Salient object detection (SOD) has been widely used in practical applications, such as multisensor image fusion, remote sensing, and defect detection. Recently, SOD from RGB and thermal (T) has been rapidly developed due to its robustness to extreme situations, such as low illumination and occlusion. However, existing methods all utilize a dual-stream encoder, which significantly increases the computation burdens and hinders real-world deployment. To this end, we propose a real-time One-stream Semantic-guided Refinement Network (OSRNet) for RGB-T SOD. Specifically, we first fuse the RGB and T via concatenation, addition, and multiplication operations to dig the complementary information between each modality. The efficient early fusion not only facilitates the information exchange between each modality but also avoids the cumbersome dual-stream encoder structure. Then, the lightweight decoder is proposed, making the high-level semantic information filter the low-level noisy features and gradually refine the final prediction. Also, we apply deep supervision to make the training procedure more stable and fast. Due to the early fusion strategy, OSRNet can run at a real-time speed (53–60 fps) on a single GPU. Extensive quantitative and qualitative experiments show that our network outperforms 11 state-of-the-art methods in terms of seven evaluation metrics. Our codes have been released at https://github.com/huofushuo/OSRNet .

RGB-T salient object detection (SOD) aims at utilizing the complementary cues of RGB and Thermal (T) modalities to detect and segment the common objects. However, on one hand, existing methods simply fuse the features of two modalities without fully considering the characters of RGB and T. On the other hand, the high computational cost of existing methods prevents them from real-world applications (e.g., automatic driving, abnormal detection, person re-ID). To this end, we proposed an efficient encoder-decoder network named Context-guided Stacked Refinement Network (CSRNet). Specifically, we utilize a lightweight backbone and design efficient decoder parts, which greatly reduce the computational cost. To fuse RGB and T modalities, we proposed an efficient Context-guided Cross Modality Fusion (CCMF) module to filter the noise and explore the complementation of two modalities. Besides, Stacked Refinement Network (SRN) progressively refines the features from top to down via the interaction of semantic and spatial information. Extensive experiments show that our method performs favorably against state-of-the-art algorithms on RGB-T SOD task while with small model size (4.6M), few FLOPs (4.2G), and real-time speed (38 fps ). Our codes is available at: https://github.com/huofushuo/CSRNet .

Haze can seriously affect the visible and visual quality of outdoor optical sensor systems, e.g., driving assistance, remote sensing, and video surveillance. Single image dehazing is an intractable problem due to its ill-posed nature. The main idea of the paper is combining multi-scale fusion strategy and prior knowledge, thereby presenting balanced image contrast enhancement and intrinsic color preservation, efficiently. The atmospheric illumination prior (AIP) has been proved that haze mainly degrades the contrast of the luminance channel rather than chrominance channels in YCrCb colorspace. To this end, we firstly identify and remove the color veil (unbalanced color channel) with the white balance algorithm, to reduce the influence of unbalanced color channels neglected by the AIP. Considering the new observation that hazy regions exhibit low contrast with high-intensity pixels, the dense and mild haze are enhanced by a set of histogram modification techniques, respectively. Then, with the derived inputs, multi-scale fusion based on Laplacian decomposition strategy is proposed to blend visual contrast only in the luminance channel. Without relying on complex enhancement algorithms and only dealing with one channel, the proposed method is attractive for real-time applications. Moreover, The proposed method can be directly applied to the video sequences frame by frame, alleviating visual artifacts. The simulation results show that our method is comparative to and even better than the more complex state-of-the-art techniques.

Near-field phase measurements are often difficult and very time-consuming for real applications in comparison with phaseless ones. Meanwhile, it is also challenging, with global optimization or phase recovery algorithm implemented, to build an equivalent radiation model based on a dipole array through phaseless near-field data. The optimization and phase recovery algorithms have certain problems in the selections of dipole moment limits and local optimality, respectively. Here, a new hybrid equivalent modeling method of low-frequency radiation characteristics is proposed, which combines the Gerchberg-Saxton (GS) algorithm with adaptive differential evolution algorithm effectively. An initial set of dipole arrays with dipole position, array height, and dipole moment is obtained using the fast solution of the GS algorithm at first, and global optimization algorithm is further used to update the dipole arrays with the global seeking to improve both accuracy and efficiency of the equivalent modeling for the low-frequency radiation source. Such hybrid method can solve the problem of the GS algorithm, which is easy to fall into the local optimum, as well as the problem of global optimization algorithm not being able to quickly determine upper and lower bounds of dipole moments. Its effectiveness is verified by simulations as well as measurements.

Unexploded ordnance (UXO) survey is the foremost task of clearance project. Transient electromagnetic method (TEM) is proved effective for UXO survey. However, it is still difficult for TEM to detect small-size, ultra-shallow and dense UXO targets because the large-size devices and inversion methods for large-scale applications are usually ineffective. In the work, in order to avoid the complex inversion of apparent resistivity, the voltages acquired by our specified small-loop TEM system are used to depict a voltage distribution profile, which is then processed with an improved imaging algorithm. Several major influences on the secondary voltage image are discussed during UXO survey, including emitting coil size, target attitude, basin effect and shell thickness. Furthermore, an improved watershed imaging algorithm is proposed to obtain the best threshold marking and automatically realize the dense target discrimination. Oversegmentation resulting from burrs, noises, and scraps is reduced through background marking. And also under-segmentation is avoided during foreground marking through adaptive search of saddle point. The algorithm has been verified effective using simulation data and experiment data of UXO-like targets.

This paper focuses on the problem of the non-uniform magnetic field distribution in short-distance magnetic coupled wireless power transfer (MC-WPT) systems, which causes the transfer power and power transfer efficiency to decrease when the transmitter and receiver coils are offset. At first, the distribution law of the magnetic field generated by the printed circuit board (PCB) coil is studied. A new method is proposed to design the transmitter coil, which combines a genetic algorithm (GA) with a partial element equivalent circuit (PEEC). The appropriate turn radii are first obtained by the GA, and the quality factor is further evaluated by the PEEC to select the optimal coil turns. Finally, the PCB coils with uneven pitches are fabricated, and experiments are carried out on an MC-WPT system. The effective power transfer area is expanded noticeably and the high efficiency of the system remains stable, which is very useful to provide a wider working space and steady wireless energy supply for mobile objects.