Visual simultaneous localization and mapping (VSLAM), which is a core technology for intelligent mobile robots, is typically based on static environment assumptions. However, it encounters challenges in dynamic scenes such as accurately distinguishing between static and dynamic feature points and high computational costs. These issues lead to significant deviations in camera tracking and introduce ghosting in mapping. To address these issues, we propose DMS-SLAM, a fast semantic visual SLAM based on deep mask segmentation. First, semantic segmentation is performed using the YOLOv8s-seg network, followed by a mask correction algorithm based on depth consistency and a missed detection compensation algorithm based on relative displacement invariance, ensuring precise segmentation of dynamic objects within the semantic thread. Then, the segmented objects are classified according to dynamic probability, and the motion of potential dynamic objects is determined through a depth mask association algorithm. Dynamic feature points are eliminated by utilizing epipolar geometric constraints to improve localization accuracy. Finally, local point clouds with dynamic objects removed are stitched together to construct a global dense point cloud map, presenting a static scene free of ghosting. Experiments on the Technical University of Munich RGB-D dataset and in real-world scenarios show that the method enhances absolute trajectory accuracy by an average of 96.19% and relative pose accuracy by 94.27% over the ORB-SLAM2 system in highly dynamic environments. Compared to other dynamic semantic visual SLAM algorithms, DMS-SLAM improves operational efficiency by over 51.78%, significantly reducing runtime and generating clear and accurate global 3D point cloud maps, which fully demonstrates its superiority in terms of accuracy, stability and efficiency.

Mini-cameras are one of several emerging types of cat-eye devices using small lenses with insufficient retro-reflection for traditional detection systems to identify. Based on a structural analysis of these devices, this paper provides an accurate theoretical description of the received beam profile. The simulated and experimental results have good similarity in terms of profile shapes and trends with different incident angles and defocus distances. An analysis of the detection conditions and the reflection image features described in this article can thus be applied to hidden camera detection. Mini-cameras can be detected according to these features of the received beam profiles.

In frequency-sweep polarization-modulation ranging, distance is determined by the frequency of modulated waves and the corresponding wavelength multiple when emitted and returned waves are in phase. However, measurement of the frequency and the wavelength multiple is affected by thermally induced phase delay of the polarized wave. In this article we systematically discuss the principle of the ranging method and analyze the influences of thermally induced phase delay. New approaches to measurement are proposed to eliminate the impact on frequency and the wavelength multiple. Theoretical analysis and experimental results proved the efficiency and applicability of the methods.

Efficient and stable path planning in dynamic and obstacle-dense environments, such as large-scale structure assembly measurement, is essential for improving the practicality and environmental adaptability of mobile robots in measurement and quality inspection tasks. However, traditional reinforcement learning methods often suffer from inefficient use of experience and limited capability to represent policy structures in complex dynamic scenarios. To overcome these limitations, this study proposes a method named DPDQN-TER that integrates Transformer-based sequence modeling with a multi-branch parameter policy network. The proposed method introduces a temporal-aware experience replay mechanism that employs multi-head self-attention to capture causal dependencies within state transition sequences. By dynamically weighting and sampling critical obstacle-avoidance experiences, this mechanism significantly improves learning efficiency and policy performance and stability in dynamic environments. Furthermore, a multi-branch parameter policy structure is designed to decouple continuous parameter generation tasks of different action categories into independent subnetworks, thereby reducing parameter interference and improving deployment-time efficiency. Extensive simulation experiments were conducted in both static and dynamic obstacle environments, as well as cross-environment validation. The results show that DPDQN-TER achieves higher success rates, shorter path lengths, and faster convergence compared with benchmark algorithms including Parameterized Deep Q-Network (PDQN), Multi-Pass Deep Q-Network (MPDQN), and PDQN-TER. Ablation studies further confirm that both the Transformer-enhanced replay mechanism and the multi-branch parameter policy network contribute significantly to these improvements. These findings demonstrate improved overall performance (e.g., success rate, path length, and convergence) and generalization capability of the proposed method, indicating its potential as a practical solution for autonomous navigation of mobile robots in complex industrial measurement scenarios.

In this study, we propose a frequency measurement and estimation approach based on a lock-in analysis for precise frequency determination in polarization-modulated ranging signals. In this method, the modulation signal of an electro-optic modulator (EOM) is manipulated to introduce an intermediate frequency (IF) component into the detected signal. Subsequently, the detected signal is analyzed using lock-in analysis techniques to extract the necessary frequency component, and a new swept frequency waveform is generated, facilitating the frequency acquisition and distance calculation. We conducted theoretical derivations, simulations and experiments to validate the effectiveness of this method. The research findings suggest that our method can enhance the accuracy of frequency measurements by a factor of approximately ten when compared to a direct detection approach, leading to a corresponding improvement in ranging precision. Furthermore, even with larger sweep step sizes and smaller modulation frequencies, the proposed approach can achieve superior ranging results.

The aspheric surface is a commonly used method to improve the imaging quality of the fisheye lens, but it is difficult to determine the position and initial value. Based on the wave aberration theory of the plane-symmetric optical system, a method of using an aspheric surface to design a fisheye lens is proposed, which can quickly determine the appropriate aspheric surface to improve the imaging performance. First, the wave aberration of each optical surface of the fisheye lens is calculated and its aberration characteristics are analyzed. Then, a numerical evaluation function is reported based on the aberration distribution of the fisheye lens on the image plane. According to the functional relationship between the evaluation function and the aspheric coefficient, the position of the aspheric surface and the initial value of the aspheric coefficient can be calculated. Finally, the adaptive and normalized real-coded genetic algorithm is used as the evaluation function to optimize the fisheye lens using an aspheric surface. The proposed method can provide an effective solution for designing a fisheye lens using an aspheric surface.