Target Detection

Summary. 1. Audiograms are recorded from one non-echolocating and nine echolocating sympatri-cally living bat species of South India. These spe-cies are Cynopterus sphinx (non-echolocating), Ta-darida aegyptiaca, Taphozous melanopogon, T. kachhensis, ...

Honeybees Apis mellifera were trained to distinguish between the presence and the absence of a rewarded coloured spot, presented on a vertical, achromatic plane in a Y-maze. They were subsequently tested with different subtended visual angles of that spot, generated by different disk diameters and different distances from the decision point in the device. Bees were trained easily to detect bee-chromatic colours, but not an achromatic one. Chromatic contrast was not the only parameter allowing learning and, therefore, detection: α min, the subtended visual angle at which the bees detect a given stimulus with a probability P 0 = 0.6, was 5° for stimuli presenting both chromatic contrast and contrast for the green photoreceptors [i.e. excitation difference in the green photoreceptors, between target and background (green contrast)], and 15° for stimuli presenting chromatic but no green contrast. Our results suggest that green contrast can be utilized for target detection if target recognition has been established by means of the colour vision system. The green-contrast signal would be used as a far-distance signal for flower detection. This signal would always be detected before chromatic contrast during an approach flight and would be learned in compound with chromatic contrast, in a facilitation-like process.

This paper presents the design and implementation of a vision-based navigation and landing algorithm for an autonomous helicopter. The vision system allows to define target areas from a high resolution aerial or satellite image to determine the waypoints of the navigation trajectory or the landing area. The helicopter is required to navigate from an initial position to a final position in a partially known environment using GPS and vision, to locate a landing target (a helipad of a known shape or a natural landmark) and to land on it. The vision system, using a feature-based image matching algorithm, finds the area and gives feedbacks to the control system for autonomous landing. Vision is used for accurate target detection, recognition and tracking. The helicopter updates its landing target parameters owing to vision and uses an on board behavior-based controller to follow a path to the landing site. Results show the appropriateness of the vision-based approach that does not require any artificial landmark (e.g., helipad) and is quite robust to occlusions, light variations and seasonal changes (e.g., brown or green leaves).

Layered sensing provides a hierarchical net-centric architecture for universal situational awareness with global coverage and persistent surveillance. Sensors in the layered hierarchy provide spatial, temporal, spectral, and polarization diversity with different scales and resolutions over different time horizons. Cooperative management of netted sensors is a successful strategy to achieve targeting performance and overall measures of merit (MOM) goals. After a brief introduction to issues in layered sensors, a resource management strategy based on geometry information is described so as to enhance performance in target detection (minimum detectable Doppler) and tracking accuracy (geometric dilution of precision). Preliminary simulation results are presented to illustrate this Geometric Approach to Layered Sensing (GALS) concept.

Kablosuz Algılayıcı Ağlar (KAA); bilginin toplanması, kısmi işlenmesi ve iletimi için tasarlanmış, dağıtık uygulama ve ortak hareket edebilme kabiliyetine sahip ancak sınırlı hafıza, sınırlı işlem gücü, sınırlı güç kaynağı ve sınırlı iletim dezavantajlarını barındıran algılayıcı düğümlerden oluşan sistemlerdir. KAA sistemlerinin askeri amaçlı olarak kritik bina, bölge güvenliği ve sınır izleme amaçlı kullanımı uzun zamandan bu yana araştırılmakta, önemli model ve uygulamalar ortaya konulmaktadır. BU tez çalışmamızda KAA yapısının askeri maksatlı kullanımı için kurulum ve işletim maliyetlerin düşürülmesi, sistemden alınacak hedef tespit ve izleme verilerine verilecek olası tepkilerin anlamlı hale getirilmesi hedeflenmiştir. Çalışmamızda yaygın olan görüntü işleme tabanlı sistemler yerine hedefin konum, hız ve yükseklik/boy bilgilerinin işlenmesi yolu ile tehdit analizi yapabilecek DEVS tabanlı bir güvenlik modeli ortaya konmuştur.

ABSTRACT Individuals with high-functioning autism spectrum disorder (HF-ASD) often show superior performance in simple visual tasks, despite difficulties in the perception of socially important information such as facial expression. The neural basis of visual perception abnormalities associated with HF-ASD is currently unclear. We sought to elucidate the functioning of bottom-up and top-down visual information processing in HF-ASD using event-related potentials (ERPs). Eleven adults with HF-ASD and 11 age-matched normal controls (NC) participated in this study. Visual ERPs were recorded using 128-channel EEG. The P1 and P300 were recorded in response to target stimuli. Visual mismatch negativity (vMMN) potentials were obtained by subtracting responses to standard from those to deviant stimuli. Behaviorally, individuals with HF-ASD showed faster target detection than NCs. However, vMMN amplitude and latency were the same between the two groups. In contrast, P1 and P300 amplitudes were significantly decreased in HF-ASD compared with NCs. In addition, P300 latency was significantly delayed in HF-ASD. Individuals with HF-ASD exhibit altered visual information processing. Intact bottom-up attention (vMMN) may contribute to their superior simple visual task performance in spite of abnormal low-level (P1) and top-down (P300) visual information processing.

