Emitter localization is an active research topic in electronic reconnaissance. Recently, passive synthetic aperture (PSA) is used to determine the azimuth and range distance of emitter. However, the existing methods approximate the distance equation of the spaceborne model through the airborne model, resulting in a large positioning error. In this paper, an emitter localization algorithm based on PSA in spaceborne model is proposed. First, the phase of the received signal is accumulated by using the symmetry of the Doppler history of the received signal in long synthetic aperture time, improving the azimuth positioning accuracy. The effective velocity is then used to establish the nonlinear equations of range distance. A modulus function is used to solve the equations, correcting the range positioning error in spaceborne model. Finally, the influence of noise, satellite position error, and satellite speed error on the positioning results is analyzed. The error matrix of proposed method in wide swath is obtained. Simulation results show that the positioning accuracy of this method is one order of magnitude higher than that of traditional single satellite positioning methods. The effectiveness of the proposed method is verified through actual satellite experiments.

Endovascular surgery is a high-risk operation with limited vision and intractable guidewires. At present, endovascular surgery robot (ESR) systems based on force feedback liberates surgeons’ operation skills, but it lacks the ability to combine force perception with vision. In this study, a deep learning-based guidewire-compliant control method (GCCM) is proposed, which guides the robot to avoid surgical risks and improve the efficiency of guidewire operation. First, a deep learning-based model called GCCM-net is built to identify whether the guidewire tip collides with the vascular wall in real time. The experimental results in a vascular phantom show that the best accuracy of GCCM-net is 94.86 ± 0.31%. Second, a real-time operational risk classification method named GCCM-strategy is proposed. When the surgical risks occur, the GCCM-strategy uses the result of GCCM-net as damping and decreases the robot’s running speed through virtual resistance. Compared with force sensors, the robot with GCCM-strategy can alleviate the problem of force position asynchrony caused by the long and soft guidewires in real-time. Experiments run by five guidewire operators show that the GCCM-strategy can reduce the average operating force by 44.0% and shorten the average operating time by 24.6%; therefore the combination of vision and force based on deep learning plays a positive role in improving the operation efficiency in ESR.

Contourlets have been attracting increasing attention in despeckling of synthetic aperture radar (SAR) images in recent years. However, contourlets produce undesirable artifacts while despeckling. This letter presents a novel contourlet-based regularization method to remove speckle without introducing extra artifacts. In this method, a nonlocal regression function is constructed for the regularization term through patch weighting on the contourlet reconstruction. Moreover, by employing the intrinsic dependence of contourlet coefficients, a parameterized shrinkage algorithm is proposed to resolve the contourlet reconstruction. This contourlet despeckling method enables significant elimination of speckle and resultant artifacts with well-protected strong scatters and structures of the scene. Experiments demonstrate such superiority on real SAR images.

Stereo vision technology based on line structured light can effectively solve the problem of a three-dimensional (3D) reconstruction of a smooth surface. A method for 3D reconstruction of mobile binocular stereo vision based on push-broom line structured light for a workpiece surface is presented in this paper. The subpixel coordinates of the light strip centers of the line structured light are obtained by the Steger algorithm while the binocular module moves along the guide rail, and the polar constraint is used to achieve the matching of the extracted light strip centers. As a result, the 3D coordinates of the light strip centers in each location can be calculated because of the known interior and external parameters of the binocular module. To obtain the 3D point cloud data of the entire surface, a relative pose optimization method with respect to the initial frame is proposed, which accurately estimates the pose of the cameras in each location with respect to that in the initial location and unifies the 3D coordinates of the light strip centers in each location to the datum coordinates. The relative pose optimization method first estimates the rough values by using the direct linear transform method, and then iteratively calculates the refined solutions based on the principle of minimizing the re-projection errors. Simulation data and substantial experimental results validate the effectiveness of our method. Our method is compared to the direct linear transform method and the frame-by-frame transfer method, and the root mean square error (RMSE) of the distance from 3D point cloud to fitted plane is used to evaluate the 3D reconstruction accuracy. The repeatability experiment shows that the RMSE from our method is as low as 0.83 mm.

Composite indoor human activity recognition is very important in elderly health monitoring and is more difficult than identifying individual human movements. This article proposes a sensor-based human indoor activity recognition method that integrates indoor positioning. Convolutional neural networks are used to extract spatial information contained in geomagnetic sensors and ambient light sensors, while transform encoders are used to extract temporal motion features collected by gyroscopes and accelerometers. We established an indoor activity recognition model with a multimodal feature fusion structure. In order to explore the possibility of using only smartphones to complete the above tasks, we collected and established a multisensor indoor activity dataset. Extensive experiments verified the effectiveness of the proposed method. Compared with algorithms that do not consider the location information, our method has a 13.65% improvement in recognition accuracy.