Vehicle Detection and Attribution from a Multi-Sensor Dataset Using a Rule-Based Approach Combined with Data Fusion.

Vehicle detection using data fusion techniques from overhead platforms (RGB/MSI imagery and LiDAR point clouds) with vector and shape data can be a powerful tool in a variety of fields, including, but not limited to, national security, disaster relief efforts, and traffic monitoring. Knowing the location and number of vehicles in a given area can provide insight into the surrounding activities and patterns of life, as well as support decision-making processes. While researchers have developed many approaches to tackling this problem, few have exploited the multi-data approach with a classical technique. In this paper, a primarily LiDAR-based method supported by RGB/MSI imagery and road network shapefiles has been developed to detect stationary vehicles. The addition of imagery and road networks, when available, offers an improved classification of points from LiDAR data and helps to reduce false positives. Furthermore, detected vehicles can be assigned various 3D, relational, and spectral attributes, as well as height profiles. This method was evaluated on the Houston, TX dataset provided by the IEEE 2018 GRSS Data Fusion Contest, which includes 1476 ground truth vehicles from LiDAR data. On this dataset, the algorithm achieved a 92% precision and 92% recall. It was also evaluated on the Vaihingen, Germany dataset provided by ISPRS, as well as data simulated using an image generation model called DIRSIG. Some known limitations of the algorithm include false positives caused by low vegetation and the inability to detect vehicles (1) in extremely close proximity with high precision and (2) from low-density point clouds.

Assessment of Various Multimodal Fusion Approaches Using Synthetic Aperture Radar (SAR) and Electro-Optical (EO) Imagery for Vehicle Classification via Neural Networks.

Multimodal fusion approaches that combine data from dissimilar sensors can better exploit human-like reasoning and strategies for situational awareness. The performance of a six-layer convolutional neural network (CNN) and an 18-layer ResNet architecture are compared for a variety of fusion methods using synthetic aperture radar (SAR) and electro-optical (EO) imagery to classify military targets. The dataset used is the Synthetic and Measured Paired Labeled Experiment (SAMPLE) dataset, using both original measured SAR data and synthetic EO data. We compare the classification performance of both networks using the data modalities individually, feature level fusion, decision level fusion, and using a novel fusion method based on the three RGB-input channels of a residual neural network (ResNet). In the proposed input channel fusion method, the SAR and the EO imagery are separately fed to each of the three input channels, while the third channel is fed a zero vector. It is found that the input channel fusion method using ResNet was able to consistently perform to a higher classification accuracy in every equivalent scenario.

Target Classification in Synthetic Aperture Radar Images Using Quantized Wavelet Scattering Networks.

The need to classify targets and features in high-resolution imagery is of interest in applications such as detection of landmines in ground penetrating radar and tumors in medical ultrasound images. Convolutional neural networks (CNNs) trained using extensive datasets are being investigated recently. However, large CNNs and wavelet scattering networks (WSNs), which share similar properties, have extensive memory requirements and are not readily extendable to other datasets and architectures-and especially in the context of adaptive and online learning. In this paper, we quantitatively study several quantization schemes on WSNs designed for target classification using X-band synthetic aperture radar (SAR) data and investigate their robustness to low signal-to-noise ratio (SNR) levels. A detailed study was conducted on the tradeoffs involved between the various quantization schemes and the means of maximizing classification performance for each case. Thus, the WSN-based quantization studies performed in this investigation provide a good benchmark and important guidance for the design of quantized neural networks architectures for target classification.

The Spectrum Analysis Solution (SAS) System: Theoretical Analysis, Hardware Design and Implementation.