The paper deals with the cancellation of direct signal, multipath and clutter echoes in passive radar, where the transmitted waveform is not under control of the radar designer and the sidelobes of the ambiguity function mask even targets largely displaced in range and Doppler from the disturbance. A sequential approach is presented for disturbance cancellation and target detection based on projections of the received signals in a subspace orthogonal to both disturbance and previously detected targets. Modeling the clutter spread on few Doppler bins allows complete clutter cancellation. The approach is shown to be effective against typical scenarios with a limited number of iterations.

Target detection is the front-end stage in any automatic target recognition system for synthetic aperture radar (SAR) imagery (SAR-ATR). The efficacy of the detector directly impacts the succeeding stages in the SAR-ATR processing chain. There are numerous methods reported in the literature for implementing the detector. We offer an umbrella under which the various research activities in the field are broadly probed and taxonomized. First, a taxonomy for the various detection methods is proposed. Second, the underlying assumptions for different implementation strategies are overviewed. Third, a tabular comparison between careful selections of representative examples is introduced. Finally, a novel discussion is presented, wherein the issues covered include suitability of SAR data models, understanding the multiplicative SAR data models, and two unique perspectives on constant false alarm rate (CFAR) detection: signal processing and pattern recognition. From a signal processing perspective, CFAR is shown to be a finite impulse response band-pass filter. From a statistical pattern recognition perspective, CFAR is shown to be a suboptimal one-class classifier: a Euclidean distance classifier and a quadratic discriminant with a missing term for one-parameter and two-parameter CFAR, respectively. We make a contribution toward enabling an objective design and implementation for target detection in SAR imagery.

Automatic target detection methods for synthetic aperture radar (SAR) images are sensitive to image resolution, size of the target to be detected, clutter complexity, and speckle noise level. A robust automatic target detection method needs to be less sensitive to the above factors. In this study, a constant false alarm rate (CFAR) based automatic target detection method which can find a target and its heterogeneous clutter independent of the image resolution and the target size has been developed. The proposed method provides efficient memory usage and low computational complexity.

The purpose of this paper is to survey and assess the state-of-the-art in automatic target recognition for synthetic aperture radar imagery (SAR-ATR). The aim is not to develop an exhaustive survey of the voluminous literature, but rather to capture in one place the various approaches for implementing the SAR-ATR system. This paper is meant to be as self-contained as possible, and it approaches the SAR-ATR problem from a holistic end-to-end perspective. A brief overview for the breadth of the SAR-ATR challenges is conducted. This is couched in terms of a single-channel SAR, and it is extendable to multi-channel SAR systems. Stages pertinent to the basic SAR-ATR system structure are defined, and the motivations of the requirements and constraints on the system constituents are addressed. For each stage in the SAR-ATR processing chain, a taxonomization methodology for surveying the numerous methods published in the open literature is proposed. Carefully selected works from the literature are presented under the taxa proposed. Novel comparisons, discussions, and comments are pinpointed throughout this paper. A twofold benchmarking scheme for evaluating existing SAR-ATR systems and motivating new system designs is proposed. The scheme is applied to the works surveyed in this paper. Finally, a discussion is presented in which various interrelated issues, such as standard operating conditions, extended operating conditions, and target-model design, are addressed. This paper is a contribution toward fulfilling an objective of end-to-end SAR-ATR system design.

With the advances in remote sensing domain, images with higher spatial and spectral resolution are obtained from increasing number of sensors, and they have been employed in more research fields, including object detection and tracking. In particular, the detection of marine vehicles has a significant role in civil and military applications. However, due to the varying type, size, posture, and complex background of the ships to be detected, ship target detection is still considered as a challenging task. Deep learning techniques with their widespread use in computer vision applications have been successfully applied to object detection problems that is important to monitor marine traffic and ensure maritime safety. In this study, a freely available aerial image dataset is utilized to train and test the two popular single-stage object detection models, namely YOLOv4 and Tiny YOLOv4, based on the “You Only Look Once” approach. Produced results were analyzed using conventional accuracy metrics, and average prediction times were also compared. The trained models were evaluated on different ship images and detections were performed. As a result of the study, mean average precision (mAP) values of 80.82% and 62.30% were obtained using YOLOv4 and Tiny YOLOv4 architectures, respectively. This indicates major performance difference between YOLOv4 and Tiny YOLOv4 models for ship detection studies.

In this paper, we address the issue of handling uncertainty and information fusion for an efficient WSN deployment. We present a flexible framework for collaborative target detection within the transferable belief model. Using the developed framework, we propose an uncertainty-aware deployment algorithm that is able to determine the minimum number of sensors and their locations such that full area coverage is achieved. The issues of connectivity, obstacles, preferential coverage, challenging environments and sensor reliability are also discussed. Experimental results are provided to demonstrate the ability of our approach to achieve an efficient sensor deployment by exploiting a collaborative target detection scheme.