operations outside of North America as well as future capital projects. The safety and integrity of BP operations has become increasing important as the oil and gas industry has become closely watched and scrutinized by stakeholders, government agencies and the public. BP has been working diligently in providing assurance to its facilities and processes especially its gas gathering systems. BP strives to achieve its safety values where No Accidents, No Harm to People, and No Damage to the Environment within its operations. Several companies that were evaluated employing leading technologies in gas leak detection systems (LDS). Three different technologies for gas leak detection systems are laser, thermal camera, and sophisticated gas sampling based detection technologies and were tested in field trials. All of these technologies were installed on aircraft either helicopters or fixed-wing aircraft and can be deployed on the ground via vehicle mounted or hand held use. The remote detection capabilities of these technologies were attractive features that showed promise in using it on the BP gas gathering systems in order to meet its safety and integrity in the operation of gas gathering systems (GGS). B. Leak Detection Technologies The following technologies were reviewed: lasers, thermal camera and gas sampling based systems for leak detection systems (LDS). These hardware technologies have remote capabilities and can detect and locate leaks from a distance that can be deployed on fast moving aircraft giving them rapid measurement capabilities. There are obvious advantages in using aircraft compared to ground methods and will be discussed in the following section. Lasers (in the infrared wavelength) using light detection and radar (LIDAR) principles, similar to that of

Evaluating curve progression in adolescent idiopathic scoliosis (AIS) patients involves repeated exposure to radiation. Rasterstereography is reported to be a reliable, valid alternative to classic radiography. Few studies have evaluated rasterstereography's responsiveness in detecting curve progression over time or how brace treatment might influence these results. The present study aimed to evaluate rasterstereography and scoliometer measurement responsiveness in detecting curve progression in a large cohort of AIS patients with a follow-up time of > 6months and comparing brace-treated and non-braced patients. We included consecutively AIS patients who underwent same-day rasterstereography, scoliometer and radiography evaluations from 2016 to 2018, with at least 6months between visits. Each patient's major scoliosis curve was evaluated using their Cobb angle (CA) from radiography, their scoliosis angle (SA) from rasterstereography and their axial trunk rotation (ATR) angle from scoliometer measurement. Patients were separated into brace-treated and non-braced groups. Progressive curves were defined by an increase in CA ≥ 5°. The area under the curve (AUC) of non-parametric receiver operating characteristics (ROC) curves was used to assess responsiveness of SA and ATR in detecting progressive curves. We reported sensitivity and specificity. One-hundred-and-eleven AIS patients (55 brace-treated, 56 non-braced) were evaluated, of whom 17 (16%) had progressive curves: 10/55 (18%) brace-treated and 7/56 (13%) non-braced patients. We found poor AUC and sensitivity (< 50%) in detecting progressive curves among brace-treated patients. However, we found a good AUC (> 75%) and moderate sensitivity (< 70%) in detecting progressive curves among non-braced patients. Rasterstereography and scoliometer measurements both showed poor and moderate sensitivity in detecting curve progression in brace-treated and non-braced AIS patients, respectively. This suggests that rasterstereography should not be used to monitor curve progression among AIS patients to reduce their exposure to radiation, particularly among brace-treated patients. Presents results adds to ongoing debates about surface topography's role in AIS monitoring, particularly for braced patients where torso shape changes may confound measurements. Although rasterstereography and scoliometer lacks sufficient sensitivity to serve as a standalone monitoring tool, these results identify untreated patients as the most promising target population for future technological refinements of surface topography.

The detection of human beings in a camera attracts more attention because of its wide range of applications such as abnormal event detection, person counting in a dense crowd, person identification, fall detection for care to elderly people, etc. Over the time, various techniques have evolved to enhance the visual information. This article presents a novel 3-D intelligent information system for identifying abnormal human activity using background subtraction, rectification, morphology, neural networks and depth estimation with a thermal camera and a pair of hand held Universal Serial Bus (USB) camera to visualize un-calibrated images. The proposed system detects strongest points using Speed-Up Robust Features (SURF). The Sum of Absolute Difference (SAD) algorithm match the strongest points detected by SURF. 3-D object model and image stitching from image sequences are carried out in the proposed work. A series of images captured from different cameras are stitched into a geometrically consistent mosaic either horizontally/vertically based on the image acquisition. 3-D image and depth estimation of un-calibrated stereo images are acquired using rectification and disparity. The background is separated from the scene using threshold approach. Features are extracted using morphological operators in order to get the skeleton. Junction points and end points of the skeleton image are obtained from the skeleton. Data set of abnormal human activity is created using supervised learning such as neural network with a thermal camera and a pair of webcam. The feature vector of an activity is compared with already created data set, if a match occurs the classifier detects abnormal human activity. Additionally the proposed algorithm performs depth estimation to measure real time distance of objects dynamically. The system use thermal camera, Intel computing stick, converter, video graphics array (VGA) to high-definition multimedia interface (HDMI) and webcams. The proposed novel intelligent information system gives 94% maximum accuracy and 89% minimum accuracy for different activities, thus it effectively detects suspicious activity during day and night.

