Concealed weapon detection using UWB 3-D radar imaging and automatic target recognition

Diabetic macular edema (DME) is a major cause of visual loss in the patients with diabetic retinopathy. DME detection in Optical Coherence Tomography (OCT) image contributes to the early diagnosis of diabetic retinopathy and blindness prevention. Currently, DME detection in the OCT image mainly relies on the handwork by the experienced clinician. It is a laborious, time-consuming, and challenging work to organize a comprehensive DME screening for diabetic patients. In this study, we proposed a novel algorithm for the detection and segmentation of DME region in OCT image based on the K-means clustering algorithm and improved Selective Binary and Gaussian Filtering regularized level set (SBGFRLS) algorithm named as SBGFRLS-OCT algorithm. SBGFRLS-OCT algorithm was compared with the current level set algorithms, including C-V (Chan-Vese), GAC (geodesic active contour), and SBGFRLS, to estimate the performance of DME detection. SBGFRLS-OCT algorithm was also compared with the clinician to estimate the precision, sensitivity, and specificity of DME segmentation. Compared with C-V, GAC, and SBGFRLS algorithm, the SBGFRLS-OCT algorithm enhanced the accuracy and reduces the processing time of DME detection. Compared with manual DME segmentation, the SBGFRLS-OCT algorithm achieved a comparable precision (97.7%), sensitivity (91.8%), and specificity (99.2%). Collectively, this study presents a novel algorithm for DME detection in the OCT image, which can be used for mass diabetic retinopathy screening.

This paper proposes a method for recognition and classification of 3D objects using 2D moments and HMLP network. The 2D moments are calculated based on 2D intensity images taken from multiple cameras that have been arranged using multiple views technique. 2D moments are commonly used for 2D pattern recognition. However, the current study proves that with some adaptation to multiple views technique, 2D moments are sufficient to model 3D objects. In addition, the simplicity of 2D moment's calculation reduces the processing time for feature extraction, thus decreases the recognition time. The 2D moments were then fed into a neural network for classification of the 3D objects. In the current study, hybrid multi-layered perceptron (HMLP) network is proposed to perform the classification. Two distinct groups of objects that are polyhedral and free-form objects were used to access the performance of the proposed method. The recognition results show that the proposed method has successfully classified the 3D object with the accuracy of up to 100%.

We propose a framework for three-dimensional (3D) object recognition and classification in very low illumination environments using convolutional neural networks (CNNs). 3D images are reconstructed using 3D integral imaging (InIm) with conventional visible spectrum image sensors. After imaging the low light scene using 3D InIm, the 3D reconstructed image has a higher signal-to-noise ratio than a single 2D image, which is a result of 3D InIm being optimal in the maximum likelihood sense for read-noise dominant images. Once 3D reconstruction has been performed, the 3D image is denoised and regions of interest are extracted to detect 3D objects in a scene. The extracted regions are then inputted into a CNN, which was trained under low illumination conditions using 3D InIm reconstructed images, to perform object recognition. To the best of our knowledge, this is the first report of utilizing 3D InIm and convolutional neural networks for 3D training and 3D object classification under very low illumination conditions.

Inverse synthetic aperture radar (ISAR) imaging is an effective method to identify unknown targets regardless of weather and illumination conditions. Research results published regarding this topic have focused mainly on imaging and automatic target recognition (ATR) of single targets. However, targets generally fly in formation, so the applicability of ISAR images to ATR of multiple targets must be studied. This paper proposes an ATR procedure for targets flying in formation. ATR accuracy derived using five targets composed of point scatterers and the measured radar signal of a Boeing 747 aircraft was as high as that of the solo flight in terms of SNR and the size of the training database; this result shows that ISAR is an adequate tool for ATR even if an image is contaminated by radar reflections from neighboring targets.

With the rapid development of computer vision technology and the maturity of 2D object detection technology, 3D object detection has attracted more and more attention of scholars. As an extension of 2D object detection, 3D object detection can not only detect the object category and position in the image, but also output the spatial position and pose angle of the object in a certain 3D coordinate system. It has a considerable application prospects in automatic driving, robot operation and augmented reality. However, 3D object detection is much more difficult than 2D object detection, and it is very difficult to make and label the data set, which has high hardware requirements. At present, there is no dominant algorithm, and scholars use a variety of methods. In order to solve the above problems, this paper proposes a method of making and synthesising 3D object detection data sets. Based on the improved 2D object detection algorithm, 3D object detection of single RGB image is realised.

