Search

Loop closure detection (LCD), also known as place recognition, is a crucial component of visual simultaneous localization and mapping (vSLAM) systems, aiding in the reduction of cumulative localization errors on a global scale. However, changes in environmental appearance and differing viewpoints pose significant challenges to the accuracy of the LCD algorithm. Addressing this issue, this paper presents a novel end-to-end framework (MetricNet) for LCDs to enhance detection performance in complex scenes with distinct appearance variations. Focusing on deep features with high distinguishability, an attention-based Channel Weighting Module(CWM) is designed to adaptively detect salient regions of interest. In addition, a patch-by-patch Similarity Measurement Module (SMM) is incorporated to steer the network for handling challenging situations that tend to cause perceptual aliasing. Experiments on three typical datasets have demonstrated MetricNet's appealing detection performance and generalization ability compared to many state-of-the-art learning-based methods, where the mean average precision is increased by up to 11.92%, 18.10%, and 5.33% respectively. Moreover, the detection results on additional open datasets with apparent viewpoint variations and the odometry dataset for localization problems have also revealed the dependability of MetricNet under different adaptation scenarios. [ABSTRACT FROM AUTHOR]

To better harvest the kinetic energy of the human and broaden the energy harvest frequency band, a nonlinear piezo-electromagnetic composite human energy harvester (NPE-HEH) is proposed. A magnetic repulsion force between the two groups of magnets makes the energy harvester nonlinear. The excitation experiment and the actual experiment of the human are carried out for the harvester. The excitation experiment results show that there is an optimal resistance value of the harvester to maximize the output power value. When the excitation acceleration is 0.4 g and the excitation frequency is 9 Hz, the output voltage value and the output power of the electromagnetic part of the energy harvester are 0.86 V and 2.47 mW respectively, and the output performance is excellent. When the energy harvester is installed in a backpack with a moving speed of 9 km/h, it can generate 0.7 mW of power. When the energy harvester is placed on the leg, the output performance is good and the output power can reach 1.3 mW. The energy harvester can efficiently harvest energy at low frequencies. This harvester is efficient at low frequencies, compact in size, and easy to carry, making it highly suitable for human vibration energy harvesting applications. [ABSTRACT FROM AUTHOR]

In this article, a new type of piezoelectric energy harvester device is proposed, which has good output performance and can scavenge a large amount of vibration energy at low frequency. By setting up the experimental platform and testing, the results show that the external resistance, the mass of the cantilever end, the excitation acceleration and the magnet distance have an impact on the device. When the mass of the end of the cantilever beam is 15 g and the acceleration is 0.5 g, the output power of the device is 5.2 mW, and the output performance is good. [ABSTRACT FROM AUTHOR]

This paper proposes a Dual-Cylinder Piezoelectric Energy Harvester (DC-PEH). The cylinders generate vortex-induced vibration under the action of wind, driving the cantilever beam to deform. During the vibration process, the cantilever beam produces two types of bending modes, namely U-shaped vibration and S-shaped vibration. According to the experimental results, as the wind speed increases, the output power of the DC-PEH first increases and then decreases. When the diameter of the cylinders at both ends of the DC-PEH is 36 mm and the wind speed is 4.3 m/s, the output power can reach 7.812 mW. [ABSTRACT FROM AUTHOR]

This paper presents a magnetically coupling bending-torsion piezoelectric energy harvester based on vortex-induced vibration from low-speed wind. The theoretical model of the energy harvester was formulated and validated by wind tunnel experiments. Numerical and experimental results showed that the power output and bandwidth of the proposed harvester are improved about 180% and 230% respectively compared with the nonmagnetic coupling harvester. Furthermore, the effects of cylinder, piezoelectric layer, load resistance, and magnetic nonlinear parameters on the harvester were investigated based on the distributed parameter model. The results showed that the length of cylinder hardly affect output power, but the diameter of cylinder presented complicated influences. The width of piezoelectric beam was negatively correlated with the torsion angle. With increasing the length of piezoelectric layer, an optimal wind velocity and load resistance can be obtained for the maximum output power. With decreasing of the distance between two magnets, the resonant bandwidth, the optimal power output, and torsion angle can be enhanced, respectively. Besides, the magnetic potential energy increased owing to the magnetically coupling, which led to the improvement of onset speed for the energy harvester. This study provides a guideline on improving the performance of bending-torsion vibration piezoelectric energy harvester. [ABSTRACT FROM AUTHOR]