Search

Traffic sign detection is considered as one of the active research topics in transportation and computer vision. The previous works mainly focus on detecting traffic signs in images or in mobile light detection and ranging (LiDAR) data. In this paper, we propose a novel deep learning method to accurately detect traffic signs by fusing the complementary features from registered airborne geo-referenced color images and noisy airborne LiDAR data. Specifically, we first segment the airborne color images to road and non-road segments by integrating various local features in an inequality constraint quadratic optimization model. Next, we find the corresponding road regions in LiDAR data and extract high elevated objects above the road. We then segment the extracted objects to different regions corresponding to traffic sign candidates using Euclidean distance-based clustering. Finally, we find the corresponding traffic sign candidates in color images, extract their deep features, and represent them in a convex optimization model to classify the candidates. A set of extensive experiments have been carried out on the airborne geo-referenced color images and noisy airborne LiDAR data captured by Utah State University from I-15 highway. The results show the effectiveness of the proposed method in detecting traffic signs.

Sound barriers can be configured with different top edge impedance to improve their noise control performance. In this paper, the integral equation method was used to calculate the sound field of a barrier with various top edge impedance, and the effects of the barrier top edge impedance on sound barrier diffraction were investigated. The simulation results showed that the noise reduction performance of a sound barrier with a soft boundary on its top edge was larger than that with a hard boundary, but there were some impedance values which, if assigned to the top edge boundary, would give the sound barrier even better noise reduction performance. It was found that the sound barrier with a good top edge impedance formed a dipole-like radiation pattern above the barrier to expand the effective range of the shadow zone. The research discoveries reported in this paper point out the potentials of using acoustics metamaterials or active control methods to implement the desired good impedance on the top edge of a sound barrier for better noise reduction.

The presence of control signal feedback to the reference microphone in feedforward active control systems deteriorates the control performance. A four-stage method is proposed in this paper to carry out online feedback path modelling with the control signal. It consists of controller initialization, feedback path modelling using decorrelation filters, active control operation, and feedback path change detection for maintaining the control operation. In contrast to the existing auxiliary noise injection method, the proposed method uses five switches and three thresholds to control and maintain the system stability by avoiding the interference between control operation and feedback path modelling, and adaptive decorrelation filters are used to increase the feedback path modelling performance. Simulation results reveal that the proposed method is capable of tracking feedback path changes without injecting any auxiliary noise and maintaining the noise reduction performance and stability of the system.

It has been demonstrated that a single shunted loudspeaker can be used as an effective low frequency sound absorber in a duct, but many shunted loudspeakers have to be used in practice for noise reduction or reverberation control in rooms, thus it is necessary to understand the performance of an array of shunted loudspeakers. In this paper, a model for the parallel shunted loudspeaker array for multi-tone sound absorption is proposed based on a modal solution, and then the acoustic properties of a shunted loudspeaker array under normal incidence are investigated using both the modal solution and the finite element method. It was found that each shunted loudspeaker can work almost independently where each unit resonates. Based on the interaction analysis, multi-tone absorbers in low frequency can be achieved by designing multiple shunted loudspeakers with different shunt circuits respectively. The simulation and experimental results show that the normal incidence sound absorption coefficient of the designed absorber has four absorption peaks with values of 0.42, 0.58, 0.80, and 0.84 around 100 Hz, 200 Hz, 300 Hz, and 400 Hz respectively.