Hyper spectral image are used in various applications such as geological systems, geo sciences and astronomy. These images are acquired using remote sensing. Remote sensing is the process of getting information about an object without making any physical contact with the object. Satellite Images referred as hyper spectral images are the most used images in remote sensing and are of more interest to find out the classification of objects in those images. The classification can give us the important factors like vegetation, buildings, roads and more. Satellite images can be of assistance in supervision of effects due to natural disasters, to recognize mining areas which are hidden from human view, biodiversity examination, rural and urban environment detection for analysis, etc. However, occasionally the Satellite images acquired can be affected by unforeseen distortions, artificial unwanted structures called artifacts that are formed by the tool itself or sometimes due to the diverse pre-processing procedures involved. Optimization algorithms in combination with Image processing methods are used to classify the objects in satellite images for easy perception and analysis. In this paper, various optimization techniques like particle swarm optimization (PSO), DPSO, HSO, and Proposed MFA optimization algorithms are compared to obtain optimal classification of objects in a satellite image.

Object detection in images is a computing demanding task which usually needs to deal with the detection of different classes of objects, and thus requiring variations and adaptations easily provided by software solutions. Object detection algorithms are being part of real-time smarter embedded systems, such as automotive, medical, robotics and security systems. In most embedded systems, efficient implementations of object oriented algorithms need to provide high performance, low power consumption, and programmability to allow greater development flexibility. The Histogram of Oriented Gradients (HOG) is one of the most widely used algorithms for object detection in images. In this paper, we show our work towards mapping the HOG algorithm to an FPGA-based system consisting of multiple Nios II softcore processors and bearing in mind high-performance and programmability issues. We show how to reduce 19x the algorithms execution time by source to source transformations and specially avoiding redundant processing. Furthermore, we show how the use of pipelining processing using three Nios II processors allows a speedup of 49x compared to the embedded baseline application.

We present a novel approach to measuring distances between objects in images, suitable for information-rich object representations which simultaneously capture several properties in each image pixel. Multiple spatial fuzzy sets on the image domain, unified in a vector-valued fuzzy set, are used to model such representations. Distance between such sets is based on a novel point-to-set distance suitable for vector-valued fuzzy representations. The proposed set distance may be applied in, e.g., template matching and object classification, with an advantage that a number of object features are simultaneously considered. The distance measure is of linear time complexity w.r.t. the number of pixels in the image. We evaluate the performance of the proposed measure in template matching in presence of noise, as well as in object detection and classification in low resolution Transmission Electron Microscopy images.

Detection of objects in images in an automated fashion is necessary for many applications, including automated target recognition. In this paper, we present results of boundary detection using Markov random fields. Once the boundaries of regions are detected, object recognition can be conducted to classify the regions within the boundaries. Thus, an approach that gives good boundary detection is very important in many automated target recognition systems. Our algorithm for boundary detection combines Bayesian approach with a histogram specification technique to locate edges of objects that have a closed-loop boundary. The boundary image is modeled by a Markov random field. The method is relatively insensitive to the input parameters required by the user and provides a fairly robust automated detection procedure that produces an image with closed one-pixel-wide boundaries. We apply our method to mine data with very good results.

In this paper, we propose SparseDet for end-to-end 3D object detection from point cloud. Existing works on 3D object detection rely on dense object candidates over all locations in a 3D or 2D grid following the mainstream methods for object detection in 2D images. However, this dense paradigm requires expertise in data to fulfill the gap between label and detection. As a new detection paradigm, SparseDet maintains a fixed set of learnable proposals to represent latent candidates and directly perform classification and localization for 3D objects through stacked transformers. It demonstrates that effective 3D object detection can be achieved with none of post-processing such as redundant removal and non-maximum suppression. With a properly designed network, SparseDet achieves highly competitive detection accuracy while running with a more efficient speed of 34.5 FPS. We believe this end-to-end paradigm of SparseDet will inspire new thinking on the sparsity of 3D object detection.