This paper describes a multichannel super-heterodyne signal analyzer, called the Spectrum Analysis Solution (SAS), which performs multi-purpose spectrum sensing to support spectrally adaptive and cognitive radar applications. The SAS operates from ultrahigh frequency (UHF) to the S-band and features a wideband channel with eight narrowband channels. The wideband channel acts as a monitoring channel that can be used to tune the instantaneous band of the narrowband channels to areas of interest in the spectrum. The data collected from the SAS has been utilized to develop spectrum sensing algorithms for the budding field of spectrum sharing (SS) radar. Bandwidth (BW), average total power, percent occupancy (PO), signal-to-interference-plus-noise ratio (SINR), and power spectral entropy (PSE) have been examined as metrics for the characterization of the spectrum. These metrics are utilized to determine a contiguous optimal sub-band (OSB) for a SS radar transmission in a given spectrum for different modalities. Three OSB algorithms are presented and evaluated: the spectrum sensing multi objective (SS-MO), the spectrum sensing with brute force PSE (SS-BFE), and the spectrum sensing multi-objective with brute force PSE (SS-MO-BFE).

On the Opportunities and Challenges in Microwave Medical Sensing and Imaging.

Widely used medical imaging systems in clinics currently rely on X-rays, magnetic resonance imaging, ultrasound, computed tomography, and positron emission tomography. The aforementioned technologies provide clinical data with a variety of resolution, implementation cost, and use complexity, where some of them rely on ionizing radiation. Microwave sensing and imaging (MSI) is an alternative method based on nonionizing electromagnetic (EM) signals operating over the frequency range covering hundreds of megahertz to tens of gigahertz. The advantages of using EM signals are low health risk, low cost implementation, low operational cost, ease of use, and user friendliness. Advancements made in microelectronics, material science, and embedded systems make it possible for miniaturization and integration into portable, handheld, mobile devices with networking capability. MSI has been used for tumor detection, blood clot/stroke detection, heart imaging, bone imaging, cancer detection, and localization of in-body RF sources. The fundamental notion of MSI is that it exploits the tissue-dependent dielectric contrast to reconstruct signals and images using radar-based or tomographic imaging techniques. This paper presents a comprehensive overview of the active MSI for various medical applications, for which the motivation, challenges, possible solutions, and future directions are discussed.

Design of a covert RFID tag network for target discovery and target information routing.

Radio frequency identification (RFID) tags are small electronic devices working in the radio frequency range. They use wireless radio communications to automatically identify objects or people without the need for line-of-sight or contact, and are widely used in inventory tracking, object location, environmental monitoring. This paper presents a design of a covert RFID tag network for target discovery and target information routing. In the design, a static or very slowly moving target in the field of RFID tags transmits a distinct pseudo-noise signal, and the RFID tags in the network collect the target information and route it to the command center. A map of each RFID tag's location is saved at command center, which can determine where a RFID tag is located based on each RFID tag's ID. We propose the target information collection method with target association and clustering, and we also propose the information routing algorithm within the RFID tag network. The design and operation of the proposed algorithms are illustrated through examples. Simulation results demonstrate the effectiveness of the design.

Enhanced resolution in Sar/ISAR imaging using iterative sidelobe apodization.

Resolution enhancement techniques in radar imaging have attracted considerable interest in recent years. In this work, we develop an iterative sidelobe apodization technique and investigate its applications to synthetic aperture radar (SAR) and inverse SAR (ISAR) image processing. A modified noninteger Nyquist spatially variant apodization (SVA) formulation is proposed, which is applicable to direct iterative image sidelobe apodization without using computationally intensive upsampling interpolation. A refined iterative sidelobe apodization procedure is then developed for image-resolution enhancement. Examples using this technique demonstrate enhanced image resolution in various applications, including airborne SAR imaging, image processing for three-dimensional interferometric ISAR imaging, and foliage-penetration ultrawideband SAR image processing.

Design and performance of a multiwavelength airborne polarimetric lidar for vegetation remote sensing.

The University of Nebraska has developed a multiwavelength airborne polarimetric lidar (MAPL) system to support its Airborne Remote Sensing Program for vegetation remote sensing. The MAPL design and instrumentation are described in detail. Characteristics of the MAPL system include lidar waveform capture and polarimetric measurement capabilities, which provide enhanced opportunities for vegetation remote sensing compared with current sensors. Field tests were conducted to calibrate the range measurement. Polarimetric calibration of the system is also discussed. Backscattered polarimetric returns, as well as the cross-polarization ratios, were obtained from a small forested area to validate the system's ability for vegetation canopy detection. The system has been packaged to fly abroad a Piper Saratoga aircraft for airborne vegetation remote sensing applications.