ALBERT

Description: Sensors, Vol. 18, Pages 2915: Flood Detection in Gaofen-3 SAR Images via Fully Convolutional Networks Sensors doi: 10.3390/s18092915 Authors: Wenchao Kang Yuming Xiang Feng Wang Ling Wan Hongjian You Emergency flood monitoring and rescue need to first detect flood areas. This paper provides a fast and novel flood detection method and applies it to Gaofen-3 SAR images. The fully convolutional network (FCN), a variant of VGG16, is utilized for flood mapping in this paper. Considering the requirement of flood detection, we fine-tune the model to get higher accuracy results with shorter training time and fewer training samples. Compared with state-of-the-art methods, our proposed algorithm not only gives robust and accurate detection results but also significantly reduces the detection time.

Description: Sensors, Vol. 18, Pages 1335: Exploring on the Sensitivity Changes of the LC Resonance Magnetic Sensors Affected by Superposed Ringing Signals Sensors doi: 10.3390/s18051335 Authors: Tingting Lin Kun Zhou Sijia Yu Pengfei Wang Ling Wan Jing Zhao LC resonance magnetic sensors are widely used in low-field nuclear magnetic resonance (LF-NMR) and surface nuclear magnetic resonance (SNMR) due to their high sensitivity, low cost and simple design. In magnetically shielded rooms, LC resonance magnetic sensors can exhibit sensitivities at the fT/√Hz level in the kHz range. However, since the equivalent magnetic field noise of this type of sensor is greatly affected by the environment, weak signals are often submerged in practical applications, resulting in relatively low signal-to-noise ratios (SNRs). To determine why noise increases in unshielded environments, we analysed the noise levels of an LC resonance magnetic sensor (L ≠ 0) and a Hall sensor (L ≈ 0) in different environments. The experiments and simulations indicated that the superposed ringing of the LC resonance magnetic sensors led to the observed increase in white noise level caused by environmental interference. Nevertheless, ringing is an inherent characteristic of LC resonance magnetic sensors. It cannot be eliminated when environmental interference exists. In response to this problem, we proposed a method that uses matching resistors with various values to adjust the quality factor Q of the LC resonance magnetic sensor in different measurement environments to obtain the best sensitivity. The LF-NMR experiment in the laboratory showed that the SNR is improved significantly when the LC resonance magnetic sensor with the best sensitivity is selected for signal acquisition in the light of the test environment. (When the matching resistance is 10 kΩ, the SNR is 3.46 times that of 510 Ω). This study improves LC resonance magnetic sensors for nuclear magnetic resonance (NMR) detection in a variety of environments.

Description: Edge detection in Synthetic Aperture Radar (SAR) images has been a challenging task due to the speckle noise. Ratio-based edge detectors are robust operators for SAR images that provide constant false alarm rates, but they are only optimal for step edges. Edge detectors developed by the phase congruency model provide the identification of different types of edge features, but they suffer from speckle noise. By combining the advantages of the two edge detectors, we propose a SAR phase congruency detector (SAR-PC). Firstly, an improved local energy model for SAR images is obtained by replacing the convolution of raw image and the quadrature filters by the ratio responses. Secondly, a new noise level is estimated for the multiplicative noise. Substituting the SAR local energy and the new noise level into the phase congruency model, SAR-PC is derived. Edge response corresponds to the max moment of SAR-PC. We compare the proposed detector with the ratio-based edge detectors and the phase congruency edge detectors. Receiver Operating Characteristic (ROC) curves and visual effects are used to evaluate the performance. Experimental results of simulated images and real-world images show that the proposed edge detector is robust to speckle noise and it provides a consecutive edge response.

Description: The Scale-Invariant Feature Transform (SIFT) algorithm and its many variants have been widely used in Synthetic Aperture Radar (SAR) image registration. The SIFT-like algorithms maintain rotation invariance by assigning a dominant orientation for each keypoint, while the calculation of dominant orientation is not robust due to the effect of speckle noise in SAR imagery. In this paper, we propose an advanced local descriptor for SAR image registration to achieve rotation invariance without assigning a dominant orientation. Based on the improved intensity orders, we first divide a circular neighborhood into several sub-regions. Second, rotation-invariant ratio orientation histograms of each sub-region are proposed by accumulating the ratio values of different directions in a rotation-invariant coordinate system. The proposed descriptor is composed of the concatenation of the histograms of each sub-region. In order to increase the distinctiveness of the proposed descriptor, multiple image neighborhoods are aggregated. Experimental results on several satellite SAR images have shown an improvement in the matching performance over other state-of-the-art algorithms.