Many applications reported in artificial neural networks are associated with military problems. This paper reviews concepts associated with the processing of military data to find and recognize targets -- automatic target recognition (ATR). A general-purpose automatic target recognition system does not exist. The work presented here is demonstrated on military data, but it can only be considered proof of principle until systems are fielded and proven `under- fire.' ATR data can be in the form of nonimaging one-dimensional sensor returns, such as ultra-high range-resolution radar returns (UHRR) for air-to-air automatic target recognition and vibration signatures from a laser radar for recognition of ground targets. The ATR data can be two-dimensional images. The most common ATR images are infrared, but current systems must also deal with synthetic aperture radar (SAR) images. Finally, the data can be three-dimensional, such as sequences of multiple exposures taken over time from a nonstationary world. Targets move, as do sensors, and that movement can be exploited by the ATR. Hyperspectral data, which are views of the same piece of the world looking at different spectral bands, is another example of multiple image data; the third dimension is now wavelength and not time. ATR system design usually consists of four stages. The first stage is to select the sensor or sensors to produce the target measurements. The next stage is the preprocessing of the data and the location of regions of interest within the data (segmentation). The human retina is a ruthless preprocessor. Physiologically motivated preprocessing and segmentation is demonstrated along with supervised and unsupervised artificial neural segmentation techniques. The third design step is feature extraction and selection: the extraction of a set of numbers which characterize regions of the data. The last step is the processing of the features for decision making (classification). The area of classification is where most ATR related neural network research has been accomplished. The relation of neural classifiers to Bayesian techniques is emphasized along with the more recent use of feature sequences to enhance classification. © (1995) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.

Artificial intelligence and machine learning have great ability to solve real-time problems related to various fields and have many applications. One such subfield is deep learning, deep learning has many architectures like DNN, CNN and RNN. One of the major applications of deep learning is object detection. YOLO a SOTA object detector considered to be a smart convolutional neural network having capability of detecting objects in the image, classifying them accordingly and localizing the object perfectly with annotations. YOLOv4 is employed in this work for multiple object detection in image and video for traffic surveillance applications trained using a custom dataset created with Indian road traffic images. 9 different classes namely Car, Bus, Van, Truck, Two-wheeler, Auto, Person, Bicycle and Mini truck are considered in creating custom dataset. Proposed custom model trained for 500 epochs with a custom image dataset has achieved a training mAP of 92% and a training loss of 0.001. Achieved an accuracy of 99.28%, sensitivity of 94.44% and MCC of 96.78% on unseen or test dataset. Proposed model predicted all the classes with an average precision of 98.32%. This proves that our model is robust and proficient in detecting road traffic classes and has scope in developing traffic surveillance systems.

Currently, lung cancer has one of the highest mortality rates because it is often caught too late. Therefore, early detection is essential to reduce the risk of death. Pulmonary nodules are considered key indicators of primary lung cancer. Developing an efficient and accurate computer-aided diagnosis system for pulmonary nodule detection is an important goal. Typically, a computer-aided diagnosis system for pulmonary nodule detection consists of two parts: candidate nodule extraction and false-positive reduction of candidate nodules. The reduction of false positives (FPs) of candidate nodules remains an important challenge due to morphological characteristics of nodule height changes and similar characteristics to other organs. In this study, we propose a novel multi-scale heterogeneous three-dimensional (3D) convolutional neural network (MSH-CNN) based on chest computed tomography (CT) images. There are three main strategies of the design: (1) using multi-scale 3D nodule blocks with different levels of contextual information as inputs; (2) using two different branches of 3D CNN to extract the expression features; (3) using a set of weights which are determined by back propagation to fuse the expression features produced by step 2. In order to test the performance of the algorithm, we trained and tested on the Lung Nodule Analysis 2016 (LUNA16) dataset, achieving an average competitive performance metric (CPM) score of 0.874 and a sensitivity of 91.7% at two FPs/scan. Moreover, our framework is universal and can be easily extended to other candidate false-positive reduction tasks in 3D object detection, as well as 3D object classification.

This article presents a system for texture-based probabilistic classification and localization of 3D objects in 2D digital images and discusses selected applications.

Multiview synthetic aperture radar (SAR) images contain much richer information for automatic target recognition (ATR) than a single-view one. It is desirable to establish a reasonable multiview ATR scheme and design effective ATR algorithm to thoroughly learn and extract that classification information, so that superior SAR ATR performance can be achieved. Hence, a general processing framework applicable for a multiview SAR ATR pattern is first given in this paper, which can provide an effective approach to ATR system design. Then, a new ATR method using a multiview deep feature learning network is designed based on the proposed multiview ATR framework. The proposed neural network is with a multiple input parallel topology and some distinct deep feature learning modules, with which significant classification features, the intra-view and inter-view features existing in the input multiview SAR images, will be learned simultaneously and thoroughly. Therefore, the proposed multiview deep feature learning network can achieve an excellent SAR ATR performance. Experimental results have shown the superiorities of the proposed multiview SAR ATR method under various operating conditions.