Search

In on-street parking lots, it is very important to obtain the positions and license plate numbers of the vehicles for charging and management. Existing algorithms usually detect vehicles from an input image first, then localize their license plates, and finally recognize the license plate numbers. However, they are of high time and space complexity and cannot work if the vehicles or license plates are obscured. Therefore, this paper proposes an open-space vehicle positioning algorithm based on detection and tracking in video sequences. The work is as follows: (1) To reduce the time and space complexity, parallel detection of vehicles and license plates is carried out. Then, geometric matching is performed to accomplish the correspondences between them. (2) To track vehicles and license plates, this paper improves DeepSORT by combining with integrated voting based on the historical license plate library. (3) To accurately judge the vehicle behavior of entry or exit, a cumulative state detector is designed to increase the fault-tolerance of the proposed algorithm. The experimental results reveal that the proposed algorithm makes improvements in model parameters, inference speed, and tracking accuracy, demonstrating that it can be well applied to open-space vehicle positioning.

Flexible corrugated skins are ideal structures for morphing wings, and the associated load measurements are of great significance in structural health monitoring. This paper proposes a novel load-identification method for flexible corrugated skins based on improved Fisher discrimination dictionary learning (FDDL). Several fiber Bragg grating sensors are pasted on the skin to monitor the load on multiple corrugated crests. The loads on different crests cause nonuniform strain fields, and these discriminative spectra are recorded and used as training data. The proposed method involves load-positioning and load-size identification. In the load-size-identification stage, a classifier is trained for every corrugated crest. An interleaved block grouping of samples is introduced to enhance the discrimination of dictionaries, and a two-resolution load-size classifier is introduced to improve the performance and resolution of the grouping labels. An adjustable weight is introduced to the FDDL classification scheme to optimize the contribution from different sensors for different load-size classifiers. With the proposed method, the individual loads on eight crests can be identified by two fiber Bragg grating sensors. The positioning accuracy is 100%, and the mean error of the load-size identification is 0.2106 N, which is sufficiently precise for structural health monitoring.

Carbon-fiber aluminum honeycomb sandwich panels are vulnerable to low-velocity impacts, which can cause structural damage and failures that reduce the bearing performance and reliability of the structure. Therefore, a method for locating such impacts through a sensor network is very important for structural health monitoring. Unlike composite laminates, the stress wave generated by an impact is damped rapidly in a sandwich panel, meaning that the signal qualities measured by different sensors vary greatly, thereby making it difficult to locate the impact. This paper presents a method for locating impacts on carbon-fiber aluminum honeycomb sandwich panels utilizing fiber Bragg grating sensors. This method is based on a projective dictionary pair learning algorithm and uses structural sparse representation for impact localization. The measurement area is divided into several sub-areas, and a corresponding dictionary is trained separately for each sub-area. For each dictionary, the sensors are grouped into main sensors within the sub-area and auxiliary sensors outside the sub-area. A balancing weight factor is added to optimize the proportion of the two types of sensor in the recognition model, and the algorithm for determining the balancing weight factor is designed to suppress the negative effects on the positioning of the sensors with poor signal quality. The experimental results show that on a 300 mm × 300 mm × 15 mm sandwich panel, the impact positioning accuracy of this method is 96.7% and the average positioning error is 0.85 mm, which are both sufficient for structural health monitoring.

A magnetically-quiet environment is important for detecting faint magnetic-field signals or nonmagnetic spin-dependent interactions. Passive magnetic shielding using layers of large magnetic-permeability materials is widely used to reduce the magnetic-field noise. The magnetic-field noise can also be actively monitored with magnetometers and then compensated, acting as a complementary method to the passive shielding. We present here a general model to quantitatively depict and optimize the performance of active magnetic-field stabilization and experimentally verify our model using optically-pumped atomic magnetometers. We experimentally demonstrate a magnetic-field noise rejection ratio of larger than ∼800 at low frequencies and an environment with a magnetic-field noise floor of ∼40 fT/Hz1/2 in unshielded Earth’s field. The proposed model provides a general guidance on analyzing and improving the performance of active magnetic-field stabilization with magnetometers. This work offers the possibility of sensitive detections of magnetic-field signals in a variety of unshielded natural environments.