Despite the significant progress in diagnosis and treatment, breast cancer still continues to be the most common deadly disease occurring among women in the world. Histopathological analysis is the standard method for breast cancer diagnosis. Manual inspection of histological samples is a highly specialized and time consuming task. Computer-Aided Diagnosis Systems (CAD) could overcome the limitations of manual analysis and assist pathologists to diagnose cancer more accurately and efficiently. Hence, we propose a novel approach that uses deep learned nucleus feature classifier fusion framework for breast cancer detection from histopathological images. Recently, convolutional neural networks (CNNs) have produced high recognition rates compared to hand crafted features but results in much higher complexity in network design. Moreover, designing CNN from scratch requires large amount of training data. So, we use pretrained CNNs for feature extraction. Extracted features are fused using norm pooling and fed to Support Vector Machine (SVM) for classification. Classification results using the different CNNs are fused using belief theory based fusion. Performance analysis is done using accuracy, sensitivity, specificity, receiver operating characteristics (ROC) curve and AUC (Area under the ROC curve) measures. Results comparable to the current state of the art is achieved.

Change detection in image sequences has mainly focused on the recovery of moving objects when the viewing system is static, or on the detection of simple production effects such as video shot boundaries or scene transitions. Camera motion is usually handled by the compensation of dominant motion, using motion estimation and segmentation schemes. We propose a novel statistical change detection method able to handle more complex events such as entering or exiting objects, or changes in object appearance, when the camera is moving. Temporal changes of objects are captured by analyzing the statistics of successive images. Considering an appropriate choice of image features, we show how it is possible to extract the statistics of changing objects from a pair of successive image histograms. Changing objects are then located by statistical backprojection techniques. The method is completely unsupervised and does not require any motion estimation or motion compensation. It is illustrated here on real world road scenes exhibiting large camera motion.

Small target detection using bilateral filter and temporal cross product in infrared images

This paper describes a new wavelet-transform-based nonlinear spatial filter called the scale subtraction filter (SSF). The SSF enhances dim target signals relative to clutter in forward- looking infrared (FLIR) imagery using the scale characteristics of the target. The SSF was applied to a database of FLIR image sequences representing different target, sensor, and background clutter scenarios. Detection performance was quantified in terms of the receiver operating characteristics (ROC) for all sequences. The detection performance of the new algorithm was compared to the Holmes double-grated filter method and was found to be equivalent or significantly better depending on the image sequence.

The purpose of this study was to investigate the diagnostic efficacy of a range of conventional magnetic resonance imaging (MRI) pulse sequences in the identification of internuclear ophthalmoplegia (INO) caused by medial longitudinal fasciculus (MLF) lesions in multiple sclerosis patients using a receiver-operating characteristic (ROC) methodology. A total of 15 clinically confirmed INO and 15 control subjects underwent conventional MRI at 1.5 T consisting of T2-weighted, proton density (PD)-weighted, and fluid-attenuated inversion recovery (FLAIR) sequences, following full institutional approval. A free-response, multiple-reader multiple-case design ROC study was used to evaluate the diagnostic efficacy of each sequence. All imaging sequences were evaluated by 10 board-certified neuroradiologists. Area under the curve (AUC), sensitivity, and specificity were analysed statistically for all three pulse sequences using repeated-measures analyses of variance and post-test analysis using Bonferroni's multiple comparison test of differences. No significant AUC differences were found between the three sequences (p = 0.0697), with T2 recording the highest AUC (0.8346). Sensitivity differences between PD (0.7927) and FLAIR (0.6329) were significant (p < 0.05). Non-significant differences were also evident between T2 and FLAIR (p = 0.0511). The specificity analysis revealed an overall difference (p = 0.0005), with specific inter-sequence differences shown between T2 and PD (p < 0.05) and PD and FLAIR (p < 0.001) with the PD values being lower than those provided with the other two sequences. T2-weighted axial imaging through the MLF region resulted in the greatest overall diagnostic efficacy when viewing a combination of mean AUC, sensitivity, and specificity, in terms of the identification of INO-causing lesions.

Achieving high-resolution thermal imagery in low-contrast lake surface waters by aerial remote sensing and image registration

Most research in vision-based driver assistance has utilized graylevel or color image sequences. Since the spatial arrangement of scene objects is often more relevant than the reflected brightness information, there has been an increasing interest in range sensors for collision avoidance systems recently. In our approach for obstacle detection and tracking, obstacles are defined as non-traversable objects. Thus obstacle detection is done by checking the traversability of the environment in the sensor's field of view. Once an obstacle is detected, it is tracked along the time axis. Robust long-term tracking is performed by the analysis of the spatial arrangement of obstacles. Our tracking scheme handles problems as occlusion, new appearance or disappearance of scene objects. To be robust against segmentation errors and poor reflection properties of scene objects, splitting of obstacles is taken into account. Our approach was tested on 11 range image sequences consisting of 447 frames. Different scenarios such as driving along a curve, oncoming traffic, high relative velocity between vehicles, and heavy traffic were investigated.© (1998) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.